" - "A Data-driven Cross-tissue Machine Learning Framework for Inverse design of 3D (Bio)printing Scaffolds " - "For more details, please refer to and cite our paper: " - "https://doi.org/xxx" - "
", - unsafe_allow_html=True -) - -st.subheader("Biomaterials (enter range for each)") -if st.button("β Add Biomaterial"): - used = {r['mat'] for r in st.session_state.bio_rows} - available = [m for m in BIOMATERIAL_OPTIONS if m not in used] - if available: - st.session_state.bio_rows.append({ - 'mat': available[0], 'min': 0.0, 'max': 10.0, 'step': 0.1 - }) - st.rerun() - -for i, row in enumerate(st.session_state.bio_rows): - used_except_current = { - r['mat'] for idx, r in enumerate(st.session_state.bio_rows) if idx != i - } - options = [m for m in BIOMATERIAL_OPTIONS if m not in used_except_current] - - c1, c2, c3, c4, c5 = st.columns([2, 1, 1, 1, 0.3]) - mat = c1.selectbox( - "Biomaterial", options, - index=options.index(row['mat']) if row['mat'] in options else 0, - key=f"bio_mat_{i}", - label_visibility="collapsed", - ) - st.session_state.bio_rows[i]['mat'] = mat - - mn = c2.number_input( - "Min", min_value=0.0, max_value=row['max'], - value=row['min'], step=row['step'], key=f"bio_min_{i}" - ) - mx = c3.number_input( - "Max", min_value=row['step'], max_value=100.0, - value=max(row['max'], row['step']), step=row['step'], - key=f"bio_max_{i}" - ) - st.session_state.bio_rows[i].update(min=mn, max=mx) - - st.session_state.bio_rows[i]['step'] = c4.number_input( - "Step", min_value=0.0, - max_value=(mx - mn) if mx > mn else 0.1, - value=row['step'], step=0.1, key=f"bio_step_{i}" - ) - - if c5.button("β", key=f"rem_{i}"): - st.session_state.bio_rows.pop(i) - st.rerun() - -st.markdown("---") - -st.subheader("Cell Line & Density (10^6 cells/ml)") -col1, col2, col3, col4 = st.columns([2,1,1,1]) - -cell_line = col1.selectbox("Cell Line", CELL_LINE_OPTIONS, key="cell_line_select") - -if cell_line == "NoCellCultured": - st.info("π§ͺ **Acellular 3D printing mode** β No cells will be included. Cell density is forced to 0.") - st.session_state.density_range.update({'min': 0.0, 'max': 0.0, 'step': 0.0}) - - col2.number_input("Min Density", value=0.0, disabled=True, key="cd_min") - col3.number_input("Max Density", value=0.0, disabled=True, key="cd_max") - col4.number_input("Step", value=0.0, disabled=True, key="cd_step") -else: - if st.session_state.density_range.get('max', 0) <= 0.1: - st.session_state.density_range.update({'min': 1.0, 'max': 20.0, 'step': 0.5}) - - dr = st.session_state.density_range - dmin = col2.number_input( - "Min Density", - min_value=0.0, - max_value=dr['max'], - value=dr['min'], - step=dr['step'], - key="cd_min" - ) - dmax = col3.number_input( - "Max Density", - min_value=dr['step'], - max_value=1000.0, - value=max(dr['max'], dr['step']), - step=dr['step'], - key="cd_max" - ) - dstep = col4.number_input( - "Step", - min_value=0.0, - max_value=(dmax - dmin) if dmax > dmin else 0.1, - value=dr['step'], - step=0.1, - key="cd_step" - ) - st.session_state.density_range.update({'min': dmin, 'max': dmax, 'step': dstep}) - -st.markdown("---") - -st.subheader("Crosslinking Settings") - -col_cross1, col_cross2 = st.columns(2) - -disable_physical = col_cross1.checkbox( - "Disable Physical Crosslinking", - value=False, - help="Check if you do not want physical/ionic crosslinking (e.g. CaClβ bath, temperature-induced)" -) - -disable_photo = col_cross2.checkbox( - "Disable Photo Crosslinking", - value=False, - help="Check if you do not want UV/visible light crosslinking" -) - -st.subheader("Printing Parameters (enter range)") - -for name in PRINT_PARAM_NAMES: - if name == "Physical Crosslinking Duration (s)" and disable_physical: - st.session_state.pp_ranges[name].update({'min': 0.0, 'max': 0.0, 'step': 0.0}) - c1, c2, c3, c4 = st.columns([2,1,1,1]) - c1.write(name + " (DISABLED)") - c2.number_input("Min", value=0.0, disabled=True, key=f"pp_min_{name}") - c3.number_input("Max", value=0.0, disabled=True, key=f"pp_max_{name}") - c4.number_input("Step", value=0.0, disabled=True, key=f"pp_step_{name}") - continue - - elif name == "Photo Crosslinking Duration (s)" and disable_photo: - st.session_state.pp_ranges[name].update({'min': 0.0, 'max': 0.0, 'step': 0.0}) - c1, c2, c3, c4 = st.columns([2,1,1,1]) - c1.write(name + " (DISABLED)") - c2.number_input("Min", value=0.0, disabled=True, key=f"pp_min_{name}") - c3.number_input("Max", value=0.0, disabled=True, key=f"pp_max_{name}") - c4.number_input("Step", value=0.0, disabled=True, key=f"pp_step_{name}") - continue - - pmin = st.session_state.pp_ranges[name]['min'] - pmax = st.session_state.pp_ranges[name]['max'] - pstep = st.session_state.pp_ranges[name]['step'] - - c1, c2, c3, c4 = st.columns([2,1,1,1]) - c1.write(name) - - pmin = c2.number_input( - "Min", min_value=0.0, max_value=pmax, - value=pmin, step=pstep, key=f"pp_min_{name}" - ) - pmax = c3.number_input( - "Max", min_value=pstep, max_value=10000.0, - value=max(pmax, pstep), step=pstep, key=f"pp_max_{name}" - ) - pstep = c4.number_input( - "Step", min_value=0.0, - max_value=(pmax - pmin) if pmax > pmin else 1.0, - value=pstep, step=max(1e-3, pstep/10), - key=f"pp_step_{name}" - ) - st.session_state.pp_ranges[name].update(min=pmin, max=pmax, step=pstep) -st.markdown("---") - -if st.button("Optimize WSSQ"): - with st.spinner("Running Optunaβ¦"): - try: - model_print = load_prediction_model( - print_model_options[selected_print_model_name], - "printability", - preprocessed_input_dim, - len(label_encoder_print.classes_), - ) - model_cell = load_prediction_model( - cell_model_options[selected_cell_model_name], - "cell_response", - preprocessed_input_dim, - len(label_encoder_cell.classes_), - ) - except Exception as exc: - st.error( - "Could not load the selected prediction model. This model will only work when the " - "running environment matches the saved artifact dependencies. For HistGradientBoosting, " - "use numpy>=2.0 in the Python environment that runs Streamlit.\n\n" - f"Details:\n{exc}" - ) - st.stop() - - def objective(trial): - bi_vals = { - r['mat']: trial.suggest_float( - f"bio__{r['mat']}", r['min'], r['max'], step=r['step'] - ) - for r in st.session_state.bio_rows - } - for m in BIOMATERIAL_OPTIONS: - bi_vals.setdefault(m, 0.0) - - cd = 0.0 if cell_line=="NoCellCultured" else trial.suggest_float( - "cell_density", dr['min'], dr['max'], step=dr['step'] - ) - - pp_vals = { - name: trial.suggest_float( - f"pp__{name}", - st.session_state.pp_ranges[name]['min'], - st.session_state.pp_ranges[name]['max'], - step=st.session_state.pp_ranges[name]['step'] - ) - for name in PRINT_PARAM_NAMES - } - - feat = {**bi_vals, **pp_vals} - feat["Cell Density (cells/mL)"] = cd - feat["Cell Line"] = cell_line - - X = pd.DataFrame([feat]).reindex(columns=feature_cols, fill_value=0.0) - - exp_p = expected_class_value(model_print, X, preprocessor, label_encoder_print) - exp_c = expected_class_value(model_cell, X, preprocessor, label_encoder_cell) - - np.random.seed(42) - # Use dynamic weights from the sidebar sliders - return scaffold_quality_combined( - exp_p, - exp_c, - weight_printability=w_print, - weight_cell_response=w_cell - ) - - sampler = optuna.samplers.TPESampler( - seed=42, - n_startup_trials=30, - multivariate=True, - group=True, - consider_prior=True - ) - - study = optuna.create_study( - direction="maximize", - sampler=sampler, - pruner=optuna.pruners.MedianPruner() - ) - study.optimize(objective, n_trials=int(n_trials)) - - # Store results in session state to persist after rerun - st.session_state.best_params = study.best_trial.params - st.session_state.best_value = study.best_trial.value - st.session_state.optimized_cell_line = cell_line - -if 'best_params' in st.session_state: - st.success(f"Best WSSQ: **{st.session_state.best_value:.3f}**") - best_df = pd.Series(st.session_state.best_params, name="value") \ - .rename_axis("parameter") \ - .to_frame() - st.table(best_df) - - st.markdown("---") - st.subheader("Customize Fabrication Protocol") - user_inquiry = st.text_area( - "Add specific limitations, equipment, or extra requirements:", - placeholder="e.g., I only have a 25G nozzle available, or I need to use a specific UV intensity of 10mW/cmΒ²...", - key="user_inquiry" - ) - - if st.button("Generate Fabrication Procedure"): - if not gemini_key: - st.error("Please enter your Gemini API key in the sidebar before generating a fabrication procedure.") - st.stop() - - with st.spinner("Generating rigorous fabrication procedureβ¦"): - client = genai.Client(api_key=gemini_key) - - formatted_params = "\n".join([ - f"- {k.replace('bio__', 'Biomaterial: ').replace('pp__', 'Print Setting: ')}: {v:.2f}" - for k, v in st.session_state.best_params.items() - ]) - - # Base prompt (remains unchanged) - base_prompt = ( - f"Please act as a senior tissue engineer with 15+ years of hands-on experience in 3D bioprinting for regenerative medicine. " - f"Write a **highly practical, bench-ready laboratory fabrication protocol** for fabricating a scaffold. " - f"Assume the reader is an experienced experimentalist who routinely works in a tissue engineering lab.\n\n" - f"**Use exactly these inputs to tailor every step:**\n" - f"Target Cell Line: {st.session_state.optimized_cell_line}\n" - f"Parameters:\n{formatted_params}\n\n" - f"**Critical requirements for the protocol (you MUST follow all of them):**\n" - f"β’ If Target Cell Line is 'NoCellCultured', this is **acellular 3D printing** (not bioprinting). Remove all references to cells, cell viability, cell density, and cell culturing. The final scaffold is cell-free. Change section 6 title to 'Post-Printing Incubation & Storage Instructions' and adapt its content accordingly.\n" - f"β’ If any suggested parameter is physically unrealistic (e.g. nozzle diameter 9 Β΅m or syringe temp 2Β°C) or the nozzle diameter is very small relative to the cell diameter of the target cell line (when cells are used), adjust it slightly in the protocol and explicitly note the adjustment with justification.\n" - f"β’ Every quantity must be given in precise, measurable lab units (e.g., 2.5 mL, 1.2 % w/v, 10 mg/mL, 37 Β°C, 5 min, 150 rpm).\n" - f"β’ Include exact timings, temperatures, and workflow order to protect structural fidelity (and cell viability >85 % post-print when cells are used).\n" - f"β’ Anticipate and explicitly address common bioprinting pitfalls relevant to the given parameters (nozzle clogging, shear-induced cell death, premature gelation, filament fusion, air bubbles, etc.) and give precise mitigation steps.\n" - f"β’ Use only reagents and equipment that are standard in tissue engineering labs; if a specific brand/model is implied by the parameters, note a common equivalent.\n" - f"β’ Include simple quality-control checkpoints (visual inspection, live/dead staining timing when cells are used, etc.).\n\n" - f"Your response must be structured **exactly** with the following sections (no extra sections, no introductory text, no summary, no conclusions):\n" - f"1. Required Materials & Equipment\n" - f"2. Sterilization & Safety Precautions\n" - f"3. Bioink Preparation\n" - f"4. 3D Bioprinting Settings & Execution\n" - f"5. Post-processing & Crosslinking\n" - f"6. Cell Culturing & Incubation Instructions\n" - ) - - # Append user inquiry if provided - final_prompt = base_prompt - if user_inquiry: - final_prompt += f"\n**Additional User Constraints & Inquiries (Integrate these into the protocol):**\n{user_inquiry}" - - resp = client.models.generate_content( - model=gemini_model, - contents=final_prompt, - config=types.GenerateContentConfig( - system_instruction=( - "You are a senior tissue engineer and expert experimentalist specializing in translating optimized bioprinting parameters into reproducible, high-viability laboratory protocols. " - "Your protocols are used daily by PhD students and post-docs in regenerative medicine labs. " - "You always prioritize: (1) maximum cell viability and function, (2) structural fidelity of the printed construct, (3) workflow efficiency under sterile conditions, and (4) safety. " - "Write in clear, imperative, step-by-step language with numbered or bulleted sub-steps. " - "Never be vague β give exact volumes, times, temperatures, speeds, and concentrations. " - "Never add disclaimers or theoretical background unless explicitly asked." - ), - temperature=0.1, - top_p=0.85, - max_output_tokens=6144 - ) - ) - - st.markdown("## Fabrication Procedure") - st.markdown(resp.text) +""" +MLATE V3 β scaffold optimisation and protocol generation +======================================================== + + streamlit run 06_webapp/app.py + +A thin interface over `mlate.optimize`, `mlate.wssq` and `mlate.protocol`. The +previous release put the objective function, the WSSQ formula and the language +model call inside this file, which meant none of them could be run, tested or +reported without launching a browser. Everything scientific now lives in the +package; this file collects inputs, calls it, and displays the result. + +Deployable to a Hugging Face Space: model artefacts are located relative to +this file, and the only corpus data required at run time is the trimmed +reference table that `build_app_data.py` writes beside the app. +""" + +from __future__ import annotations + +import json +import sys +from pathlib import Path +from types import SimpleNamespace + +import joblib +import numpy as np +import pandas as pd +import streamlit as st + +HERE = Path(__file__).resolve().parent +sys.path.insert(0, str(HERE.parent)) +sys.path.insert(0, str(HERE)) + +from mlate import config as cfg # noqa: E402 +from mlate import optimize as opt # noqa: E402 +from mlate import protocol as proto # noqa: E402 +from mlate import serving # noqa: E402 +from mlate import wssq as wssq_mod # noqa: E402 + +from biomaterials import BIOMATERIAL_OPTIONS, BIOMATERIAL_RANGES # noqa: E402 +from cell_lines import (ACELLULAR_TOKEN, CELL_DENSITY_RANGES, # noqa: E402 + CELL_LINE_COUNTS, CELL_LINE_OPTIONS) +from model_performance import (PERFORMANCE_GUIDE, # noqa: E402 + PERFORMANCE_GUIDE_FULL) + +st.set_page_config(page_title="MLATE V3", page_icon="π§¬", layout="wide") + +# Deployment layout: a Space carries deploy/models next to the app, a checkout +# has it at the repository root. Both are tried so the same file runs in either. +MODEL_ROOTS = [HERE / "deploy" / "models", cfg.ROOT / "deploy" / "models"] +PRINT_PARAMS = ["Physical Crosslinking Duration (s)", + "Photo Crosslinking Duration (s)", + "Extrusion Pressure (kPa)", + "Nozzle Movement Speed (mm/s)", + "Nozzle Diameter (Β΅m)", + "Syringe Temperature (Β°C)", + "Substrate Temperature (Β°C)"] +CROSSLINK = PRINT_PARAMS[:2] +PROTOCOL_PARAMS = PRINT_PARAMS[2:] + + +def models_root() -> Path | None: + for r in MODEL_ROOTS: + if (r / "classifiers").exists(): + return r + return None + + +# ββ loading ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ + +@st.cache_resource(show_spinner=False) +def load_preprocessor(): + """The release preprocessor, fitted on every row for inference.""" + root = models_root() + d = root / "preprocessors" + return (joblib.load(d / "preprocessor.pkl"), + joblib.load(d / "input_columns.pkl")) + + +@st.cache_resource(show_spinner=False) +def load_manifest() -> dict: + root = models_root() + p = root / "deployment_manifest.json" + return json.loads(p.read_text(encoding="utf-8")) if p.exists() else {} + + +@st.cache_data(show_spinner=False) +def available_models(task: str) -> list[dict]: + """ + Every model offered for one target, ranked by benchmarked weighted F1. + + All three families, not only the pickled classifiers: the previous release + listed the conventional models alone, which meant TabICL - the strongest + printability model on the benchmark - was exported, reported and then not + offered. Discovery costs a filename parse; an estimator is opened when it + is chosen. + + Random-split artefacts only. The application serves prediction inside the + design space the corpus covers - adjusting a concentration, swapping a cell + line, moving a pressure within observed ranges - which is the interpolation + regime the random protocol estimates. The study-grouped models are the + conservative bound for an unseen laboratory and are reported in the + manuscript, but they are tuned for a harder task than the one performed + here. The foundation models are split-independent and appear under both. + """ + root = models_root() + if root is None: + return [] + return [{"name": st_.name, "family": st_.family, "path": str(st_.path), + "weighted_f1": st_.weighted_f1, "cost": st_.cost_hint} + for st_ in serving.discover(root, task, "random")] + + +def model_label(entry: dict) -> str: + """Menu text: the model, what kind it is, and what it scored.""" + kind = {"ml": "", "dl": " Β· deep", "foundation": " Β· foundation"} + return (f"{entry['name']}{kind.get(entry['family'], '')} Β· " + f"F1 {entry['weighted_f1']:.3f}") + + +@st.cache_resource(show_spinner=False) +def load_model(path_str: str, family: str): + """ + Open one artefact. Cached, because a foundation model re-supplies its + 2,646-row context on first use and there is no reason to pay that twice. + """ + return serving.load(Path(path_str), family) + + +@st.cache_data(show_spinner=False) +def load_corpus() -> tuple[pd.DataFrame | None, object]: + """ + The observed formulations, shipped beside the app by `build_app_data.py`. + + Needed for the two checks that a prediction alone cannot make: how far the + proposed formulation sits from anything published, and which real + formulations are closest to it. Returns (None, None) if the file is absent + rather than failing, so the application still optimises; the interface then + says the check could not be performed instead of implying it passed. + """ + table, meta = HERE / "corpus_reference.parquet", HERE / "corpus_reference.json" + if not (table.exists() and meta.exists()): + return None, None + groups = json.loads(meta.read_text(encoding="utf-8")) + return pd.read_parquet(table), SimpleNamespace(**groups) + + +@st.cache_data(show_spinner=False, ttl=3600) +def list_llms() -> tuple[list[tuple], bool]: + """ + The language models on offer, checked against OpenRouter's live catalogue. + + Checked rather than trusted because the catalogue turns over quickly: five + of the eleven identifiers shipped with the previous revision had been + withdrawn within weeks, and a withdrawn identifier fails only when the user + presses Generate, after an optimisation has already been paid for. Cached + for an hour so the check costs one request per session. + + No key is passed. The catalogue is public, and Streamlit's cache is shared + across every session of a deployment, so a secret used as a cache key would + be a secret held on behalf of all of them. + """ + return proto.available_models(None) + + +# ββ help dialogs βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ + +@st.dialog("Weighted Synergistic Scaffold Quality (WSSQ)", width="large") +def show_wssq_guidance(): + st.markdown( + """ +WSSQ combines **printability** and **cell response** into a single score the +optimiser can maximise. + +Both components are combined by two *conjunctive* means β a weighted harmonic +mean and a weighted geometric mean, averaged. Conjunctive means collapse toward +zero if either component does, so neither objective can be traded away: a +scaffold that prints perfectly but supports no cells does not score well. An +ordinary average would allow exactly that. + +Two boundary rules apply. A formulation that does not extrude (printability 0) +scores 0. An **acellular** formulation has no cell response to assess, so it is +scored on printability alone rather than being penalised for a biological +outcome that does not apply to it. + +The **cell-response weight** below is yours to set. Cell response carries more +than biology: pore size, porosity, interconnectivity and stiffness are not known +before fabrication and cannot be model inputs, but they strongly shape how cells +behave, so cell response acts as a proxy for them. + """) + + +@st.dialog("Choosing a model", width="large") +def show_model_guidance(): + st.markdown( + "Ranked by weighted F1 on the held-out test partition of the " + "random split (n = 530 records per target).\n\n" + "All three families are offered: the conventional classifiers, the six " + "deep networks, and the three in-context foundation models. The " + "highest-ranked model appears first in each menu.\n\n" + "**What the choice costs.** A foundation model carries the corpus " + "rather than fitted parameters and re-reads all 2,646 records on every " + "pass, so it is slower than a conventional classifier - measured at " + "about 1 s per batch of candidates on a GPU and about 17 s without " + "one, against 80 ms. Candidates are scored in batches of 32 precisely " + "so that this is paid once per batch rather than once per candidate; a " + "150-trial search is a few seconds with a conventional model, under a " + "minute with a foundation model on a GPU, and around three minutes on " + "CPU.\n\n" + "Models are refitted on the complete dataset for deployment. If one " + "fails to load because of a local package-version mismatch, choose the " + "next in the list.") + tp, tc = st.tabs(["Printability", "Cell Response"]) + with tp: + st.markdown(PERFORMANCE_GUIDE["printability"]) + with st.expander("All models"): + st.markdown(PERFORMANCE_GUIDE_FULL["printability"]) + with tc: + st.markdown(PERFORMANCE_GUIDE["cell_response"]) + with st.expander("All models"): + st.markdown(PERFORMANCE_GUIDE_FULL["cell_response"]) + + +@st.dialog("Optimisation trials") +def show_trial_guidance(): + st.markdown( + "Each trial is one candidate formulation, scored by the two models " + "and combined into WSSQ. The search is Bayesian: it models which " + "regions of the space produce good scores and samples there, so later " + "trials are better targeted than earlier ones.\n\n" + "The first 30 trials or so explore broadly and their scores mean " + "little on their own. **100 to 300 trials** is a reasonable range; " + "more trials help most when many variables are being searched at once.") + + +@st.dialog("Getting an OpenRouter API key", width="large") +def show_api_key_guidance(): + st.markdown( + """ +Protocol generation calls a language model through **OpenRouter**, which +provides access to models from many vendors β Anthropic, OpenAI, Google, Meta, +DeepSeek, Mistral and others β through a single key. Nothing else in this +application requires a key: prediction and optimisation run entirely locally. + +**To obtain a key** + +1. Go to **openrouter.ai** and create an account. +2. Open **Keys** from the account menu and choose **Create Key**. +3. Copy the key and paste it into the sidebar field. It is held only for this + browser session and is never stored or logged. + +**Free models.** Models whose name ends in `:free` cost nothing and need no +credit. They are the right place to start, but they are shared and heavily +rate-limited: a request may be refused outright when the model is busy, and the +remedy is to wait a minute or pick another. For routine use, add a small amount +of credit under **Credits**; a protocol typically costs well under one cent on +the mid-range models. + +**Choosing a model.** The menu lists a curated selection with a note on each, +filtered against OpenRouter's live catalogue so that a model withdrawn since +this release does not appear. Stronger reasoning models follow the protocol's +constraints more reliably β particularly the instruction to report an +implausible parameter rather than quietly correct it, and the instruction not +to invent supplier names or catalogue numbers. + """) + + +# ββ sidebar ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ + +root = models_root() +if root is None: + st.error( + "No model artefacts found. Expected `deploy/models/` beside this file " + "or at the repository root. Run `python 06_webapp/export_deployment.py` " + "to create them.") + st.stop() + +st.sidebar.header("Optimisation weights") +w_cell_pct = st.sidebar.slider( + "Cell-response weight (%)", 0, 100, 70, 5, + help="Printability weight is the remainder.") +w_print_pct = 100 - w_cell_pct +st.sidebar.number_input("Printability weight (%)", value=w_print_pct, + disabled=True) +if st.sidebar.button("What is WSSQ?", use_container_width=True): + show_wssq_guidance() + +st.sidebar.header("Models") +print_models = available_models("printability") +cell_models = available_models("cell_response") +if not print_models or not cell_models: + st.error("Model artefacts are present but none could be loaded.") + st.stop() + +def default_index(entries: list[dict]) -> int: + """ + Which model the menu opens on. + + The highest-ranked model overall when a GPU is present. On a CPU host - a + free Hugging Face Space, or most laptops - the highest-ranked model that is + not a foundation model, because an in-context model re-reads its whole + context on every pass and turns a search that takes seconds into one taking + minutes. The foundation models stay in the menu with their cost stated; the + difference is only what a first-time visitor is given before choosing. + """ + if serving.device() == "cuda": + return 0 + return next((i for i, e in enumerate(entries) + if e["family"] != "foundation"), 0) + + +print_entry = st.sidebar.selectbox( + "Printability model", print_models, format_func=model_label, + index=default_index(print_models)) +cell_entry = st.sidebar.selectbox( + "Cell-response model", cell_models, format_func=model_label, + index=default_index(cell_models)) +if "foundation" in (print_entry["family"], cell_entry["family"]): + st.sidebar.caption( + f"Foundation model selected - {print_entry['cost']}. These carry the " + f"corpus rather than fitted parameters and re-read it on every pass, " + f"so a search is slower than with a conventional classifier and much " + f"slower without a GPU.") +if st.sidebar.button("Model performance", use_container_width=True): + show_model_guidance() + +st.sidebar.header("Search") +n_trials = st.sidebar.number_input("Optimisation trials", 20, 2000, 150, 10) +if st.sidebar.button("How many trials?", use_container_width=True): + show_trial_guidance() + +st.sidebar.header("Protocol generation") +# Never prefilled from the server's own key. `type="password"` masks a value +# on screen but still sends it to the browser, so prefilling would hand the +# operator's key to every visitor of a public deployment. A key configured on +# the server remains usable - `proto.api_key` falls back to it when this field +# is empty - but it is never transmitted. +api_key_input = st.sidebar.text_input( + "OpenRouter API key", type="password", + help="Needed only for protocol generation. Held for this browser session " + "only; never stored or logged.") +if not api_key_input and proto.api_key(): + st.sidebar.caption("A key is configured on the server; leave this blank " + "to use it.") +llm_models, llm_verified = list_llms() +model_labels = [f"{m} Β· {tier}" for m, _, tier, _ in llm_models] +llm_idx = st.sidebar.selectbox( + "Language model", range(len(model_labels)), + format_func=lambda i: model_labels[i], + index=next((i for i, m in enumerate(llm_models) + if m[0] == proto.DEFAULT_MODEL), 0)) +llm_model, _vendor, _tier, llm_note = llm_models[llm_idx] +st.sidebar.caption( + llm_note if llm_verified + else f"{llm_note} \n_Availability unconfirmed: the OpenRouter " + f"catalogue could not be reached._") +if st.sidebar.button("How to get a key", use_container_width=True): + show_api_key_guidance() + +# ββ main βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ + +st.title("MLATE: Machine Learning Applications in Tissue Engineering") +st.markdown( + "Define the ranges you can work within, and the optimiser searches them for " + "the formulation with the highest predicted scaffold quality. Predictions " + "come from models trained on 2,646 scaffold records extracted from the " + "literature, and are decision support rather than validated outcomes.") + +if "bio_rows" not in st.session_state: + st.session_state.bio_rows = [ + {"mat": "Alginate (%w/v)", "min": 1.0, "max": 6.0, "step": 0.5}] + +st.subheader("Biomaterials") +st.caption("Give a range for each component. The optimiser searches within it.") +c1, c2 = st.columns([1, 5]) +if c1.button("Add biomaterial"): + remaining = [m for m in BIOMATERIAL_OPTIONS + if m not in {r["mat"] for r in st.session_state.bio_rows}] + if remaining: + st.session_state.bio_rows.append( + {"mat": remaining[0], "min": 0.0, "max": 5.0, "step": 0.5}) +if c2.button("Clear all") and st.session_state.bio_rows: + st.session_state.bio_rows = [] + +for i, row in enumerate(list(st.session_state.bio_rows)): + a, b, c, d, e = st.columns([4, 1.4, 1.4, 1.4, 0.8]) + row["mat"] = a.selectbox("Material", BIOMATERIAL_OPTIONS, + index=BIOMATERIAL_OPTIONS.index(row["mat"]) + if row["mat"] in BIOMATERIAL_OPTIONS else 0, + key=f"mat{i}", label_visibility="collapsed") + obs = BIOMATERIAL_RANGES.get(row["mat"]) + row["min"] = b.number_input("min", value=float(row["min"]), step=0.1, + key=f"lo{i}") + row["max"] = c.number_input("max", value=float(row["max"]), step=0.1, + key=f"hi{i}") + row["step"] = d.number_input("step", value=float(row["step"]), step=0.1, + min_value=0.01, key=f"st{i}") + if e.button("β", key=f"rm{i}"): + st.session_state.bio_rows.pop(i) + st.rerun() + if obs: + note = (f"observed in corpus: {obs['min']:.3g} β {obs['max']:.3g} " + f"(median {obs['median']:.3g}, n = {obs['n']})") + if row["max"] > obs["max"] or (row["min"] > 0 + and row["min"] < obs["min"]): + a.caption(f":orange[{note} β your range extends beyond this]") + else: + a.caption(note) + +st.markdown("---") +st.subheader("Cell line and density") +labels = [f"{c} ({CELL_LINE_COUNTS.get(c, 0)} records)" + for c in CELL_LINE_OPTIONS] +ci = st.selectbox("Cell line", range(len(CELL_LINE_OPTIONS)), + format_func=lambda i: labels[i], index=0) +cell_line = CELL_LINE_OPTIONS[ci] + +density_var = None +if cell_line == ACELLULAR_TOKEN: + st.info( + "Acellular mode. Cell response does not apply, so scaffold quality is " + "scored on printability alone and the cell-response weight is ignored.") +else: + obs = CELL_DENSITY_RANGES.get(cell_line) + d1, d2, d3 = st.columns(3) + dmin = d1.number_input("Density min (Γ10βΆ cells/mL)", + value=float(obs["min"]) if obs else 1.0, step=0.5) + dmax = d2.number_input("Density max (Γ10βΆ cells/mL)", + value=float(obs["max"]) if obs else 10.0, step=0.5) + dstep = d3.number_input("Density step", value=0.5, step=0.1, + min_value=0.01) + density_var = opt.Variable(cfg.CELL_COLS[1], dmin, dmax, dstep) + if obs: + st.caption(f"observed for {cell_line}: {obs['min']:.3g} β " + f"{obs['max']:.3g} (median {obs['median']:.3g})") + +st.markdown("---") +st.subheader("Crosslinking") +xl_vars = [] +for p in CROSSLINK: + a, b, c = st.columns(3) + lo = a.number_input(f"{p} β min", value=0.0, step=5.0, key=f"xlo{p}") + hi = b.number_input(f"{p} β max", value=300.0, step=5.0, key=f"xhi{p}") + stp = c.number_input("step", value=5.0, step=1.0, min_value=0.01, + key=f"xst{p}") + xl_vars.append(opt.Variable(p, lo, hi, stp)) + +st.subheader("Printing parameters") +DEFAULTS = {"Extrusion Pressure (kPa)": (20.0, 200.0, 5.0), + "Nozzle Movement Speed (mm/s)": (1.0, 20.0, 0.5), + "Nozzle Diameter (Β΅m)": (100.0, 600.0, 10.0), + "Syringe Temperature (Β°C)": (18.0, 40.0, 0.5), + "Substrate Temperature (Β°C)": (4.0, 40.0, 0.5)} +pp_vars = [] +for p in PROTOCOL_PARAMS: + lo0, hi0, s0 = DEFAULTS[p] + a, b, c = st.columns(3) + lo = a.number_input(f"{p} β min", value=lo0, step=s0, key=f"plo{p}") + hi = b.number_input(f"{p} β max", value=hi0, step=s0, key=f"phi{p}") + stp = c.number_input("step", value=s0, step=0.1, min_value=0.01, + key=f"pst{p}") + pp_vars.append(opt.Variable(p, lo, hi, stp)) + +st.markdown("---") + +if st.button("Optimise scaffold quality", type="primary"): + if not st.session_state.bio_rows: + st.error("Add at least one biomaterial.") + st.stop() + + pre, feature_columns = load_preprocessor() + space = opt.SearchSpace( + cell_line=cell_line, + biomaterials=[opt.Variable(r["mat"], r["min"], r["max"], r["step"]) + for r in st.session_state.bio_rows], + printing=xl_vars + pp_vars, + cell_density=density_var) + + objective = opt.Objective( + space, pre, feature_columns, + load_model(print_entry["path"], print_entry["family"]), + load_model(cell_entry["path"], cell_entry["family"]), + print_weight=w_print_pct / 100, cell_weight=w_cell_pct / 100) + + bar = st.progress(0.0, text="Searchingβ¦") + + def report(done, total, best): + bar.progress(min(done / total, 1.0), + text=f"Trial {done}/{total} Β· best WSSQ {best:.1f}%") + + best, score, study = opt.optimise(objective, n_trials=int(n_trials), + progress=report) + bar.empty() + + detail = objective.evaluate(best) + corpus, groups = load_corpus() + st.session_state.update( + best_params=best, best_value=score, best_detail=detail, + opt_cell_line=cell_line, + best_distance=(None if corpus is None + else opt.distance_report(best, corpus))) + +if "best_params" in st.session_state: + best = st.session_state.best_params + detail = st.session_state.best_detail + + st.success(f"Best WSSQ: **{st.session_state.best_value:.1f}%**") + m1, m2, m3 = st.columns(3) + m1.metric("Expected printability", + f"{detail['expected_printability']:.2f}", help="Scale 0β3") + if st.session_state.opt_cell_line != ACELLULAR_TOKEN: + m2.metric("Expected cell response", + f"{detail['expected_cell_response']:.2f}", help="Scale 1β5") + m3.metric("Cell line", st.session_state.opt_cell_line) + + st.subheader("Optimised formulation") + tidy = pd.DataFrame( + {"Parameter": list(best), "Value": [f"{v:.4g}" for v in best.values()]}) + st.dataframe(tidy, use_container_width=True, hide_index=True) + + st.caption( + "Predicted values, not measurements. The expected scores are " + "probability-weighted averages over the predicted class distribution, " + "so a value between two classes reflects genuine model uncertainty.") + + dist = st.session_state.get("best_distance") + if dist is None: + st.info( + "The corpus reference table is not present, so how far this " + "formulation sits from published work could not be checked. Run " + "`python 06_webapp/build_app_data.py` to generate it.") + else: + d1, d2 = st.columns(2) + d1.metric("Parameters outside the observed range", + dist["n_out_of_range"], + help="Values no published study in the corpus reports. The " + "models are extrapolating for these.") + d2.metric("Distance to nearest published formulation", + f"{dist['nearest_neighbour_distance']:.3f}", + help="Scaled Euclidean distance. A formulation can sit " + "inside the observed range of every single variable and " + "still be a combination no one has attempted; this " + "number is what catches that.") + if dist["n_out_of_range"]: + with st.expander("Which parameters, and by how much"): + st.dataframe(pd.DataFrame([ + {"Parameter": k, "Proposed": f"{v['value']:.4g}", + "Observed range": f"{v['observed_min']:.4g} - " + f"{v['observed_max']:.4g}"} + for k, v in dist["out_of_range"].items()]), + use_container_width=True, hide_index=True) + + st.markdown("---") + st.subheader("Fabrication protocol") + user_inquiry = st.text_area( + "Constraints or equipment you must work with", + placeholder="e.g. only a 25 G nozzle is available; UV source is " + "fixed at 10 mW/cmΒ²", + key="user_inquiry") + + if st.button("Generate protocol"): + key = proto.api_key(api_key_input) + if not key: + st.error("Enter an OpenRouter API key in the sidebar first.") + st.stop() + + bio = {k: v for k, v in best.items() if k in BIOMATERIAL_OPTIONS} + printing = {k: v for k, v in best.items() if k in PRINT_PARAMS} + # The neighbours and the extrapolation report are what ground the + # prompt. Passing neither leaves the template asserting that no similar + # formulation exists and that the candidate is in range, and neither + # would have been checked. + corpus, groups = load_corpus() + neighbours = (None if corpus is None else + proto.nearest_formulations(best, corpus, groups, n=3)) + form = proto.Formulation( + cell_line=st.session_state.opt_cell_line, + biomaterials=bio, printing=printing, + cell_density=best.get(cfg.CELL_COLS[1]), + expected_printability=detail["expected_printability"], + expected_cell_response=detail["expected_cell_response"], + printability_proba=detail.get("printability_proba"), + cell_response_proba=detail.get("cell_response_proba"), + wssq=st.session_state.best_value, + neighbours=neighbours, + extrapolation=st.session_state.get("best_distance")) + + # Streamed rather than awaited. A free model takes between thirty + # seconds and two and a half minutes to write a protocol, and a + # spinner held for that long is indistinguishable from a hang. + st.markdown("## Fabrication procedure") + status = st.empty() + stream_area = st.empty() + status.info(f"Generating with {llm_model}β¦") + pieces: list[str] = [] + + def on_chunk(piece: str) -> None: + pieces.append(piece) + stream_area.markdown("".join(pieces)) + + def on_retry(attempt: int, reason: str | None) -> None: + status.warning( + f"Attempt {attempt} of {proto.DEFAULT_RETRIES}: {reason}") + + try: + out = proto.generate( + form, key=key, model=llm_model, + user_constraints=user_inquiry, + n_records=(len(corpus) if corpus is not None else 2646), + on_chunk=on_chunk, on_retry=on_retry) + except Exception as exc: + status.empty() + stream_area.empty() + st.error(f"Generation failed: {exc}") + st.stop() + + status.empty() + stream_area.markdown(out["protocol"]) + if out.get("truncated"): + st.warning( + "The model reached its output limit and the protocol is " + "incomplete. Generate again, or choose another model.") + with st.expander("Generation record"): + st.json({k: v for k, v in out.items() if k != "protocol"}) + st.download_button("Download protocol (Markdown)", + out["protocol"], + file_name="mlate_protocol.md") + +st.markdown("---") +st.caption( + "MLATE V3 β decision support for 3D-printed and bioprinted scaffolds. " + "Predictions narrow the experimental search space; they do not replace " + "experimental validation.") diff --git a/biomaterials.py b/biomaterials.py index 43240fa6b4f966b9fb354cfaf5270f3eb760828c..a8719f94e4313b97e60ace500149adfe78b5decc 100644 --- a/biomaterials.py +++ b/biomaterials.py @@ -1,124 +1,926 @@ +""" +Biomaterial vocabulary and observed concentration ranges. + +GENERATED by 06_webapp/build_app_data.py - do not edit by hand. +Regenerate after any change to the dataset or the benchmark tables. +""" + BIOMATERIAL_OPTIONS = [ - "Alginate (%w/v)", - "PVA-HA (%w/v)", - "CaSO4 (%w/v)", - "Na2HPO4 (%w/v)", - "Gelatin (%w/v)", - "GelMA (%w/v)", - "laponite (%w/v)", - "graphene oxide (%w/v)", - "hydroxyapatite (%w/v)", - "Hyaluronic_Acid (%w/v)", - "hyaluronan metacrylate (%w/v)", - "NorHA (%w/v)", - "Fibroin/Fibrinogen (%w/v)", - "Pluronic P-123 (%w/v)", - "Collagen (%w/v)", - "Chitosan (%w/v)", - "CS-AEMA (%w/v)", - "RGD (mM)", - "TCP (%w/v)", - "Gellan (%w/v)", - "bioactive glass (%w/v)", - "Nano/Methycellulose (%w/v)", - "PEGTA (%w/v)", - "PEGMA (%w/v)", - "PEGDA (%w/v)", - "Agarose (%w/v)", - " hyaluronic acid+ Ph moieties (%w/v)", - "matrigel (%w/v)", - "CaCl2(mM)", - "NaCl(mM)", - "BaCl2(mM)", - "SrCl2(mM)", - "CaCO3 (mM)", - "Genipin (%w/v)", - "PVA (%wt)", - "trans-glutaminase (%w/v)", - "alginate lyase (U/ml)", - "D-glucose (%w/v)", - "PLGA (%w/v)", - "vascular tissued-derived dECM (%w/v)", - "PEG-8-SH (mM)", - "Alginate dialdehyde (%w/v)", - "Alginate sulfate (%w/v)", - "RGD-modified alginate (%w/v)", - "poly(N-isopropylacrylamide) grafted hyaluronan (%w/v)", - "chondroitin sulfate methacrylate (%w/v)", - "PCL (%w/v)", - "alginate methacrylate (%w/v)", - "HRP (U/ml)", - "Pluronic F127 (%w/v)/Lutrol F127 (%w/v)", - "Irgacure 2959 (%w/v)", - "Eosin Y (%w/v)", - "Ruthenium (mM)", - "sodium persulfate (SPS) (mM)", - "HEPES (mM)", - "LAP (%w/v)", - "glutaraldehyde (%w/v)", - "PBS (M)", - "glycerol (%w/v)", - "cECM (%w/v)", - "gel-fu(%w/v)", - "Rose Bengal (%w/v)", - "Vitamin B2(%w/v)", - "VEGF(%w/v)", - "Polypyrrole:PSS(%w/v)", - "boratebioactiveglass(%w/v)", - "astaxanthin(%w/v)", - "PRP (%v/v)", - "methacrylated collagen (%w/v)", - "Ξ±-Toc (Β΅M)", - "ascorbic acid (mM)", - "Liver dECM(%w/v)", - "galactosylated alginate (%w/v)", - "SC-PEG(%w/v)", - "SFMA-L(%w/v)", - "SFMA-M(%w/v)", - "SFMA-H(%w/v)", - "KdECMMA(%w/v)", - "BA silk fibronin (%w/v)", - "Carrageenan(%v)", - "Carbopol ETD 2020 NF (%w/v)", - "Carbopol Ultrez 10 NF(%w/v)", - "Carbopol NF-980(%w/v)", - "FBS (%v/v)", - "MeTro (%w/v)", - "Triethanolamine (%v/v)", - "PEG-Fibrinogen (%w/v)", - "polyethylene glycol dimethacrylate (%w/v)", - "aprotinin (Β΅g/ml)", - "gold nanorod (mg/mL)", - "egg white (w/v)", - "1-Vinyl-2-Pyrrolidione (v/v)", - "carboxyl functionalized carbon nanotubes (%w/v)", - "polyHIPE (%w/v)", - "Ξ²-D galactose (mM)", - "hydrogen peroxide (H2O2) (%v/v)", - "lactic acid v/v", - "NorCol (%w/v)", - "DDT (%w/v)", - "ammonium persulfate (mM)", - "diTyr-RGD (mM)", - "PHEG-Tyr (%w/v)", - "MMP2-degradable peptide (%w/v)", - "KdECM (%w/v)", - "EDC (mg)", - "NHS (mg)", - "VA086 (%w/v)", - "PGS (%w/v)", - "thiolated HA (%w/v)", - "boron nitride nanotubes (%w/v)", - "PEDOT:PSS (ul)", - "KCl (mM)", - "skeletal muscle ECM methacrylate (%w/v)", - "PEO (%w/v)", - "Carbon dots (mg/ml)", - "Laminin (ug/ml)", - "DF-PEG (%w/v)", - "omenta ECM (%w/v)", - "thrombin (unit/ml)", - "Carbon nanotube (CNT) (w/v)", - "Phytagel(%v)", - "Laponite-XLG (%w/w)" -] \ No newline at end of file + 'Alginate (%w/v)', + 'PVA-HA (%w/v)', + 'CaSO4 (%w/v)', + 'Na2HPO4 (%w/v)', + 'Gelatin (%w/v)', + 'GelMA (%w/v)', + 'laponite (%w/v)', + 'graphene oxide (%w/v)', + 'hydroxyapatite (%w/v)', + 'Hyaluronic_Acid (%w/v)', + 'hyaluronan methacrylate (%w/v)', + 'NorHA (%w/v)', + 'Fibroin/Fibrinogen (%w/v)', + 'Pluronic P-123 (%w/v)', + 'Collagen (%w/v)', + 'Chitosan (%w/v)', + 'CS-AEMA (%w/v)', + 'RGD (mM)', + 'TCP (%w/v)', + 'Gellan (%w/v)', + 'bioactive glass (%w/v)', + 'Nano/Methylcellulose (%w/v)', + 'PEGTA (%w/v)', + 'PEGMA (%w/v)', + 'PEGDA (%w/v)', + 'Agarose (%w/v)', + 'hyaluronic acid+ Ph moieties (%w/v)', + 'matrigel (%w/v)', + 'CaCl2 (mM)', + 'NaCl (mM)', + 'BaCl2 (mM)', + 'SrCl2 (mM)', + 'CaCO3 (mM)', + 'Genipin (%w/v)', + 'PVA (%wt)', + 'trans-glutaminase (%w/v)', + 'alginate lyase (U/ml)', + 'D-glucose (%w/v)', + 'PLGA (%w/v)', + 'vascular tissue-derived dECM (%w/v)', + 'PEG-8-SH (mM)', + 'Alginate dialdehyde (%w/v)', + 'Alginate sulfate (%w/v)', + 'RGD-modified alginate (%w/v)', + 'poly(N-isopropylacrylamide) grafted hyaluronan (%w/v)', + 'chondroitin sulfate methacrylate (%w/v)', + 'PCL (%w/v)', + 'alginate methacrylate (%w/v)', + 'HRP (U/ml)', + 'Pluronic F127 / Lutrol F127 (%w/v)', + 'Irgacure 2959 (%w/v)', + 'Eosin Y (%w/v)', + 'Ruthenium (mM)', + 'sodium persulfate (SPS) (mM)', + 'HEPES (mM)', + 'LAP (%w/v)', + 'glutaraldehyde (%w/v)', + 'PBS (M)', + 'glycerol (%w/v)', + 'cECM (%w/v)', + 'gel-fu (%w/v)', + 'Rose Bengal (%w/v)', + 'Vitamin B2 (%w/v)', + 'VEGF (%w/v)', + 'Polypyrrole:PSS (%w/v)', + 'borate bioactive glass (%w/v)', + 'astaxanthin (%w/v)', + 'PRP (%v/v)', + 'methacrylated collagen (%w/v)', + 'Ξ±-Toc (Β΅M)', + 'ascorbic acid (mM)', + 'Liver dECM (%w/v)', + 'galactosylated alginate (%w/v)', + 'SC-PEG (%w/v)', + 'SFMA-L (%w/v)', + 'SFMA-M (%w/v)', + 'SFMA-H (%w/v)', + 'KdECMMA (%w/v)', + 'BA silk fibroin (%w/v)', + 'Carrageenan (%v)', + 'Carbopol ETD 2020 NF (%w/v)', + 'Carbopol Ultrez 10 NF (%w/v)', + 'Carbopol NF-980 (%w/v)', + 'FBS (%v/v)', + 'MeTro (%w/v)', + 'Triethanolamine (%v/v)', + 'PEG-Fibrinogen (%w/v)', + 'polyethylene glycol dimethacrylate (%w/v)', + 'aprotinin (Β΅g/ml)', + 'gold nanorod (mg/mL)', + 'egg white (w/v)', + '1-Vinyl-2-pyrrolidone (v/v)', + 'carboxyl functionalized carbon nanotubes (%w/v)', + 'polyHIPE (%w/v)', + 'Ξ²-D galactose (mM)', + 'hydrogen peroxide (H2O2) (%v/v)', + 'lactic acid (v/v)', + 'NorCol (%w/v)', + 'DTT (%w/v)', + 'ammonium persulfate (mM)', + 'diTyr-RGD (mM)', + 'PHEG-Tyr (%w/v)', + 'MMP2-degradable peptide (%w/v)', + 'KdECM (%w/v)', + 'EDC (mg)', + 'NHS (mg)', + 'VA086 (%w/v)', + 'PGS (%w/v)', + 'thiolated HA (%w/v)', + 'boron nitride nanotubes (%w/v)', + 'PEDOT:PSS (ul)', + 'KCl (mM)', + 'skeletal muscle ECM methacrylate (%w/v)', + 'PEO (%w/v)', + 'Carbon dots (mg/ml)', + 'Laminin (ug/ml)', + 'DF-PEG (%w/v)', + 'omentum ECM (%w/v)', + 'thrombin (unit/ml)', + 'Carbon nanotube (CNT) (w/v)', + 'Phytagel (%v)', + 'Laponite-XLG (%w/w)', + 'sodium carboxymethyl cellulose (mg)', + 'lysozyme amyloid nanofibrils:gold nanoparticles (mg)', + 'Lysozyme amyloid nanofibrils (mg)', + 'rGO (mg/ml)', + 'Methacrylated gellan gum (%w/v)', + 'Acetylsalicylic Acid (%w/w)', + 'PVA methacrylate (%w/v)', + 'MXene (mg/ml)', +] + +# Observed range among formulations that CONTAIN each material. +# The UI seeds its range widgets from these so a user starts +# inside the region the models were trained on; values outside +# are permitted but flagged as extrapolation. +BIOMATERIAL_RANGES = { + "Alginate (%w/v)": { + "min": 0.25, + "max": 20.0, + "median": 4.0, + "n": 1138 + }, + "PVA-HA (%w/v)": { + "min": 0.3, + "max": 2.5, + "median": 2.0, + "n": 15 + }, + "CaSO4 (%w/v)": { + "min": 0.03, + "max": 25.71, + "median": 1.0, + "n": 32 + }, + "Na2HPO4 (%w/v)": { + "min": 0.12, + "max": 0.15, + "median": 0.15, + "n": 9 + }, + "Gelatin (%w/v)": { + "min": 0.5, + "max": 80.0, + "median": 5.0, + "n": 797 + }, + "GelMA (%w/v)": { + "min": 1.0, + "max": 30.0, + "median": 7.0, + "n": 880 + }, + "laponite (%w/v)": { + "min": 0.05, + "max": 2.3, + "median": 2.3, + "n": 96 + }, + "graphene oxide (%w/v)": { + "min": 0.001, + "max": 1.5, + "median": 0.5, + "n": 43 + }, + "hydroxyapatite (%w/v)": { + "min": 2.0, + "max": 70.0, + "median": 70.0, + "n": 43 + }, + "Hyaluronic_Acid (%w/v)": { + "min": 0.2, + "max": 2.0, + "median": 0.3, + "n": 62 + }, + "hyaluronan methacrylate (%w/v)": { + "min": 0.1, + "max": 6.0, + "median": 2.0, + "n": 151 + }, + "NorHA (%w/v)": { + "min": 2.0, + "max": 2.0, + "median": 2.0, + "n": 4 + }, + "Fibroin/Fibrinogen (%w/v)": { + "min": 0.009375, + "max": 25.0, + "median": 2.0, + "n": 207 + }, + "Pluronic P-123 (%w/v)": { + "min": 40.0, + "max": 60.0, + "median": 50.0, + "n": 12 + }, + "Collagen (%w/v)": { + "min": 0.01, + "max": 7.8, + "median": 2.0, + "n": 85 + }, + "Chitosan (%w/v)": { + "min": 1.0, + "max": 62.0, + "median": 2.0, + "n": 74 + }, + "CS-AEMA (%w/v)": { + "min": 4.0, + "max": 4.0, + "median": 4.0, + "n": 8 + }, + "RGD (mM)": { + "min": 3.0, + "max": 3.0, + "median": 3.0, + "n": 1 + }, + "TCP (%w/v)": { + "min": 0.5, + "max": 3.0, + "median": 0.5, + "n": 9 + }, + "Gellan (%w/v)": { + "min": 0.5, + "max": 150.0, + "median": 150.0, + "n": 54 + }, + "bioactive glass (%w/v)": { + "min": 1.0, + "max": 50.0, + "median": 1.0, + "n": 7 + }, + "Nano/Methylcellulose (%w/v)": { + "min": 0.25, + "max": 80.0, + "median": 4.0, + "n": 157 + }, + "PEGTA (%w/v)": { + "min": 1.0, + "max": 3.0, + "median": 2.0, + "n": 33 + }, + "PEGMA (%w/v)": { + "min": 12.5, + "max": 100.0, + "median": 17.5, + "n": 9 + }, + "PEGDA (%w/v)": { + "min": 1.0, + "max": 20.0, + "median": 8.25, + "n": 119 + }, + "Agarose (%w/v)": { + "min": 0.5, + "max": 60.0, + "median": 24.0, + "n": 51 + }, + "hyaluronic acid+ Ph moieties (%w/v)": { + "min": 0.1, + "max": 1.5, + "median": 0.8, + "n": 8 + }, + "matrigel (%w/v)": { + "min": 5.0, + "max": 50.0, + "median": 10.0, + "n": 19 + }, + "CaCl2 (mM)": { + "min": 0.001, + "max": 1500.0, + "median": 100.0, + "n": 1057 + }, + "NaCl (mM)": { + "min": 0.72, + "max": 350.0, + "median": 145.0, + "n": 23 + }, + "BaCl2 (mM)": { + "min": 55.0, + "max": 60.0, + "median": 55.0, + "n": 12 + }, + "SrCl2 (mM)": { + "min": 20.0, + "max": 70.0, + "median": 20.0, + "n": 6 + }, + "CaCO3 (mM)": { + "min": 15.88, + "max": 25.71, + "median": 18.0, + "n": 9 + }, + "Genipin (%w/v)": { + "min": 0.025, + "max": 1.0, + "median": 0.025, + "n": 18 + }, + "PVA (%wt)": { + "min": 3.0, + "max": 15.0, + "median": 15.0, + "n": 50 + }, + "trans-glutaminase (%w/v)": { + "min": 0.04, + "max": 6.0, + "median": 1.0, + "n": 63 + }, + "alginate lyase (U/ml)": { + "min": 0.5, + "max": 500.0, + "median": 5.0, + "n": 7 + }, + "D-glucose (%w/v)": { + "min": 4.4, + "max": 4.4, + "median": 4.4, + "n": 5 + }, + "PLGA (%w/v)": { + "min": 100.0, + "max": 100.0, + "median": 100.0, + "n": 4 + }, + "vascular tissue-derived dECM (%w/v)": { + "min": 1.0, + "max": 3.0, + "median": 3.0, + "n": 7 + }, + "PEG-8-SH (mM)": { + "min": 2.25, + "max": 8.0, + "median": 2.25, + "n": 10 + }, + "Alginate dialdehyde (%w/v)": { + "min": 2.0, + "max": 7.5, + "median": 3.75, + "n": 48 + }, + "Alginate sulfate (%w/v)": { + "min": 1.0, + "max": 1.0, + "median": 1.0, + "n": 26 + }, + "RGD-modified alginate (%w/v)": { + "min": 1.0, + "max": 1.0, + "median": 1.0, + "n": 2 + }, + "poly(N-isopropylacrylamide) grafted hyaluronan (%w/v)": { + "min": 15.0, + "max": 15.0, + "median": 15.0, + "n": 3 + }, + "chondroitin sulfate methacrylate (%w/v)": { + "min": 5.0, + "max": 5.0, + "median": 5.0, + "n": 1 + }, + "PCL (%w/v)": { + "min": 1.0, + "max": 100.0, + "median": 8.0, + "n": 34 + }, + "alginate methacrylate (%w/v)": { + "min": 1.0, + "max": 3.0, + "median": 3.0, + "n": 24 + }, + "HRP (U/ml)": { + "min": 5.0, + "max": 100.0, + "median": 15.0, + "n": 68 + }, + "Pluronic F127 / Lutrol F127 (%w/v)": { + "min": 3.0, + "max": 100.0, + "median": 6.0, + "n": 83 + }, + "Irgacure 2959 (%w/v)": { + "min": 0.01, + "max": 2.0, + "median": 0.25, + "n": 530 + }, + "Eosin Y (%w/v)": { + "min": 0.5, + "max": 100.0, + "median": 0.5, + "n": 32 + }, + "Ruthenium (mM)": { + "min": 0.254, + "max": 1.0, + "median": 0.5, + "n": 28 + }, + "sodium persulfate (SPS) (mM)": { + "min": 2.52, + "max": 10.0, + "median": 5.0, + "n": 28 + }, + "HEPES (mM)": { + "min": 10.0, + "max": 25.0, + "median": 10.0, + "n": 22 + }, + "LAP (%w/v)": { + "min": 0.01, + "max": 4.46, + "median": 0.4, + "n": 310 + }, + "glutaraldehyde (%w/v)": { + "min": 0.125, + "max": 0.4, + "median": 0.25, + "n": 62 + }, + "PBS (M)": { + "min": 0.082, + "max": 0.328, + "median": 0.165, + "n": 3 + }, + "glycerol (%w/v)": { + "min": 10.0, + "max": 10.0, + "median": 10.0, + "n": 21 + }, + "cECM (%w/v)": { + "min": 0.1, + "max": 20.0, + "median": 4.6, + "n": 118 + }, + "gel-fu (%w/v)": { + "min": 10.0, + "max": 155.0, + "median": 100.0, + "n": 15 + }, + "Rose Bengal (%w/v)": { + "min": 1.0, + "max": 5.0, + "median": 5.0, + "n": 14 + }, + "Vitamin B2 (%w/v)": { + "min": 0.02, + "max": 0.2, + "median": 0.02, + "n": 20 + }, + "VEGF (%w/v)": { + "min": 0.01, + "max": 10.0, + "median": 1.0, + "n": 6 + }, + "Polypyrrole:PSS (%w/v)": { + "min": 0.1, + "max": 0.4, + "median": 0.2, + "n": 3 + }, + "borate bioactive glass (%w/v)": { + "min": 0.1, + "max": 0.1, + "median": 0.1, + "n": 1 + }, + "astaxanthin (%w/v)": { + "min": 0.01, + "max": 0.01, + "median": 0.01, + "n": 1 + }, + "PRP (%v/v)": { + "min": 20.0, + "max": 20.0, + "median": 20.0, + "n": 3 + }, + "methacrylated collagen (%w/v)": { + "min": 0.2, + "max": 50.0, + "median": 0.48, + "n": 25 + }, + "\u03b1-Toc (\u00b5M)": { + "min": 100.0, + "max": 100.0, + "median": 100.0, + "n": 5 + }, + "ascorbic acid (mM)": { + "min": 3.4, + "max": 3.4, + "median": 3.4, + "n": 5 + }, + "Liver dECM (%w/v)": { + "min": 0.5, + "max": 100.0, + "median": 2.0, + "n": 139 + }, + "galactosylated alginate (%w/v)": { + "min": 0.375, + "max": 1.0, + "median": 1.0, + "n": 22 + }, + "SC-PEG (%w/v)": { + "min": 1.44, + "max": 1.44, + "median": 1.44, + "n": 4 + }, + "SFMA-L (%w/v)": { + "min": 10.0, + "max": 10.0, + "median": 10.0, + "n": 1 + }, + "SFMA-M (%w/v)": { + "min": 10.0, + "max": 10.0, + "median": 10.0, + "n": 1 + }, + "SFMA-H (%w/v)": { + "min": 10.0, + "max": 10.0, + "median": 10.0, + "n": 1 + }, + "KdECMMA (%w/v)": { + "min": 1.0, + "max": 3.0, + "median": 2.0, + "n": 15 + }, + "BA silk fibroin (%w/v)": { + "min": 0.5, + "max": 3.0, + "median": 1.5, + "n": 32 + }, + "Carrageenan (%v)": { + "min": 0.5, + "max": 1.5, + "median": 1.0, + "n": 43 + }, + "Carbopol ETD 2020 NF (%w/v)": { + "min": 0.1, + "max": 1.2, + "median": 0.5, + "n": 32 + }, + "Carbopol Ultrez 10 NF (%w/v)": { + "min": 1.5, + "max": 1.5, + "median": 1.5, + "n": 6 + }, + "Carbopol NF-980 (%w/v)": { + "min": 1.2, + "max": 1.2, + "median": 1.2, + "n": 4 + }, + "FBS (%v/v)": { + "min": 10.0, + "max": 10.0, + "median": 10.0, + "n": 34 + }, + "MeTro (%w/v)": { + "min": 7.5, + "max": 7.5, + "median": 7.5, + "n": 28 + }, + "Triethanolamine (%v/v)": { + "min": 3.0, + "max": 3.0, + "median": 3.0, + "n": 4 + }, + "PEG-Fibrinogen (%w/v)": { + "min": 1.0, + "max": 1.0, + "median": 1.0, + "n": 8 + }, + "polyethylene glycol dimethacrylate (%w/v)": { + "min": 1.0, + "max": 1.0, + "median": 1.0, + "n": 50 + }, + "aprotinin (\u00b5g/ml)": { + "min": 0.2, + "max": 10.0, + "median": 0.2, + "n": 3 + }, + "gold nanorod (mg/mL)": { + "min": 0.1, + "max": 0.1, + "median": 0.1, + "n": 24 + }, + "egg white (w/v)": { + "min": 1.0, + "max": 3.0, + "median": 2.0, + "n": 10 + }, + "1-Vinyl-2-pyrrolidone (v/v)": { + "min": 0.75, + "max": 0.75, + "median": 0.75, + "n": 4 + }, + "carboxyl functionalized carbon nanotubes (%w/v)": { + "min": 0.3, + "max": 2.0, + "median": 1.0, + "n": 9 + }, + "polyHIPE (%w/v)": { + "min": 1.0, + "max": 5.0, + "median": 3.0, + "n": 5 + }, + "\u03b2-D galactose (mM)": { + "min": 40.0, + "max": 40.0, + "median": 40.0, + "n": 2 + }, + "hydrogen peroxide (H2O2) (%v/v)": { + "min": 0.09, + "max": 3.87, + "median": 3.87, + "n": 55 + }, + "lactic acid (v/v)": { + "min": 3.0, + "max": 3.0, + "median": 3.0, + "n": 30 + }, + "NorCol (%w/v)": { + "min": 0.2, + "max": 1.0, + "median": 0.6, + "n": 13 + }, + "DTT (%w/v)": { + "min": 0.5, + "max": 8.0, + "median": 0.7, + "n": 10 + }, + "ammonium persulfate (mM)": { + "min": 3.75, + "max": 5.0, + "median": 4.375, + "n": 16 + }, + "diTyr-RGD (mM)": { + "min": 2.0, + "max": 6.0, + "median": 4.0, + "n": 8 + }, + "PHEG-Tyr (%w/v)": { + "min": 10.0, + "max": 10.0, + "median": 10.0, + "n": 12 + }, + "MMP2-degradable peptide (%w/v)": { + "min": 0.1, + "max": 0.5, + "median": 0.3, + "n": 8 + }, + "KdECM (%w/v)": { + "min": 1.0, + "max": 5.0, + "median": 3.3, + "n": 11 + }, + "EDC (mg)": { + "min": 50.0, + "max": 50.0, + "median": 50.0, + "n": 22 + }, + "NHS (mg)": { + "min": 10.0, + "max": 25.0, + "median": 10.0, + "n": 22 + }, + "VA086 (%w/v)": { + "min": 0.5, + "max": 20.0, + "median": 0.75, + "n": 10 + }, + "PGS (%w/v)": { + "min": 2.0, + "max": 20.0, + "median": 11.0, + "n": 2 + }, + "thiolated HA (%w/v)": { + "min": 0.04, + "max": 0.067, + "median": 0.05, + "n": 10 + }, + "boron nitride nanotubes (%w/v)": { + "min": 0.05, + "max": 0.1, + "median": 0.075, + "n": 3 + }, + "PEDOT:PSS (ul)": { + "min": 0.1, + "max": 0.3, + "median": 0.1, + "n": 18 + }, + "KCl (mM)": { + "min": 5.0, + "max": 5.0, + "median": 5.0, + "n": 15 + }, + "skeletal muscle ECM methacrylate (%w/v)": { + "min": 3.0, + "max": 3.0, + "median": 3.0, + "n": 7 + }, + "PEO (%w/v)": { + "min": 0.4, + "max": 0.4, + "median": 0.4, + "n": 9 + }, + "Carbon dots (mg/ml)": { + "min": 20.0, + "max": 20.0, + "median": 20.0, + "n": 9 + }, + "Laminin (ug/ml)": { + "min": 10.0, + "max": 93.75, + "median": 70.0, + "n": 13 + }, + "DF-PEG (%w/v)": { + "min": 25.0, + "max": 25.0, + "median": 25.0, + "n": 6 + }, + "omentum ECM (%w/v)": { + "min": 2.0, + "max": 2.0, + "median": 2.0, + "n": 2 + }, + "thrombin (unit/ml)": { + "min": 2.5, + "max": 50.0, + "median": 10.0, + "n": 41 + }, + "Carbon nanotube (CNT) (w/v)": { + "min": 0.5, + "max": 6.0, + "median": 1.5, + "n": 18 + }, + "Phytagel (%v)": { + "min": 0.3, + "max": 0.3, + "median": 0.3, + "n": 1 + }, + "Laponite-XLG (%w/w)": { + "min": 2.3, + "max": 2.3, + "median": 2.3, + "n": 25 + }, + "sodium carboxymethyl cellulose (mg)": { + "min": 75.0, + "max": 150.0, + "median": 100.0, + "n": 60 + }, + "lysozyme amyloid nanofibrils:gold nanoparticles (mg)": { + "min": 2.5, + "max": 37.5, + "median": 12.5, + "n": 6 + }, + "Lysozyme amyloid nanofibrils (mg)": { + "min": 2.5, + "max": 37.5, + "median": 12.5, + "n": 31 + }, + "rGO (mg/ml)": { + "min": 150.0, + "max": 150.0, + "median": 150.0, + "n": 2 + }, + "Methacrylated gellan gum (%w/v)": { + "min": 2.0, + "max": 3.5, + "median": 3.0, + "n": 15 + }, + "Acetylsalicylic Acid (%w/w)": { + "min": 10.0, + "max": 10.0, + "median": 10.0, + "n": 3 + }, + "PVA methacrylate (%w/v)": { + "min": 1.0, + "max": 5.0, + "median": 5.0, + "n": 11 + }, + "MXene (mg/ml)": { + "min": 0.1, + "max": 5.0, + "median": 0.75, + "n": 6 + } +} diff --git a/cell_lines.py b/cell_lines.py index 08b60291e75680b3c16061f4fd2ea75d9fe7e657..fe4eba5e46221b1fc6aeb10e82b2bdd51700837c 100644 --- a/cell_lines.py +++ b/cell_lines.py @@ -1,178 +1,1320 @@ +""" +Cell-line vocabulary and observed seeding densities. + +GENERATED by 06_webapp/build_app_data.py - do not edit by hand. +Regenerate after any change to the dataset or the benchmark tables. +""" + +# Ordered by frequency in the corpus, with the acellular token +# first because it selects a different mode: cell response is +# not applicable and WSSQ falls back to printability alone. +ACELLULAR_TOKEN = 'NoCellCultured' + CELL_LINE_OPTIONS = [ - "NoCellCultured", - "chondrocyteyte", - "HepG2", - "bMSCs", - "HUVECs", - "NIH3T3", - "MESCs", - "hiPSC-CMs /ATCCs", - "CPCs", - "L929", - "Myoblast cells", - "hiPSCs", - "HepaRG", - "hESCs", - "10T1/2", - "Cardiac progenitor cells", - "NSCLC PDX", - "RAMECs", - "hASCs", - "HAVIC", - "Primary mouse hepatocyte", - "PTECs", - "human nasoseptal chondrocytes", - "PDX", - "HPFs", - "U87-MG", - "ESCs", - "HASSMC", - "dermal fibroblasts", - "MC3T3-E1", - "Schwann cells", - "hiPSC-CMs and HS-27A", - "Saos-2 ", - "SU3", - "hTMSCs", - "HACs", - "HADMSCs", - "HeLa", - "human primary kidney cells", - "myoblasts", - "MSCs", - "human primary kidneycells", - "293FT", - "HEK 293FT", - "Wnt3a-293FT", - "RSC96/HUVECs", - "human adipogenic mesenchymal stem cells", - "HEPG2/ECs", - "HUVECs/MSCs", - "RHECs", - "Human non-small cell lung cancer line Calu-3 (Calu-3)", - "HL-1", - "mouse cardiac cells", - "IMR-90", - "EPCs", - "MRC5", - "rMSC", - "basil plant cell", - "hNCs", - "A549", - "human induced pluripotent stem cell-derived cardiomyocytes", - "bMSCs/hACs", - "EA.hy 926 cells", - "HepG2/C3A", - "human epithelial lung carcinoma cells", - "Human cardiac fibroblasts", - "hTERT-MSC", - "cardiomyocytes", - "Huh7", - "NRCMs", - "HCF", - "Wnt reporter-293FT", - "neonatal rat ventricular CFs", - "human coronary artery endothelial cells", - "hiPSC-CM / fibroblasts", - "primary mouse hepatocyte", - "NIH3T3/ HUVECs", - "murine macrophage-like cell line", - "Endothelial cells", - "Human aortic VIC", - "sADSC", - "HUVECs/H9C2", - "neonatal rat ventricular cardiomyocytes", - "MG-63", - "Neonatal mouse cardiomyocytes (NMVCMs)", - "human hepatic stellate cell line", - "HEK-293", - "aHSC", - "MFCs", - "fibroblasts", - "HNDF", - "cardiomyocyte/MSCs", - "ADSCs", - "HCASMCs", - "cardiomyocyte", - "hCPCs", - "Human CM /adult human fibroblasts ", - "primary rat hepatocyte", - "human cardiac progenitor cells", - "SMC", - "Human MSCs", - "ACPCs", - "Huh7/HepaRG", - "Human umbilical vein endothelial cells", - "ATDC5", - "hESC-derived HLCs", - "NIH 3T3", - "n neonatal mouse ventricular cardiomyocytes", - "CFs/CMs/HUVECs", - "MRC-5", - "VIC", - "eHep", - "hUVECs/NIH3T3", - "MC3T3", - "HLC", - "hepatoma", - "FB", - "A549 GFP+", - "HPAAF", - "PMHs", - "HUVSMCs", - "Human CPCs", - "Fibroblasts/THP-1", - "rat ventricular cardiomyocytes", - "iCMs/iCFs/iECs", - "HUVEC/HHSC", - "Human CPCs / MSCs", - "HepaRG/LX-2 ", - "iCMs/iCFs/iECs/iCMFs", - "LX-2 ", - "SMMC-7721", - "Hepatoblast- single cell/iESC/iMSC", - "iCMFs", - "Hepatoblast- spheroid/iESC/iMSC", - "hBM-MSCs", - "BMSCs", - "HUVECs and HHSCs", - "Intrahepatic cholangiocarcinoma (ICC)", - "VICs", - "CMs/CFs", - "human neonatal dermal fi broblasts", - "10T1/2 fibroblast-laden cells", - "human cardiac fibroblasts", - "neonatal rat ventricular CMs", - "HUVECs and hiPSC-CS", - "iPSC-derived CM", - "Human Umbilical Vein Endothelial Cells + iPSC-derived CM", - "rabbit bone marrow mesenchymal stem cells", - "Neonatal rat cardiomyocytes", - "NIH 3T3 mouse fibroblasts", - "Human CPCs & MSCs", - "NSCLC PDX/CAFs", - "hiPSCs-derived HLCs", - "U87", - "75% hepatoblast cells, 20% iEC and 5% iMSC", - "SMCs", - "A549/95-D cells", - "NCI-H441", - "pancreatic cancer cell", - "prostate cancer stem cell", - "human primary parathyroid cells ", - "primary human hepatocytes", - "CPCs / MSCs", - "CPCs ", - "cardiac fibroblasts", - "iPSCs-derived cardiomyocytes", - "cardiomyocytes/ fibroblasts", - "hiPSC-CM", - "iPSCs/HUVECs", - "iPSC-CMs", - "iPSCs", - "H1395", - "PC9", - "H1650", - "HULEC-5a", - "NCI-H1703" -] \ No newline at end of file + 'NoCellCultured', + 'HUVECs', + 'HepG2', + 'bMSCs', + 'chondrocytes', + 'NIH3T3', + 'HepaRG', + 'hiPSC-CMs /ATCCs', + 'Myoblast cells', + 'H9c2', + 'HEK', + 'CPCs', + 'MESCs', + 'hiPSCs', + 'L929', + 'Primary mouse hepatocyte', + 'NSCLC PDX', + 'human primary kidney cells', + 'Cardiac progenitor cells', + '10T1/2', + 'HAVIC', + 'RAMECs', + 'hESCs', + 'human nasoseptal chondrocytes', + 'PDX', + 'PTECs', + 'HPFs', + 'MG-63', + 'dermal fibroblasts', + 'HASSMC', + 'Saos-2', + 'MC3T3-E1', + 'hASCs', + 'SU3', + 'ESCs', + 'RPTEC/TERT1', + 'hiPSC-CMs and HS-27A', + 'HADMSCs', + 'HACs', + 'MRC5', + 'HeLa', + 'RHECs', + 'cardiomyocytes', + 'human adipogenic mesenchymal stem cells', + 'MSCs', + 'HUVECs/MSCs', + 'U87-MG', + 'RSC96/HUVECs', + 'HEPG2/ECs', + 'A549', + 'Human non-small cell lung cancer line Calu-3 (Calu-3)', + 'hTMSCs', + 'mouse cardiac cells', + 'Human cardiac fibroblasts', + 'Schwann cells', + 'hTERT-MSC', + 'bMSCs/hACs', + 'basil plant cell', + 'EPCs', + 'HepaRG / LX-2', + 'Caki-1', + 'human induced pluripotent stem cell-derived cardiomyocytes', + 'human epithelial lung carcinoma cells', + 'HCF', + 'Huh7', + '3T3 Fibroblasts', + 'EA.hy 926 cells', + 'human coronary artery endothelial cells', + 'NIH3T3/ HUVECs', + 'neonatal rat ventricular CFs', + 'HepG2/C3A', + 'IMR-90', + 'rMSC', + 'hiPSC-CM / fibroblasts', + 'HUVECs/H9C2', + 'fibroblasts', + 'Endothelial cells', + 'neonatal rat ventricular cardiomyocytes', + 'Neonatal mouse cardiomyocytes (NMVCMs)', + 'murine macrophage-like cell line', + '293FT', + 'sADSC', + 'human hepatic stellate cell line', + 'aHSC', + 'NRCMs', + 'HBE', + 'HEK-293', + 'Wnt3a-293FT', + 'Human aortic VIC', + 'HEK 293FT', + 'HNDF', + 'Huh7/HepaRG', + 'hiHeps', + 'hCPCs', + 'pancreatic islets cells', + 'ICC', + 'Wnt reporter-293FT', + 'Human CPCs', + 'human cardiac progenitor cells', + 'SMC', + 'hepatoma', + 'cardiomyocyte/MSCs', + 'FB', + 'eHep', + 'PMHs', + 'Human CM /adult human fibroblasts', + 'HUVSMCs', + 'ACPCs', + 'MC3T3', + 'hNCs', + 'primary rat hepatocyte', + 'Human umbilical vein endothelial cells', + 'HPAAF', + 'VIC', + 'HLC', + 'ADSCs', + 'MFCs', + 'A549 GFP+', + 'ATDC5', + 'CFs/CMs/HUVECs', + 'n neonatal mouse ventricular cardiomyocytes', + 'Human MSCs', + 'Human CPCs / MSCs', + 'hESC-derived HLCs', + 'HCASMCs', + 'iCMs/iCFs/iECs/iCMFs', + 'VICs', + 'iPSCs', + 'primary human hepatocytes', + 'SMCs', + 'iCMs/iCFs/iECs', + 'PC9', + 'H1395', + 'H1650', + 'HUVECs and hiPSC-CS', + 'human neonatal dermal fi broblasts', + '10T1/2 fibroblast-laden cells', + 'iCMFs', + 'neonatal rat ventricular CMs', + 'U87', + 'NSCLC PDX/CAFs', + 'iPSC-derived CM', + 'NIH 3T3 mouse fibroblasts', + 'Neonatal rat cardiomyocytes', + 'hiPSCs-derived HLCs', + 'iPSCs/HUVECs', + 'HULEC-5a', + 'HUVECs and HHSCs', + 'NCI-H1703', + '75% hepatoblast cells, 20% iEC and 5% iMSC', + 'Intrahepatic cholangiocarcinoma (ICC)', + 'NCI-H441', + 'Human Umbilical Vein Endothelial Cells + iPSC-derived CM', + 'rabbit bone marrow mesenchymal stem cells', + 'CMs/CFs', + 'cardiac fibroblasts', + 'iPSCs-derived cardiomyocytes', + 'cardiomyocytes/ fibroblasts', + 'hiPSC-CM', + 'iPSC-CMs', + 'hBM-MSCs', + 'Hepatoblast- single cell/iESC/iMSC', + 'Hepatoblast- spheroid/iESC/iMSC', + 'human primary parathyroid cells', + 'prostate cancer stem cell', + 'HL-1', + 'CPCs / MSCs', + 'pancreatic cancer cell', + 'A549/95-D cells', + 'SMMC-7721', + 'rat ventricular cardiomyocytes', + 'A549 lung adenocarcinoma cells', + 'HMEC-1/ fibroblast/ THP-1', + 'HMEC-1', + 'HAVSMC', + 'HUVEC/HHSC', + 'LX-2', + 'Fibroblasts/THP-1', + 'HLF', + 'HUVECs / LX-2', + 'CCAO', + 'Hepa RG/ HUVEC', + 'BEAS2B', + 'PDGFRΞ²+', + 'hMSCs', + 'CiPSC-HOs', + 'tubular epithelial', +] + +CELL_LINE_COUNTS = { + 'NoCellCultured': 1573, + 'HUVECs': 75, + 'HepG2': 71, + 'bMSCs': 65, + 'chondrocytes': 39, + 'NIH3T3': 35, + 'HepaRG': 28, + 'hiPSC-CMs /ATCCs': 26, + 'Myoblast cells': 26, + 'H9c2': 25, + 'HEK': 24, + 'CPCs': 21, + 'MESCs': 20, + 'hiPSCs': 17, + 'L929': 15, + 'Primary mouse hepatocyte': 14, + 'NSCLC PDX': 13, + 'human primary kidney cells': 13, + 'Cardiac progenitor cells': 13, + '10T1/2': 13, + 'HAVIC': 12, + 'RAMECs': 12, + 'hESCs': 11, + 'human nasoseptal chondrocytes': 10, + 'PDX': 10, + 'PTECs': 10, + 'HPFs': 10, + 'MG-63': 9, + 'dermal fibroblasts': 9, + 'HASSMC': 9, + 'Saos-2': 8, + 'MC3T3-E1': 8, + 'hASCs': 8, + 'SU3': 8, + 'ESCs': 8, + 'RPTEC/TERT1': 8, + 'hiPSC-CMs and HS-27A': 8, + 'HADMSCs': 7, + 'HACs': 7, + 'MRC5': 7, + 'HeLa': 7, + 'RHECs': 6, + 'cardiomyocytes': 6, + 'human adipogenic mesenchymal stem cells': 6, + 'MSCs': 6, + 'HUVECs/MSCs': 6, + 'U87-MG': 6, + 'RSC96/HUVECs': 6, + 'HEPG2/ECs': 6, + 'A549': 6, + 'Human non-small cell lung cancer line Calu-3 (Calu-3)': 5, + 'hTMSCs': 5, + 'mouse cardiac cells': 5, + 'Human cardiac fibroblasts': 5, + 'Schwann cells': 5, + 'hTERT-MSC': 4, + 'bMSCs/hACs': 4, + 'basil plant cell': 4, + 'EPCs': 4, + 'HepaRG / LX-2': 4, + 'Caki-1': 4, + 'human induced pluripotent stem cell-derived cardiomyocytes': 4, + 'human epithelial lung carcinoma cells': 4, + 'HCF': 4, + 'Huh7': 4, + '3T3 Fibroblasts': 4, + 'EA.hy 926 cells': 4, + 'human coronary artery endothelial cells': 4, + 'NIH3T3/ HUVECs': 4, + 'neonatal rat ventricular CFs': 4, + 'HepG2/C3A': 4, + 'IMR-90': 4, + 'rMSC': 4, + 'hiPSC-CM / fibroblasts': 3, + 'HUVECs/H9C2': 3, + 'fibroblasts': 3, + 'Endothelial cells': 3, + 'neonatal rat ventricular cardiomyocytes': 3, + 'Neonatal mouse cardiomyocytes (NMVCMs)': 3, + 'murine macrophage-like cell line': 3, + '293FT': 3, + 'sADSC': 3, + 'human hepatic stellate cell line': 3, + 'aHSC': 3, + 'NRCMs': 3, + 'HBE': 3, + 'HEK-293': 3, + 'Wnt3a-293FT': 3, + 'Human aortic VIC': 3, + 'HEK 293FT': 3, + 'HNDF': 2, + 'Huh7/HepaRG': 2, + 'hiHeps': 2, + 'hCPCs': 2, + 'pancreatic islets cells': 2, + 'ICC': 2, + 'Wnt reporter-293FT': 2, + 'Human CPCs': 2, + 'human cardiac progenitor cells': 2, + 'SMC': 2, + 'hepatoma': 2, + 'cardiomyocyte/MSCs': 2, + 'FB': 2, + 'eHep': 2, + 'PMHs': 2, + 'Human CM /adult human fibroblasts': 2, + 'HUVSMCs': 2, + 'ACPCs': 2, + 'MC3T3': 2, + 'hNCs': 2, + 'primary rat hepatocyte': 2, + 'Human umbilical vein endothelial cells': 2, + 'HPAAF': 2, + 'VIC': 2, + 'HLC': 2, + 'ADSCs': 2, + 'MFCs': 2, + 'A549 GFP+': 2, + 'ATDC5': 2, + 'CFs/CMs/HUVECs': 2, + 'n neonatal mouse ventricular cardiomyocytes': 2, + 'Human MSCs': 2, + 'Human CPCs / MSCs': 2, + 'hESC-derived HLCs': 2, + 'HCASMCs': 2, + 'iCMs/iCFs/iECs/iCMFs': 1, + 'VICs': 1, + 'iPSCs': 1, + 'primary human hepatocytes': 1, + 'SMCs': 1, + 'iCMs/iCFs/iECs': 1, + 'PC9': 1, + 'H1395': 1, + 'H1650': 1, + 'HUVECs and hiPSC-CS': 1, + 'human neonatal dermal fi broblasts': 1, + '10T1/2 fibroblast-laden cells': 1, + 'iCMFs': 1, + 'neonatal rat ventricular CMs': 1, + 'U87': 1, + 'NSCLC PDX/CAFs': 1, + 'iPSC-derived CM': 1, + 'NIH 3T3 mouse fibroblasts': 1, + 'Neonatal rat cardiomyocytes': 1, + 'hiPSCs-derived HLCs': 1, + 'iPSCs/HUVECs': 1, + 'HULEC-5a': 1, + 'HUVECs and HHSCs': 1, + 'NCI-H1703': 1, + '75% hepatoblast cells, 20% iEC and 5% iMSC': 1, + 'Intrahepatic cholangiocarcinoma (ICC)': 1, + 'NCI-H441': 1, + 'Human Umbilical Vein Endothelial Cells + iPSC-derived CM': 1, + 'rabbit bone marrow mesenchymal stem cells': 1, + 'CMs/CFs': 1, + 'cardiac fibroblasts': 1, + 'iPSCs-derived cardiomyocytes': 1, + 'cardiomyocytes/ fibroblasts': 1, + 'hiPSC-CM': 1, + 'iPSC-CMs': 1, + 'hBM-MSCs': 1, + 'Hepatoblast- single cell/iESC/iMSC': 1, + 'Hepatoblast- spheroid/iESC/iMSC': 1, + 'human primary parathyroid cells': 1, + 'prostate cancer stem cell': 1, + 'HL-1': 1, + 'CPCs / MSCs': 1, + 'pancreatic cancer cell': 1, + 'A549/95-D cells': 1, + 'SMMC-7721': 1, + 'rat ventricular cardiomyocytes': 1, + 'A549 lung adenocarcinoma cells': 1, + 'HMEC-1/ fibroblast/ THP-1': 1, + 'HMEC-1': 1, + 'HAVSMC': 1, + 'HUVEC/HHSC': 1, + 'LX-2': 1, + 'Fibroblasts/THP-1': 1, + 'HLF': 1, + 'HUVECs / LX-2': 1, + 'CCAO': 1, + 'Hepa RG/ HUVEC': 1, + 'BEAS2B': 1, + 'PDGFRΞ²+': 1, + 'hMSCs': 1, + 'CiPSC-HOs': 1, + 'tubular epithelial': 1, +} + +# Density in 10^6 cells/mL, among records using that line. +CELL_DENSITY_RANGES = { + "NoCellCultured": { + "min": 1.0, + "max": 3.0, + "median": 1.0 + }, + "HUVECs": { + "min": 0.035, + "max": 20.0, + "median": 5.0 + }, + "HepG2": { + "min": 1.0, + "max": 20.0, + "median": 1.5 + }, + "bMSCs": { + "min": 0.25, + "max": 20.0, + "median": 10.0 + }, + "chondrocytes": { + "min": 0.1, + "max": 6.0, + "median": 6.0 + }, + "NIH3T3": { + "min": 0.1, + "max": 5.0, + "median": 2.5 + }, + "HepaRG": { + "min": 1.0, + "max": 20.0, + "median": 4.0 + }, + "hiPSC-CMs /ATCCs": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "Myoblast cells": { + "min": 0.366, + "max": 10.0, + "median": 1.0 + }, + "H9c2": { + "min": 0.04, + "max": 1.0, + "median": 1.0 + }, + "HEK": { + "min": 3.0, + "max": 3.0, + "median": 3.0 + }, + "CPCs": { + "min": 2.0, + "max": 8.0, + "median": 2.0 + }, + "MESCs": { + "min": 0.5, + "max": 2.0, + "median": 1.0 + }, + "hiPSCs": { + "min": 1.0, + "max": 15.0, + "median": 15.0 + }, + "L929": { + "min": 0.1, + "max": 10.0, + "median": 1.0 + }, + "Primary mouse hepatocyte": { + "min": 0.128, + "max": 1.0, + "median": 0.128 + }, + "NSCLC PDX": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "human primary kidney cells": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "Cardiac progenitor cells": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "10T1/2": { + "min": 0.5, + "max": 2.0, + "median": 0.5 + }, + "HAVIC": { + "min": 2.5, + "max": 10.0, + "median": 3.75 + }, + "RAMECs": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "hESCs": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "human nasoseptal chondrocytes": { + "min": 4.0, + "max": 4.0, + "median": 4.0 + }, + "PDX": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "PTECs": { + "min": 15.0, + "max": 15.0, + "median": 15.0 + }, + "HPFs": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "MG-63": { + "min": 0.005, + "max": 5.0, + "median": 0.005 + }, + "dermal fibroblasts": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "HASSMC": { + "min": 2.5, + "max": 2.5, + "median": 2.5 + }, + "Saos-2": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "MC3T3-E1": { + "min": 30.0, + "max": 30.0, + "median": 30.0 + }, + "hASCs": { + "min": 1.0, + "max": 2.0, + "median": 1.3 + }, + "SU3": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "ESCs": { + "min": 6.0, + "max": 10.0, + "median": 8.0 + }, + "RPTEC/TERT1": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "hiPSC-CMs and HS-27A": { + "min": 20.0, + "max": 20.0, + "median": 20.0 + }, + "HADMSCs": { + "min": 2.0, + "max": 2.5, + "median": 2.5 + }, + "HACs": { + "min": 5.0, + "max": 15.0, + "median": 5.0 + }, + "MRC5": { + "min": 0.04, + "max": 5.0, + "median": 3.0 + }, + "HeLa": { + "min": 1.0, + "max": 150.0, + "median": 1.0 + }, + "RHECs": { + "min": 0.5, + "max": 0.5, + "median": 0.5 + }, + "cardiomyocytes": { + "min": 0.2, + "max": 10.0, + "median": 6.0 + }, + "human adipogenic mesenchymal stem cells": { + "min": 0.75, + "max": 2.25, + "median": 1.125 + }, + "MSCs": { + "min": 0.2, + "max": 5.0, + "median": 1.0 + }, + "HUVECs/MSCs": { + "min": 6.0, + "max": 6.0, + "median": 6.0 + }, + "U87-MG": { + "min": 5.25, + "max": 5.25, + "median": 5.25 + }, + "RSC96/HUVECs": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "HEPG2/ECs": { + "min": 6.0, + "max": 6.0, + "median": 6.0 + }, + "A549": { + "min": 1.0, + "max": 5.0, + "median": 2.5 + }, + "Human non-small cell lung cancer line Calu-3 (Calu-3)": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "hTMSCs": { + "min": 3.5, + "max": 3.5, + "median": 3.5 + }, + "mouse cardiac cells": { + "min": 0.32, + "max": 0.32, + "median": 0.32 + }, + "Human cardiac fibroblasts": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "Schwann cells": { + "min": 1.0, + "max": 2.0, + "median": 1.0 + }, + "hTERT-MSC": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "bMSCs/hACs": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "EPCs": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "HepaRG / LX-2": { + "min": 1.5, + "max": 3.0, + "median": 3.0 + }, + "Caki-1": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "human induced pluripotent stem cell-derived cardiomyocytes": { + "min": 20.0, + "max": 20.0, + "median": 20.0 + }, + "human epithelial lung carcinoma cells": { + "min": 7.0, + "max": 7.0, + "median": 7.0 + }, + "HCF": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "Huh7": { + "min": 0.5, + "max": 0.5, + "median": 0.5 + }, + "3T3 Fibroblasts": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "EA.hy 926 cells": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "human coronary artery endothelial cells": { + "min": 0.8, + "max": 1.0, + "median": 0.8 + }, + "NIH3T3/ HUVECs": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "neonatal rat ventricular CFs": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "HepG2/C3A": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "IMR-90": { + "min": 3.5, + "max": 3.5, + "median": 3.5 + }, + "rMSC": { + "min": 3.5, + "max": 3.5, + "median": 3.5 + }, + "hiPSC-CM / fibroblasts": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "HUVECs/H9C2": { + "min": 4.0, + "max": 4.0, + "median": 4.0 + }, + "fibroblasts": { + "min": 1.0, + "max": 10.0, + "median": 3.0 + }, + "neonatal rat ventricular cardiomyocytes": { + "min": 1.0, + "max": 200.0, + "median": 1.0 + }, + "Neonatal mouse cardiomyocytes (NMVCMs)": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "murine macrophage-like cell line": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "293FT": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "sADSC": { + "min": 1.0, + "max": 3.0, + "median": 2.0 + }, + "human hepatic stellate cell line": { + "min": 3.0, + "max": 5.0, + "median": 4.0 + }, + "aHSC": { + "min": 3.0, + "max": 5.0, + "median": 4.0 + }, + "NRCMs": { + "min": 20.0, + "max": 20.0, + "median": 20.0 + }, + "HBE": { + "min": 0.13, + "max": 0.13, + "median": 0.13 + }, + "HEK-293": { + "min": 0.05, + "max": 2.0, + "median": 2.0 + }, + "Wnt3a-293FT": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "Human aortic VIC": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "HEK 293FT": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "HNDF": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "Huh7/HepaRG": { + "min": 1.5, + "max": 1.5, + "median": 1.5 + }, + "hiHeps": { + "min": 10.0, + "max": 50.0, + "median": 30.0 + }, + "hCPCs": { + "min": 3.0, + "max": 3.0, + "median": 3.0 + }, + "pancreatic islets cells": { + "min": 0.045, + "max": 0.045, + "median": 0.045 + }, + "ICC": { + "min": 3.0, + "max": 6.0, + "median": 4.5 + }, + "Wnt reporter-293FT": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "Human CPCs": { + "min": 5e-06, + "max": 5.0, + "median": 2.5000025 + }, + "human cardiac progenitor cells": { + "min": 3.0, + "max": 3.0, + "median": 3.0 + }, + "SMC": { + "min": 2.0, + "max": 10.0, + "median": 6.0 + }, + "hepatoma": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "cardiomyocyte/MSCs": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "FB": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "eHep": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "PMHs": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "Human CM /adult human fibroblasts": { + "min": 0.01, + "max": 0.2, + "median": 0.10500000000000001 + }, + "HUVSMCs": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "ACPCs": { + "min": 20.0, + "max": 20.0, + "median": 20.0 + }, + "MC3T3": { + "min": 0.25, + "max": 0.25, + "median": 0.25 + }, + "hNCs": { + "min": 1.0, + "max": 15.0, + "median": 8.0 + }, + "primary rat hepatocyte": { + "min": 1.0, + "max": 5.0, + "median": 3.0 + }, + "Human umbilical vein endothelial cells": { + "min": 1.25, + "max": 10.0, + "median": 5.625 + }, + "HPAAF": { + "min": 0.4, + "max": 4.0, + "median": 2.2 + }, + "VIC": { + "min": 2.0, + "max": 10.0, + "median": 6.0 + }, + "HLC": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "ADSCs": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "MFCs": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "A549 GFP+": { + "min": 1.5, + "max": 1.5, + "median": 1.5 + }, + "ATDC5": { + "min": 5.68, + "max": 5.68, + "median": 5.68 + }, + "CFs/CMs/HUVECs": { + "min": 30.0, + "max": 30.0, + "median": 30.0 + }, + "n neonatal mouse ventricular cardiomyocytes": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "Human MSCs": { + "min": 5e-06, + "max": 5.0, + "median": 2.5000025 + }, + "Human CPCs / MSCs": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "hESC-derived HLCs": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "HCASMCs": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "iCMs/iCFs/iECs/iCMFs": { + "min": 3.87, + "max": 3.87, + "median": 3.87 + }, + "VICs": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "iPSCs": { + "min": 8.0, + "max": 8.0, + "median": 8.0 + }, + "primary human hepatocytes": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "SMCs": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "iCMs/iCFs/iECs": { + "min": 9.6, + "max": 9.6, + "median": 9.6 + }, + "PC9": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "H1395": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "H1650": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "HUVECs and hiPSC-CS": { + "min": 0.01, + "max": 0.01, + "median": 0.01 + }, + "human neonatal dermal fi broblasts": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "10T1/2 fibroblast-laden cells": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "iCMFs": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "neonatal rat ventricular CMs": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "U87": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "NSCLC PDX/CAFs": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "iPSC-derived CM": { + "min": 8.0, + "max": 8.0, + "median": 8.0 + }, + "NIH 3T3 mouse fibroblasts": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "Neonatal rat cardiomyocytes": { + "min": 0.2, + "max": 0.2, + "median": 0.2 + }, + "hiPSCs-derived HLCs": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "iPSCs/HUVECs": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "HULEC-5a": { + "min": 6.0, + "max": 6.0, + "median": 6.0 + }, + "HUVECs and HHSCs": { + "min": 1.8, + "max": 1.8, + "median": 1.8 + }, + "NCI-H1703": { + "min": 6.0, + "max": 6.0, + "median": 6.0 + }, + "75% hepatoblast cells, 20% iEC and 5% iMSC": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "Intrahepatic cholangiocarcinoma (ICC)": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "NCI-H441": { + "min": 6.0, + "max": 6.0, + "median": 6.0 + }, + "Human Umbilical Vein Endothelial Cells + iPSC-derived CM": { + "min": 6.0, + "max": 6.0, + "median": 6.0 + }, + "rabbit bone marrow mesenchymal stem cells": { + "min": 0.1, + "max": 0.1, + "median": 0.1 + }, + "CMs/CFs": { + "min": 30.0, + "max": 30.0, + "median": 30.0 + }, + "cardiac fibroblasts": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "iPSCs-derived cardiomyocytes": { + "min": 200.0, + "max": 200.0, + "median": 200.0 + }, + "cardiomyocytes/ fibroblasts": { + "min": 0.2, + "max": 0.2, + "median": 0.2 + }, + "hiPSC-CM": { + "min": 0.2, + "max": 0.2, + "median": 0.2 + }, + "iPSC-CMs": { + "min": 4.0, + "max": 4.0, + "median": 4.0 + }, + "hBM-MSCs": { + "min": 0.25, + "max": 0.25, + "median": 0.25 + }, + "Hepatoblast- single cell/iESC/iMSC": { + "min": 5.6, + "max": 5.6, + "median": 5.6 + }, + "Hepatoblast- spheroid/iESC/iMSC": { + "min": 5.6, + "max": 5.6, + "median": 5.6 + }, + "human primary parathyroid cells": { + "min": 0.06, + "max": 0.06, + "median": 0.06 + }, + "prostate cancer stem cell": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "HL-1": { + "min": 8.0, + "max": 8.0, + "median": 8.0 + }, + "CPCs / MSCs": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "pancreatic cancer cell": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "A549/95-D cells": { + "min": 1.0, + "max": 1.0, + "median": 1.0 + }, + "SMMC-7721": { + "min": 0.5, + "max": 0.5, + "median": 0.5 + }, + "rat ventricular cardiomyocytes": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "A549 lung adenocarcinoma cells": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "HMEC-1/ fibroblast/ THP-1": { + "min": 35.0, + "max": 35.0, + "median": 35.0 + }, + "HMEC-1": { + "min": 25.0, + "max": 25.0, + "median": 25.0 + }, + "HAVSMC": { + "min": 1.5, + "max": 1.5, + "median": 1.5 + }, + "HUVEC/HHSC": { + "min": 0.9, + "max": 0.9, + "median": 0.9 + }, + "LX-2": { + "min": 0.5, + "max": 0.5, + "median": 0.5 + }, + "Fibroblasts/THP-1": { + "min": 14.25, + "max": 14.25, + "median": 14.25 + }, + "HLF": { + "min": 5.0, + "max": 5.0, + "median": 5.0 + }, + "HUVECs / LX-2": { + "min": 10.0, + "max": 10.0, + "median": 10.0 + }, + "CCAO": { + "min": 0.02, + "max": 0.02, + "median": 0.02 + }, + "Hepa RG/ HUVEC": { + "min": 20.0, + "max": 20.0, + "median": 20.0 + }, + "BEAS2B": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "PDGFR\u03b2+": { + "min": 0.25, + "max": 0.25, + "median": 0.25 + }, + "hMSCs": { + "min": 2.0, + "max": 2.0, + "median": 2.0 + }, + "CiPSC-HOs": { + "min": 2.5, + "max": 2.5, + "median": 2.5 + }, + "tubular epithelial": { + "min": 0.4, + "max": 0.4, + "median": 0.4 + } +} diff --git a/corpus_reference.json b/corpus_reference.json new file mode 100644 index 0000000000000000000000000000000000000000..6ecaefebee6c839471b20999cc328eceb7b67d8c --- /dev/null +++ b/corpus_reference.json @@ -0,0 +1,289 @@ +{ + "biomaterials": [ + "Alginate (%w/v)", + "PVA-HA (%w/v)", + "CaSO4 (%w/v)", + "Na2HPO4 (%w/v)", + "Gelatin (%w/v)", + "GelMA (%w/v)", + "laponite (%w/v)", + "graphene oxide (%w/v)", + "hydroxyapatite (%w/v)", + "Hyaluronic_Acid (%w/v)", + "hyaluronan methacrylate (%w/v)", + "NorHA (%w/v)", + "Fibroin/Fibrinogen (%w/v)", + "Pluronic P-123 (%w/v)", + "Collagen (%w/v)", + "Chitosan (%w/v)", + "CS-AEMA (%w/v)", + "RGD (mM)", + "TCP (%w/v)", + "Gellan (%w/v)", + "bioactive glass (%w/v)", + "Nano/Methylcellulose (%w/v)", + "PEGTA (%w/v)", + "PEGMA (%w/v)", + "PEGDA (%w/v)", + "Agarose (%w/v)", + "hyaluronic acid+ Ph moieties (%w/v)", + "matrigel (%w/v)", + "CaCl2 (mM)", + "NaCl (mM)", + "BaCl2 (mM)", + "SrCl2 (mM)", + "CaCO3 (mM)", + "Genipin (%w/v)", + "PVA (%wt)", + "trans-glutaminase (%w/v)", + "alginate lyase (U/ml)", + "D-glucose (%w/v)", + "PLGA (%w/v)", + "vascular tissue-derived dECM (%w/v)", + "PEG-8-SH (mM)", + "Alginate dialdehyde (%w/v)", + "Alginate sulfate (%w/v)", + "RGD-modified alginate (%w/v)", + "poly(N-isopropylacrylamide) grafted hyaluronan (%w/v)", + "chondroitin sulfate methacrylate (%w/v)", + "PCL (%w/v)", + "alginate methacrylate (%w/v)", + "HRP (U/ml)", + "Pluronic F127 / Lutrol F127 (%w/v)", + "Irgacure 2959 (%w/v)", + "Eosin Y (%w/v)", + "Ruthenium (mM)", + "sodium persulfate (SPS) (mM)", + "HEPES (mM)", + "LAP (%w/v)", + "glutaraldehyde (%w/v)", + "PBS (M)", + "glycerol (%w/v)", + "cECM (%w/v)", + "gel-fu (%w/v)", + "Rose Bengal (%w/v)", + "Vitamin B2 (%w/v)", + "VEGF (%w/v)", + "Polypyrrole:PSS (%w/v)", + "borate bioactive glass (%w/v)", + "astaxanthin (%w/v)", + "PRP (%v/v)", + "methacrylated collagen (%w/v)", + "\u03b1-Toc (\u00b5M)", + "ascorbic acid (mM)", + "Liver dECM (%w/v)", + "galactosylated alginate (%w/v)", + "SC-PEG (%w/v)", + "SFMA-L (%w/v)", + "SFMA-M (%w/v)", + "SFMA-H (%w/v)", + "KdECMMA (%w/v)", + "BA silk fibroin (%w/v)", + "Carrageenan (%v)", + "Carbopol ETD 2020 NF (%w/v)", + "Carbopol Ultrez 10 NF (%w/v)", + "Carbopol NF-980 (%w/v)", + "FBS (%v/v)", + "MeTro (%w/v)", + "Triethanolamine (%v/v)", + "PEG-Fibrinogen (%w/v)", + "polyethylene glycol dimethacrylate (%w/v)", + "aprotinin (\u00b5g/ml)", + "gold nanorod (mg/mL)", + "egg white (w/v)", + "1-Vinyl-2-pyrrolidone (v/v)", + "carboxyl functionalized carbon nanotubes (%w/v)", + "polyHIPE (%w/v)", + "\u03b2-D galactose (mM)", + "hydrogen peroxide (H2O2) (%v/v)", + "lactic acid (v/v)", + "NorCol (%w/v)", + "DTT (%w/v)", + "ammonium persulfate (mM)", + "diTyr-RGD (mM)", + "PHEG-Tyr (%w/v)", + "MMP2-degradable peptide (%w/v)", + "KdECM (%w/v)", + "EDC (mg)", + "NHS (mg)", + "VA086 (%w/v)", + "PGS (%w/v)", + "thiolated HA (%w/v)", + "boron nitride nanotubes (%w/v)", + "PEDOT:PSS (ul)", + "KCl (mM)", + "skeletal muscle ECM methacrylate (%w/v)", + "PEO (%w/v)", + "Carbon dots (mg/ml)", + "Laminin (ug/ml)", + "DF-PEG (%w/v)", + "omentum ECM (%w/v)", + "thrombin (unit/ml)", + "Carbon nanotube (CNT) (w/v)", + "Phytagel (%v)", + "Laponite-XLG (%w/w)", + "sodium carboxymethyl cellulose (mg)", + "lysozyme amyloid nanofibrils:gold nanoparticles (mg)", + "Lysozyme amyloid nanofibrils (mg)", + "rGO (mg/ml)", + "Methacrylated gellan gum (%w/v)", + "Acetylsalicylic Acid (%w/w)", + "PVA methacrylate (%w/v)", + "MXene (mg/ml)" + ], + "print_params": [ + "Physical Crosslinking Duration (s)", + "Photo Crosslinking Duration (s)", + "Extrusion Pressure (kPa)", + "Nozzle Movement Speed (mm/s)", + "Nozzle Diameter (\u00b5m)", + "Syringe Temperature (\u00b0C)", + "Substrate Temperature (\u00b0C)" + ], + "predictors": [ + "Alginate (%w/v)", + "PVA-HA (%w/v)", + "CaSO4 (%w/v)", + "Na2HPO4 (%w/v)", + "Gelatin (%w/v)", + "GelMA (%w/v)", + "laponite (%w/v)", + "graphene oxide (%w/v)", + "hydroxyapatite (%w/v)", + "Hyaluronic_Acid (%w/v)", + "hyaluronan methacrylate (%w/v)", + "NorHA (%w/v)", + "Fibroin/Fibrinogen (%w/v)", + "Pluronic P-123 (%w/v)", + "Collagen (%w/v)", + "Chitosan (%w/v)", + "CS-AEMA (%w/v)", + "RGD (mM)", + "TCP (%w/v)", + "Gellan (%w/v)", + "bioactive glass (%w/v)", + "Nano/Methylcellulose (%w/v)", + "PEGTA (%w/v)", + "PEGMA (%w/v)", + "PEGDA (%w/v)", + "Agarose (%w/v)", + "hyaluronic acid+ Ph moieties (%w/v)", + "matrigel (%w/v)", + "CaCl2 (mM)", + "NaCl (mM)", + "BaCl2 (mM)", + "SrCl2 (mM)", + "CaCO3 (mM)", + "Genipin (%w/v)", + "PVA (%wt)", + "trans-glutaminase (%w/v)", + "alginate lyase (U/ml)", + "D-glucose (%w/v)", + "PLGA (%w/v)", + "vascular tissue-derived dECM (%w/v)", + "PEG-8-SH (mM)", + "Alginate dialdehyde (%w/v)", + "Alginate sulfate (%w/v)", + "RGD-modified alginate (%w/v)", + "poly(N-isopropylacrylamide) grafted hyaluronan (%w/v)", + "chondroitin sulfate methacrylate (%w/v)", + "PCL (%w/v)", + "alginate methacrylate (%w/v)", + "HRP (U/ml)", + "Pluronic F127 / Lutrol F127 (%w/v)", + "Irgacure 2959 (%w/v)", + "Eosin Y (%w/v)", + "Ruthenium (mM)", + "sodium persulfate (SPS) (mM)", + "HEPES (mM)", + "LAP (%w/v)", + "glutaraldehyde (%w/v)", + "PBS (M)", + "glycerol (%w/v)", + "cECM (%w/v)", + "gel-fu (%w/v)", + "Rose Bengal (%w/v)", + "Vitamin B2 (%w/v)", + "VEGF (%w/v)", + "Polypyrrole:PSS (%w/v)", + "borate bioactive glass (%w/v)", + "astaxanthin (%w/v)", + "PRP (%v/v)", + "methacrylated collagen (%w/v)", + "\u03b1-Toc (\u00b5M)", + "ascorbic acid (mM)", + "Liver dECM (%w/v)", + "galactosylated alginate (%w/v)", + "SC-PEG (%w/v)", + "SFMA-L (%w/v)", + "SFMA-M (%w/v)", + "SFMA-H (%w/v)", + "KdECMMA (%w/v)", + "BA silk fibroin (%w/v)", + "Carrageenan (%v)", + "Carbopol ETD 2020 NF (%w/v)", + "Carbopol Ultrez 10 NF (%w/v)", + "Carbopol NF-980 (%w/v)", + "FBS (%v/v)", + "MeTro (%w/v)", + "Triethanolamine (%v/v)", + "PEG-Fibrinogen (%w/v)", + "polyethylene glycol dimethacrylate (%w/v)", + "aprotinin (\u00b5g/ml)", + "gold nanorod (mg/mL)", + "egg white (w/v)", + "1-Vinyl-2-pyrrolidone (v/v)", + "carboxyl functionalized carbon nanotubes (%w/v)", + "polyHIPE (%w/v)", + "\u03b2-D galactose (mM)", + "hydrogen peroxide (H2O2) (%v/v)", + "lactic acid (v/v)", + "NorCol (%w/v)", + "DTT (%w/v)", + "ammonium persulfate (mM)", + "diTyr-RGD (mM)", + "PHEG-Tyr (%w/v)", + "MMP2-degradable peptide (%w/v)", + "KdECM (%w/v)", + "EDC (mg)", + "NHS (mg)", + "VA086 (%w/v)", + "PGS (%w/v)", + "thiolated HA (%w/v)", + "boron nitride nanotubes (%w/v)", + "PEDOT:PSS (ul)", + "KCl (mM)", + "skeletal muscle ECM methacrylate (%w/v)", + "PEO (%w/v)", + "Carbon dots (mg/ml)", + "Laminin (ug/ml)", + "DF-PEG (%w/v)", + "omentum ECM (%w/v)", + "thrombin (unit/ml)", + "Carbon nanotube (CNT) (w/v)", + "Phytagel (%v)", + "Laponite-XLG (%w/w)", + "sodium carboxymethyl cellulose (mg)", + "lysozyme amyloid nanofibrils:gold nanoparticles (mg)", + "Lysozyme amyloid nanofibrils (mg)", + "rGO (mg/ml)", + "Methacrylated gellan gum (%w/v)", + "Acetylsalicylic Acid (%w/w)", + "PVA methacrylate (%w/v)", + "MXene (mg/ml)", + "Cell Line", + "Cell Density (million cells/mL)", + "Physical Crosslinking Duration (s)", + "Photo Crosslinking Duration (s)", + "Extrusion Pressure (kPa)", + "Nozzle Movement Speed (mm/s)", + "Nozzle Diameter (\u00b5m)", + "Syringe Temperature (\u00b0C)", + "Substrate Temperature (\u00b0C)" + ], + "targets": [ + "Printability", + "Cell Response" + ], + "n_records": 2646 +} \ No newline at end of file diff --git a/corpus_reference.parquet b/corpus_reference.parquet new file mode 100644 index 0000000000000000000000000000000000000000..d1b1c2bf93e43db369289b1f31e6e5b0b43d8134 --- /dev/null +++ b/corpus_reference.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93af4ac5ab671ead33c91de0ebcc7888b08c1d8b41abb217445f5404a609d584 +size 116700 diff --git a/deploy/models/classifiers/random/cell_response__adaboost.pkl b/deploy/models/classifiers/random/cell_response__adaboost.pkl new file mode 100644 index 0000000000000000000000000000000000000000..017caef1c356bda88c7fce7a56968b7defa7ba1d --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__adaboost.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8933115563a17d4ba1ce2bcb15daa1564c86e5b697a11a3350c8424fef507f93 +size 44341 diff --git a/deploy/models/classifiers/random/cell_response__bagged_trees.pkl b/deploy/models/classifiers/random/cell_response__bagged_trees.pkl new file mode 100644 index 0000000000000000000000000000000000000000..8b734c4e0afa001d65026cf81c22cdc3bf65fad2 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__bagged_trees.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec7fd79460aca6c9212d7757da8b19b01f50ef17b35fbb1e4817a935429fd8f3 +size 1306142 diff --git a/deploy/models/classifiers/random/cell_response__bernoulli_naive_bayes.pkl b/deploy/models/classifiers/random/cell_response__bernoulli_naive_bayes.pkl new file mode 100644 index 0000000000000000000000000000000000000000..cc3a48e886d6cb17228c64b5ba19d8a017710868 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__bernoulli_naive_bayes.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:282feda9b6e91e96d5dd1ec9cf6ec43d51e8658a38aae0ff94f763ee9e800368 +size 4218 diff --git a/deploy/models/classifiers/random/cell_response__catboost.pkl b/deploy/models/classifiers/random/cell_response__catboost.pkl new file mode 100644 index 0000000000000000000000000000000000000000..dc7f3b2a22bd5589d741fe48334516c821a8d528 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__catboost.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8acf6b8932614de2bd91250155ade47fe8a9249d4190d24aacb7212f8ec9a9f +size 110986 diff --git a/deploy/models/classifiers/random/cell_response__decision_tree.pkl b/deploy/models/classifiers/random/cell_response__decision_tree.pkl new file mode 100644 index 0000000000000000000000000000000000000000..047c494c72650bbadf9f2f466eecdd9405be2dfd --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__decision_tree.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fec56bf6dad067b23827be89f8a816e5c10871268acce82da80894fbb58a5e25 +size 3478 diff --git a/deploy/models/classifiers/random/cell_response__extra_tree.pkl b/deploy/models/classifiers/random/cell_response__extra_tree.pkl new file mode 100644 index 0000000000000000000000000000000000000000..8e48a8fa60b24aca9c1cbed0f106ab34ad747b2c --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__extra_tree.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0128ac01ef824a6b8df6f745106d695b6a593a292666ae517d3d68924d514153 +size 3469 diff --git a/deploy/models/classifiers/random/cell_response__extra_trees.pkl b/deploy/models/classifiers/random/cell_response__extra_trees.pkl new file mode 100644 index 0000000000000000000000000000000000000000..75c8b463045e8d230620b04b6f34f1cd159c743b --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__extra_trees.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a1ebaf96b9d13fcc91b5a3c1ca09633eab16f7b33162624917e435cde2f2efd +size 1600493 diff --git a/deploy/models/classifiers/random/cell_response__gaussian_naive_bayes.pkl b/deploy/models/classifiers/random/cell_response__gaussian_naive_bayes.pkl new file mode 100644 index 0000000000000000000000000000000000000000..7f259ccf8fe3140966d1cb3593e951bb30692e5a --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__gaussian_naive_bayes.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d00e8cc7debd29d176894f559c3b043bd0ef03c6b1d0ecc6c86fa2149f6855d0 +size 7337 diff --git a/deploy/models/classifiers/random/cell_response__gradient_boosting.pkl b/deploy/models/classifiers/random/cell_response__gradient_boosting.pkl new file mode 100644 index 0000000000000000000000000000000000000000..b34d78f59232f32bc17a7e2b4d847a8f7a950db1 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__gradient_boosting.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a4332f43c8af0932c05662b97fde1f0d67525773457cd72ddcc670273462767 +size 28636 diff --git a/deploy/models/classifiers/random/cell_response__hist_gradient_boosting.pkl b/deploy/models/classifiers/random/cell_response__hist_gradient_boosting.pkl new file mode 100644 index 0000000000000000000000000000000000000000..8692468053a620234949c2f5a5f27f7e545968e9 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__hist_gradient_boosting.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bf42d2ad81b2b130b6d295e9d97480d9ada674e89d701575c2bf7be6d379ecb +size 645934 diff --git a/deploy/models/classifiers/random/cell_response__k_nearest_neighbours.pkl b/deploy/models/classifiers/random/cell_response__k_nearest_neighbours.pkl new file mode 100644 index 0000000000000000000000000000000000000000..20c175eccfb494e0cf3aecb3c5f5f52711b1f5f1 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__k_nearest_neighbours.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780fbe925315a38f89bbf907dac7e4b1f587266533df7c0115e0fc04276b40a0 +size 53470 diff --git a/deploy/models/classifiers/random/cell_response__k_nn_distance_weighted.pkl b/deploy/models/classifiers/random/cell_response__k_nn_distance_weighted.pkl new file mode 100644 index 0000000000000000000000000000000000000000..4add6c6a102cb33066a1d889d9640718451f6121 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__k_nn_distance_weighted.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:534a360ee86a358052a823d1107c6c002e4e9ef58a3e84f1c2c860f025c2222d +size 127106 diff --git a/deploy/models/classifiers/random/cell_response__lightgbm.pkl b/deploy/models/classifiers/random/cell_response__lightgbm.pkl new file mode 100644 index 0000000000000000000000000000000000000000..78d1cbf9bb737d9cbb1c04595d560af0a33b472b --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__lightgbm.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c198a22bf0a01258f0e9196472c74797ae0529ab244b1c3e0fe0d6c40e1d23a +size 552411 diff --git a/deploy/models/classifiers/random/cell_response__linear_discriminant.pkl b/deploy/models/classifiers/random/cell_response__linear_discriminant.pkl new file mode 100644 index 0000000000000000000000000000000000000000..4dd13d52772f9f6fc2a833a07394f52c6c755048 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__linear_discriminant.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14d6b11c6b801eef3e7f9fa0c6ad28c0a9366fad15cce208bd00725d313adcb2 +size 145025 diff --git a/deploy/models/classifiers/random/cell_response__linear_svm.pkl b/deploy/models/classifiers/random/cell_response__linear_svm.pkl new file mode 100644 index 0000000000000000000000000000000000000000..2a43a9f98d77676dc67945e517c4da357e9dc9e9 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__linear_svm.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f41c3e869a8250cbbf74ea42271cd3a07684d46794b48a1ff042f29cf8cd9d9 +size 5535 diff --git a/deploy/models/classifiers/random/cell_response__logistic_regression.pkl b/deploy/models/classifiers/random/cell_response__logistic_regression.pkl new file mode 100644 index 0000000000000000000000000000000000000000..bc5d45247c5478daa519c7cdb39e212cb06edd1e --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__logistic_regression.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe67a6655375a6e0bfcc706115cc992ed566ba87e57a5696f22843b1b681c1a9 +size 6535 diff --git a/deploy/models/classifiers/random/cell_response__logistic_regression_balanced.pkl b/deploy/models/classifiers/random/cell_response__logistic_regression_balanced.pkl new file mode 100644 index 0000000000000000000000000000000000000000..571e087e7df6300280e95ddd89c0ef58ceba2d2d --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__logistic_regression_balanced.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc90e1018ef9d648de7adb5da1b60e267f4b1e357f538b8fdaa5c6b246c0c97d +size 6514 diff --git a/deploy/models/classifiers/random/cell_response__mlp_256_128.pkl b/deploy/models/classifiers/random/cell_response__mlp_256_128.pkl new file mode 100644 index 0000000000000000000000000000000000000000..e37a716d6f3d478396212b700dc8113772e0a1f2 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__mlp_256_128.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f4bf03e58aea3bb7c171b22d4bf03077652236328dcbf30317765bd28c95a35 +size 877150 diff --git a/deploy/models/classifiers/random/cell_response__nearest_centroid.pkl b/deploy/models/classifiers/random/cell_response__nearest_centroid.pkl new file mode 100644 index 0000000000000000000000000000000000000000..43cf0d5bd2194e0fb3b0463be402fba69babd01a --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__nearest_centroid.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:579188d8f4730741cc6d4fcec2d042de26c5f1c4e9810ab23851e2152ec467e3 +size 7171 diff --git a/deploy/models/classifiers/random/cell_response__passive_aggressive.pkl b/deploy/models/classifiers/random/cell_response__passive_aggressive.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c596abb82ab0a31dfd20ebac729a184eac966c14 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__passive_aggressive.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d8c577687544c0044204267fce8e94a8fcd695be0e7d8e4660e029bf2b409f7 +size 12296 diff --git a/deploy/models/classifiers/random/cell_response__perceptron.pkl b/deploy/models/classifiers/random/cell_response__perceptron.pkl new file mode 100644 index 0000000000000000000000000000000000000000..04e831d2a71c8f1fa76e9ddce3534acc413f8dde --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__perceptron.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12bd23ecb4a5e58d8a3ba47a549bc38b7e9d027a1dde92c474a5e673b8cd3d34 +size 4111 diff --git a/deploy/models/classifiers/random/cell_response__quadratic_discriminant.pkl b/deploy/models/classifiers/random/cell_response__quadratic_discriminant.pkl new file mode 100644 index 0000000000000000000000000000000000000000..bfd375ce878d2a8c0d1edde0cf1f1510e0459bf4 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__quadratic_discriminant.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:006ecba15ba6131d1dff15163c6168615363be3716e8eb3fc96a4b63b0f44fc7 +size 29521 diff --git a/deploy/models/classifiers/random/cell_response__random_forest.pkl b/deploy/models/classifiers/random/cell_response__random_forest.pkl new file mode 100644 index 0000000000000000000000000000000000000000..30cfee0993cc690843089867349a814ec04b08c0 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__random_forest.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b5b4c7ddd69ecf0575e2cad3dc3b94992ded2934f1fbc74498182984e396165 +size 4994 diff --git a/deploy/models/classifiers/random/cell_response__random_forest_balanced.pkl b/deploy/models/classifiers/random/cell_response__random_forest_balanced.pkl new file mode 100644 index 0000000000000000000000000000000000000000..bd532ae44a58103be95b677baf8118917e06fac7 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__random_forest_balanced.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be9e347e9d4921977931954bf9d2326544452d96d7bcd2e9ddbfae163a95b77 +size 3902841 diff --git a/deploy/models/classifiers/random/cell_response__ridge_classifier.pkl b/deploy/models/classifiers/random/cell_response__ridge_classifier.pkl new file mode 100644 index 0000000000000000000000000000000000000000..06c87b9e0b30df2bd9c349cc8f74060f42c5b1a8 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__ridge_classifier.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:887429d6d2f49ef7c671d9be75c29bb94bc1c7e3abbe202dba13596533c96af9 +size 6651 diff --git a/deploy/models/classifiers/random/cell_response__sgd_hinge.pkl b/deploy/models/classifiers/random/cell_response__sgd_hinge.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ea50fd72afe7ec2674c668fc9c0b07929ecbadff --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__sgd_hinge.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0070b38894cb7ef91f72dae63d7efe23ce835ee369e481d3b366062c886d3baa +size 4886 diff --git a/deploy/models/classifiers/random/cell_response__soft_voting_rf_xgb_lr.pkl b/deploy/models/classifiers/random/cell_response__soft_voting_rf_xgb_lr.pkl new file mode 100644 index 0000000000000000000000000000000000000000..79bf5d65fcd989401e4812a76a3753a9c0ec97c4 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__soft_voting_rf_xgb_lr.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f3ea953fb061519b7d0fa42416c8edacffc93f762e87cab7a90f5692643340 +size 5233168 diff --git a/deploy/models/classifiers/random/cell_response__stacking_rf_xgb_lr_lr.pkl b/deploy/models/classifiers/random/cell_response__stacking_rf_xgb_lr_lr.pkl new file mode 100644 index 0000000000000000000000000000000000000000..22c788506cb761efed15a90f5a3c91b78bd1ba67 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__stacking_rf_xgb_lr_lr.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ed798ca8edf3a2f54aae8fde0cc0aaa3eba4457897b97ffa19be49c85c035ba +size 5233839 diff --git a/deploy/models/classifiers/random/cell_response__svm_polynomial.pkl b/deploy/models/classifiers/random/cell_response__svm_polynomial.pkl new file mode 100644 index 0000000000000000000000000000000000000000..50aa98631c91f5633cd2a86e131cdb704a5a3883 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__svm_polynomial.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd644c182976274d6ec346169b332e3f18d29912c2152e91f3b6ae17c3155a34 +size 60088 diff --git a/deploy/models/classifiers/random/cell_response__svm_rbf.pkl b/deploy/models/classifiers/random/cell_response__svm_rbf.pkl new file mode 100644 index 0000000000000000000000000000000000000000..2204db0e8c7431af9ee262581aebd59cc69e47f8 --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__svm_rbf.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec357aa39dbb6631b933c1e98e4d4b2df6135cc5237a40b2d24dfb6c7d128e45 +size 66004 diff --git a/deploy/models/classifiers/random/cell_response__xgboost.pkl b/deploy/models/classifiers/random/cell_response__xgboost.pkl new file mode 100644 index 0000000000000000000000000000000000000000..aa3181e7f925c6170fbe4c7a39321c7145e7172b --- /dev/null +++ b/deploy/models/classifiers/random/cell_response__xgboost.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9408add167a4c715a875fd88daf4457c46f058ba91c8fa6f9ca57ce1b7d9bb8 +size 189666 diff --git a/deploy/models/classifiers/random/printability__adaboost.pkl b/deploy/models/classifiers/random/printability__adaboost.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c8cb37979e85e6008e2ff50cd1c96eadd1f863a2 --- /dev/null +++ b/deploy/models/classifiers/random/printability__adaboost.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61fa142eee65a9a3dab6e40de5ec7715340c56563254ca52623e45f0a3681625 +size 48212 diff --git a/deploy/models/classifiers/random/printability__bagged_trees.pkl b/deploy/models/classifiers/random/printability__bagged_trees.pkl new file mode 100644 index 0000000000000000000000000000000000000000..1b21ed4c8110e5ebac1fde706b617a318d8c775a --- /dev/null +++ b/deploy/models/classifiers/random/printability__bagged_trees.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98d12f997b7e7bcb6789ddbf32dacddcc53c859e265778f18682b7b693397e51 +size 3775738 diff --git a/deploy/models/classifiers/random/printability__bernoulli_naive_bayes.pkl b/deploy/models/classifiers/random/printability__bernoulli_naive_bayes.pkl new file mode 100644 index 0000000000000000000000000000000000000000..ad30d22d3f8c2df554e94d15098e07e61f00b35a --- /dev/null +++ b/deploy/models/classifiers/random/printability__bernoulli_naive_bayes.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98d82bc7b87ea7a6e51932768636f4f9cb2e62d7f796d1f1f2aa420230ae0071 +size 3497 diff --git a/deploy/models/classifiers/random/printability__catboost.pkl b/deploy/models/classifiers/random/printability__catboost.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c7973120687f66f1b5f4d43d95d9db335dd191dd --- /dev/null +++ b/deploy/models/classifiers/random/printability__catboost.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45c920875ad42ed56cade9561ab095e950e209819d68f2e061ff68534dd73fd3 +size 787008 diff --git a/deploy/models/classifiers/random/printability__decision_tree.pkl b/deploy/models/classifiers/random/printability__decision_tree.pkl new file mode 100644 index 0000000000000000000000000000000000000000..d1c15221e37eb85d2c717ced8200e4f7b978a667 --- /dev/null +++ b/deploy/models/classifiers/random/printability__decision_tree.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:768ec1872e1fc323154af785e6f71d554389de56fb43aa2c0624e6a70852a6b5 +size 10029 diff --git a/deploy/models/classifiers/random/printability__extra_tree.pkl b/deploy/models/classifiers/random/printability__extra_tree.pkl new file mode 100644 index 0000000000000000000000000000000000000000..a2c5a21a9f3c387a3027cf83b23bb9ca422a45e8 --- /dev/null +++ b/deploy/models/classifiers/random/printability__extra_tree.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:591f152e86031f04d9d92a5cd88164dcb636509e63d6726010c6814b512bfa75 +size 9601 diff --git a/deploy/models/classifiers/random/printability__extra_trees.pkl b/deploy/models/classifiers/random/printability__extra_trees.pkl new file mode 100644 index 0000000000000000000000000000000000000000..f24752d40524d82d373189cac889d9123eba24e1 --- /dev/null +++ b/deploy/models/classifiers/random/printability__extra_trees.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e152e1e7423d5e3306b7abe26ee13ed67596433b1e910f818ed6840a284fffa7 +size 487961 diff --git a/deploy/models/classifiers/random/printability__gaussian_naive_bayes.pkl b/deploy/models/classifiers/random/printability__gaussian_naive_bayes.pkl new file mode 100644 index 0000000000000000000000000000000000000000..960f73feb785386dbbd466ae1bff02e4c0b6ffc7 --- /dev/null +++ b/deploy/models/classifiers/random/printability__gaussian_naive_bayes.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d806b6407b0cc8ab12d7fa836dee8811e349c8e740b7983016111b02d2239223 +size 6142 diff --git a/deploy/models/classifiers/random/printability__gradient_boosting.pkl b/deploy/models/classifiers/random/printability__gradient_boosting.pkl new file mode 100644 index 0000000000000000000000000000000000000000..033d09710e14421fa052fc9d6b20727664cbda3b --- /dev/null +++ b/deploy/models/classifiers/random/printability__gradient_boosting.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47a1931819018e107c00db7279b2e46722b92606c7d7fc1bf95f5f2728e9e7fa +size 955239 diff --git a/deploy/models/classifiers/random/printability__hist_gradient_boosting.pkl b/deploy/models/classifiers/random/printability__hist_gradient_boosting.pkl new file mode 100644 index 0000000000000000000000000000000000000000..8a389d8dc652ca107eca536153b3f9b7c5fbb3fd --- /dev/null +++ b/deploy/models/classifiers/random/printability__hist_gradient_boosting.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8503f4f620cc539db9e017106b8df556958c3e3191c60da4568d428ac0e2f64f +size 1555799 diff --git a/deploy/models/classifiers/random/printability__k_nearest_neighbours.pkl b/deploy/models/classifiers/random/printability__k_nearest_neighbours.pkl new file mode 100644 index 0000000000000000000000000000000000000000..e794e7a5260383fea518f516034055bb3f98436e --- /dev/null +++ b/deploy/models/classifiers/random/printability__k_nearest_neighbours.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454d01feb6c9b0927614bf2537641b445aac81664bb0df17b33a7472fccceb49 +size 53695 diff --git a/deploy/models/classifiers/random/printability__k_nn_distance_weighted.pkl b/deploy/models/classifiers/random/printability__k_nn_distance_weighted.pkl new file mode 100644 index 0000000000000000000000000000000000000000..547d8bd15d0bef00e070d8c1699c5c516f2c8105 --- /dev/null +++ b/deploy/models/classifiers/random/printability__k_nn_distance_weighted.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f59127db7f4e8d30b7ad810bcdd3eda19749fb13b10ac68fe4e14a32991767 +size 53689 diff --git a/deploy/models/classifiers/random/printability__lightgbm.pkl b/deploy/models/classifiers/random/printability__lightgbm.pkl new file mode 100644 index 0000000000000000000000000000000000000000..489ae76f1a9709081de0183c17aafc321d913efc --- /dev/null +++ b/deploy/models/classifiers/random/printability__lightgbm.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59b18f86de402feafc810534cd093c2fe77af87772a1a20c37d050fbc643a1cc +size 1783453 diff --git a/deploy/models/classifiers/random/printability__linear_discriminant.pkl b/deploy/models/classifiers/random/printability__linear_discriminant.pkl new file mode 100644 index 0000000000000000000000000000000000000000..835d66457bcd7b510376ecdf2909d1192cf031dc --- /dev/null +++ b/deploy/models/classifiers/random/printability__linear_discriminant.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fc2a8a5bf25dc66cabbcc83dc091e8e36d9f7457ca09595f0ca7abc8086342f +size 142568 diff --git a/deploy/models/classifiers/random/printability__linear_svm.pkl b/deploy/models/classifiers/random/printability__linear_svm.pkl new file mode 100644 index 0000000000000000000000000000000000000000..4c5380c7433ee83d224cf82dc56e56047a28ed5d --- /dev/null +++ b/deploy/models/classifiers/random/printability__linear_svm.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5003a237f95531955627e47a8b231ebc28e5ac24a3e4a9ba7d6f36b63d2ee226 +size 5296 diff --git a/deploy/models/classifiers/random/printability__logistic_regression.pkl b/deploy/models/classifiers/random/printability__logistic_regression.pkl new file mode 100644 index 0000000000000000000000000000000000000000..7d06a2f879980a241479e20781c4a989413bceff --- /dev/null +++ b/deploy/models/classifiers/random/printability__logistic_regression.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e997dcc201a4019f483df41d3c34b500e5ddc28a3c07fa6127a484128f49ce14 +size 5402 diff --git a/deploy/models/classifiers/random/printability__logistic_regression_balanced.pkl b/deploy/models/classifiers/random/printability__logistic_regression_balanced.pkl new file mode 100644 index 0000000000000000000000000000000000000000..fb9089c0e9f6fc312a22391f2d759ecec77aa044 --- /dev/null +++ b/deploy/models/classifiers/random/printability__logistic_regression_balanced.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f60a3bf8190a0775b7e2cea7a65e037e9ead9001675af5ff2ed8c10e672749f +size 5487 diff --git a/deploy/models/classifiers/random/printability__mlp_256_128.pkl b/deploy/models/classifiers/random/printability__mlp_256_128.pkl new file mode 100644 index 0000000000000000000000000000000000000000..d2a9d1c9174be474a4ac6cfddf1646c46e68a87f --- /dev/null +++ b/deploy/models/classifiers/random/printability__mlp_256_128.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8aa16d753eb9aa0e2cb19177aec37ed56c01e9e714fd41977a4a9ddc303c892 +size 2479623 diff --git a/deploy/models/classifiers/random/printability__nearest_centroid.pkl b/deploy/models/classifiers/random/printability__nearest_centroid.pkl new file mode 100644 index 0000000000000000000000000000000000000000..360ebbd96e135d5b13514d7c9dbf3609d0aaa841 --- /dev/null +++ b/deploy/models/classifiers/random/printability__nearest_centroid.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3168f56946288cec73141c20b257408f14c852bd82c626b3387d35427b76297e +size 10675 diff --git a/deploy/models/classifiers/random/printability__passive_aggressive.pkl b/deploy/models/classifiers/random/printability__passive_aggressive.pkl new file mode 100644 index 0000000000000000000000000000000000000000..8271e51050310e49ec0582bd48297504d81de8dd --- /dev/null +++ b/deploy/models/classifiers/random/printability__passive_aggressive.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be8bfb9c6800ce38759f3d005afa519170f8cb4aa0f32239f1e9c42e5b29bc8 +size 10140 diff --git a/deploy/models/classifiers/random/printability__perceptron.pkl b/deploy/models/classifiers/random/printability__perceptron.pkl new file mode 100644 index 0000000000000000000000000000000000000000..7ca96243f348108e0cd855a69f0ccd35c0e5ecef --- /dev/null +++ b/deploy/models/classifiers/random/printability__perceptron.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:495b685690763c2aab0212fa584ce4e145709cf8a44479b760a320f1e13a8f25 +size 3788 diff --git a/deploy/models/classifiers/random/printability__quadratic_discriminant.pkl b/deploy/models/classifiers/random/printability__quadratic_discriminant.pkl new file mode 100644 index 0000000000000000000000000000000000000000..20536b6ba7594d8869d2994d5d9fce8b35750db0 --- /dev/null +++ b/deploy/models/classifiers/random/printability__quadratic_discriminant.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7424e80ca7b551781302e507fe091b26669c442d5fb984ae60b456cd23d50f6b +size 140334 diff --git a/deploy/models/classifiers/random/printability__random_forest.pkl b/deploy/models/classifiers/random/printability__random_forest.pkl new file mode 100644 index 0000000000000000000000000000000000000000..eff3b241c7996bdec01acc98ad44981cbfaa3867 --- /dev/null +++ b/deploy/models/classifiers/random/printability__random_forest.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:733cbf8260af6d48d37e4957131e63a12c3f97a0f8af09d7dd4671c27084bbd3 +size 262948 diff --git a/deploy/models/classifiers/random/printability__random_forest_balanced.pkl b/deploy/models/classifiers/random/printability__random_forest_balanced.pkl new file mode 100644 index 0000000000000000000000000000000000000000..0213c8494901edbd3d10c3250b55a90d7901a994 --- /dev/null +++ b/deploy/models/classifiers/random/printability__random_forest_balanced.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3ca33c2d3fa2f80dd020a52e2f9aa734426a255039ddbeb26978294b1b056d +size 2364519 diff --git a/deploy/models/classifiers/random/printability__ridge_classifier.pkl b/deploy/models/classifiers/random/printability__ridge_classifier.pkl new file mode 100644 index 0000000000000000000000000000000000000000..747dc7a996558c6099c0dc25b61ff3c8d20d4902 --- /dev/null +++ b/deploy/models/classifiers/random/printability__ridge_classifier.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ec918b7a29e97eb50805c91628d368fdeb6c69fe8e8e67e22ef11b4e9ec072b +size 5460 diff --git a/deploy/models/classifiers/random/printability__sgd_hinge.pkl b/deploy/models/classifiers/random/printability__sgd_hinge.pkl new file mode 100644 index 0000000000000000000000000000000000000000..946021b5e5f6d8e1b1ff5152eae0a15382fceb26 --- /dev/null +++ b/deploy/models/classifiers/random/printability__sgd_hinge.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52d0ab3869aab543e325f80253801b31222adda8bf462cad90f81aff6c9a5a62 +size 5438 diff --git a/deploy/models/classifiers/random/printability__soft_voting_rf_xgb_lr.pkl b/deploy/models/classifiers/random/printability__soft_voting_rf_xgb_lr.pkl new file mode 100644 index 0000000000000000000000000000000000000000..dcc52e6931f3fc89904b0e5d3fce7d16cf18d1c6 --- /dev/null +++ b/deploy/models/classifiers/random/printability__soft_voting_rf_xgb_lr.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:157f10b8830b617c7ceaddde35d625713c2dd4e0dfef8066a2ebfde00560f578 +size 6042980 diff --git a/deploy/models/classifiers/random/printability__stacking_rf_xgb_lr_lr.pkl b/deploy/models/classifiers/random/printability__stacking_rf_xgb_lr_lr.pkl new file mode 100644 index 0000000000000000000000000000000000000000..04cd5ccb9576a54bf1b4a336221b30f74c132344 --- /dev/null +++ b/deploy/models/classifiers/random/printability__stacking_rf_xgb_lr_lr.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42d86a8fced6c364b61c8a5bff18beeae49c1e11accb2fffc2c52322c6743db6 +size 6043500 diff --git a/deploy/models/classifiers/random/printability__svm_polynomial.pkl b/deploy/models/classifiers/random/printability__svm_polynomial.pkl new file mode 100644 index 0000000000000000000000000000000000000000..008bc4ce57c8ba74a257da5604192ea052b92626 --- /dev/null +++ b/deploy/models/classifiers/random/printability__svm_polynomial.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1c73dda1047c5a30d2849fff8b56d610e76c04d4f4435bf3bdc294b3c536720 +size 67092 diff --git a/deploy/models/classifiers/random/printability__svm_rbf.pkl b/deploy/models/classifiers/random/printability__svm_rbf.pkl new file mode 100644 index 0000000000000000000000000000000000000000..fd9db930cb6955ae7fb2d6f5d725ac4a74bec9d6 --- /dev/null +++ b/deploy/models/classifiers/random/printability__svm_rbf.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11f12577a98883c69cb233a01f3682a2e3846e28c2076e34002cd1293d92c9b1 +size 68766 diff --git a/deploy/models/classifiers/random/printability__xgboost.pkl b/deploy/models/classifiers/random/printability__xgboost.pkl new file mode 100644 index 0000000000000000000000000000000000000000..494fc042c99c2e346d16be65f75c425644b6ee95 --- /dev/null +++ b/deploy/models/classifiers/random/printability__xgboost.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:456035d8a5b709323c9025021c4cc405b320ef19c12922d5343d3544f5e31fda +size 651415 diff --git a/deploy/models/deep/random/cell_response__1d_cnn.pt b/deploy/models/deep/random/cell_response__1d_cnn.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6a0e5404e71afaba7c86f02f4c444c6ef114cbc --- /dev/null +++ b/deploy/models/deep/random/cell_response__1d_cnn.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c8f12a5c725035f14226225d60bda49a4340889d2d5d7701e81f0fece22c60f +size 2255387 diff --git a/deploy/models/deep/random/cell_response__ft_transformer.pt b/deploy/models/deep/random/cell_response__ft_transformer.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ce9a9c3802ebfcfd529455ea7fa73cfac23c863 --- /dev/null +++ b/deploy/models/deep/random/cell_response__ft_transformer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae43a34114cd48bd3e3c699cbd5a4f008554a9f0ff4b29c085786a248a617bc +size 10286706 diff --git a/deploy/models/deep/random/cell_response__mlp.pt b/deploy/models/deep/random/cell_response__mlp.pt new file mode 100644 index 0000000000000000000000000000000000000000..6c1e3776115fd9758c926dd0f2c41df33cedaa4d --- /dev/null +++ b/deploy/models/deep/random/cell_response__mlp.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f89dec0eab3df20f4030b36d6d270d27578b3eeb5959638f00cc0f13094fa8ad +size 2459549 diff --git a/deploy/models/deep/random/cell_response__node_lite.pt b/deploy/models/deep/random/cell_response__node_lite.pt new file mode 100644 index 0000000000000000000000000000000000000000..e6773ec283b6f271daf243f3e2afe3f308353476 --- /dev/null +++ b/deploy/models/deep/random/cell_response__node_lite.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:037bb2ce02a8e9a2cdf5289e95dc70715a31581df37ae8de8723cb03b83220c3 +size 745231 diff --git a/deploy/models/deep/random/cell_response__resnet.pt b/deploy/models/deep/random/cell_response__resnet.pt new file mode 100644 index 0000000000000000000000000000000000000000..e60f05ccf6fb40c79d61d4328a7234abcfbfbea8 --- /dev/null +++ b/deploy/models/deep/random/cell_response__resnet.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5035fd746ebd5a80842e547a74ef84b9b6b7839b84f90a387130b0f3f68ec0f9 +size 357543 diff --git a/deploy/models/deep/random/cell_response__tabnet_lite.pt b/deploy/models/deep/random/cell_response__tabnet_lite.pt new file mode 100644 index 0000000000000000000000000000000000000000..9426def103dddad3f05f2e5f3efd92b17c124d00 --- /dev/null +++ b/deploy/models/deep/random/cell_response__tabnet_lite.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f64e7187426e3c8235da619d36604c80f02880b86b973bc701111459818d7a5d +size 3162629 diff --git a/deploy/models/deep/random/printability__1d_cnn.pt b/deploy/models/deep/random/printability__1d_cnn.pt new file mode 100644 index 0000000000000000000000000000000000000000..36c4ed31b3bb8d2de1117e320eb455b2f042c753 --- /dev/null +++ b/deploy/models/deep/random/printability__1d_cnn.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef3649953646a55eae781c730477fffe126874fc5737ecd3b923ab350f0a652 +size 7139363 diff --git a/deploy/models/deep/random/printability__ft_transformer.pt b/deploy/models/deep/random/printability__ft_transformer.pt new file mode 100644 index 0000000000000000000000000000000000000000..62168559c561c77ec1923b91c789e70e604a1d4e --- /dev/null +++ b/deploy/models/deep/random/printability__ft_transformer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2efe5b49d2317a1eb319c72c4608da81c25ea0988f30084607ff02e2e5ca9cc8 +size 3817667 diff --git a/deploy/models/deep/random/printability__mlp.pt b/deploy/models/deep/random/printability__mlp.pt new file mode 100644 index 0000000000000000000000000000000000000000..2de77ea09f98aab60dfd666ccd92034675d5bfe0 --- /dev/null +++ b/deploy/models/deep/random/printability__mlp.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24e5457124f01955414b7b080793e93f9b6efe1b9ec8adddcc8d2bfd80d5b692 +size 2181568 diff --git a/deploy/models/deep/random/printability__node_lite.pt b/deploy/models/deep/random/printability__node_lite.pt new file mode 100644 index 0000000000000000000000000000000000000000..d5155d0544ecbd9674ddf660353652ce9f822689 --- /dev/null +++ b/deploy/models/deep/random/printability__node_lite.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6cfab0ad5fb11fb0974e8b6c65e36fbfa099c13d0e665e5610fa0f3a4aa4bce +size 576316 diff --git a/deploy/models/deep/random/printability__resnet.pt b/deploy/models/deep/random/printability__resnet.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d7f81db8733f444788ba626185397a7fd1a5b30 --- /dev/null +++ b/deploy/models/deep/random/printability__resnet.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d4f4f7faa7b5a231e834c8a691601c8e80bb5694adbba815f27be1653ba5b05 +size 753903 diff --git a/deploy/models/deep/random/printability__tabnet_lite.pt b/deploy/models/deep/random/printability__tabnet_lite.pt new file mode 100644 index 0000000000000000000000000000000000000000..0799402fea69743588b0a074ef0ad2e636815e65 --- /dev/null +++ b/deploy/models/deep/random/printability__tabnet_lite.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65e43d38242eea53dd7709d714d052368c13984a1dfb1bb1c1b7e6c2a55f7c42 +size 1472384 diff --git a/deploy/models/deployment_manifest.json b/deploy/models/deployment_manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..c0af9f0c6865185f38db1224684daebb88c4f466 --- /dev/null +++ b/deploy/models/deployment_manifest.json @@ -0,0 +1,4933 @@ +{ + "created": "2026-09-05", + "selection": "weighted", + "protocols": [ + "random", + "doi" + ], + "fitted_on": "the complete dataset, behind the release preprocessor", + "selected_on": "the tuned configuration for each (task, protocol, model), chosen inside the training partition by 10-fold cross-validation", + "n_artefacts": 154, + "total_bytes": 143804929, + "models": [ + { + "family": "ml", + "task": "cell_response", + "model": "AdaBoost", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__adaboost.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7541, + "params": { + "n_estimators": 231, + "learning_rate": 1.1782013451884574 + }, + "metrics": { + "accuracy": 0.734, + "balanced_accuracy": 0.4229, + "macro_f1": 0.4199, + "weighted_f1": 0.7123, + "quadratic_kappa": 0.7937, + "kappa": 0.5478, + "mcc": 0.5556, + "roc_auc_weighted_ovr": 0.9102 + }, + "bytes": 44341, + "sha256": "8933115563a17d4ba1ce2bcb15daa1564c86e5b697a11a3350c8424fef507f93", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Bagged Trees", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__bagged_trees.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7745, + "params": { + "n_estimators": 133, + "max_samples": 0.9452775017696622, + "max_features": 0.5506389918878342, + "bootstrap": false, + "estimator__max_depth": 18, + "estimator__min_samples_leaf": 4 + }, + "metrics": { + "accuracy": 0.7774, + "balanced_accuracy": 0.5426, + "macro_f1": 0.5554, + "weighted_f1": 0.7729, + "quadratic_kappa": 0.8198, + "kappa": 0.6275, + "mcc": 0.6289, + "roc_auc_weighted_ovr": 0.9531 + }, + "bytes": 1306142, + "sha256": "ec7fd79460aca6c9212d7757da8b19b01f50ef17b35fbb1e4817a935429fd8f3", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Bernoulli Naive Bayes", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__bernoulli_naive_bayes.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7735, + "params": { + "alpha": 0.013244710803878143, + "binarize": 0.004147120866241897, + "fit_prior": true + }, + "metrics": { + "accuracy": 0.7453, + "balanced_accuracy": 0.5193, + "macro_f1": 0.5168, + "weighted_f1": 0.7432, + "quadratic_kappa": 0.7877, + "kappa": 0.5761, + "mcc": 0.5765, + "roc_auc_weighted_ovr": 0.9274 + }, + "bytes": 4218, + "sha256": "282feda9b6e91e96d5dd1ec9cf6ec43d51e8658a38aae0ff94f763ee9e800368", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "CatBoost", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__catboost.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7752, + "params": { + "iterations": 188, + "learning_rate": 0.1629637274346415, + "depth": 5, + "l2_leaf_reg": 4.712189903368168, + "bagging_temperature": 0.38131021691801714, + "random_strength": 1.0191560470062746, + "colsample_bylevel": 0.5323590714017395, + "bootstrap_type": "Bayesian" + }, + "metrics": { + "accuracy": 0.7472, + "balanced_accuracy": 0.4555, + "macro_f1": 0.4552, + "weighted_f1": 0.7289, + "quadratic_kappa": 0.7998, + "kappa": 0.5703, + "mcc": 0.5745, + "roc_auc_weighted_ovr": 0.9513 + }, + "bytes": 110986, + "sha256": "e8acf6b8932614de2bd91250155ade47fe8a9249d4190d24aacb7212f8ec9a9f", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Decision Tree", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__decision_tree.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7755, + "params": { + "criterion": "entropy", + "splitter": "best", + "max_depth": 31, + "min_samples_split": 8, + "min_samples_leaf": 1, + "max_features": null, + "ccp_alpha": 0.0047703143214407025 + }, + "metrics": { + "accuracy": 0.7472, + "balanced_accuracy": 0.466, + "macro_f1": 0.4787, + "weighted_f1": 0.7339, + "quadratic_kappa": 0.77, + "kappa": 0.5697, + "mcc": 0.5738, + "roc_auc_weighted_ovr": 0.9346 + }, + "bytes": 3478, + "sha256": "fec56bf6dad067b23827be89f8a816e5c10871268acce82da80894fbb58a5e25", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Extra Tree", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__extra_tree.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7508, + "params": { + "criterion": "log_loss", + "max_depth": 22, + "min_samples_split": 14, + "min_samples_leaf": 13, + "max_features": null, + "ccp_alpha": 0.004314149197954582 + }, + "metrics": { + "accuracy": 0.7396, + "balanced_accuracy": 0.4076, + "macro_f1": 0.3846, + "weighted_f1": 0.712, + "quadratic_kappa": 0.82, + "kappa": 0.5575, + "mcc": 0.5642, + "roc_auc_weighted_ovr": 0.9332 + }, + "bytes": 3469, + "sha256": "0128ac01ef824a6b8df6f745106d695b6a593a292666ae517d3d68924d514153", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Extra Trees", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__extra_trees.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7756, + "params": { + "n_estimators": 372, + "criterion": "entropy", + "max_depth": 53, + "min_samples_split": 2, + "min_samples_leaf": 3, + "max_features": null, + "bootstrap": true, + "ccp_alpha": 0.0034748638522106978 + }, + "metrics": { + "accuracy": 0.7453, + "balanced_accuracy": 0.4813, + "macro_f1": 0.4975, + "weighted_f1": 0.7335, + "quadratic_kappa": 0.7441, + "kappa": 0.5649, + "mcc": 0.5668, + "roc_auc_weighted_ovr": 0.9516 + }, + "bytes": 1600493, + "sha256": "2a1ebaf96b9d13fcc91b5a3c1ca09633eab16f7b33162624917e435cde2f2efd", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Gaussian Naive Bayes", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__gaussian_naive_bayes.pkl", + "source_fold": "random_holdout", + "inner_score": 0.3015, + "params": { + "var_smoothing": 8.75017262089054e-06 + }, + "metrics": { + "accuracy": 0.2698, + "balanced_accuracy": 0.401, + "macro_f1": 0.26, + "weighted_f1": 0.3115, + "quadratic_kappa": 0.3386, + "kappa": 0.1436, + "mcc": 0.1964, + "roc_auc_weighted_ovr": 0.8078 + }, + "bytes": 7337, + "sha256": "d00e8cc7debd29d176894f559c3b043bd0ef03c6b1d0ecc6c86fa2149f6855d0", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Gradient Boosting", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__gradient_boosting.pkl", + "source_fold": "random_holdout", + "inner_score": 0.69, + "params": { + "learning_rate": 0.04187594718900627, + "n_estimators": 164, + "subsample": 0.864803089169032, + "criterion": "squared_error", + "min_samples_split": 10, + "min_samples_leaf": 3, + "max_depth": 15, + "max_features": null, + "ccp_alpha": 0.02468977981821954 + }, + "metrics": { + "accuracy": 0.7358, + "balanced_accuracy": 0.385, + "macro_f1": 0.3083, + "weighted_f1": 0.6671, + "quadratic_kappa": 0.7765, + "kappa": 0.5473, + "mcc": 0.5899, + "roc_auc_weighted_ovr": 0.8972 + }, + "bytes": 28636, + "sha256": "0a4332f43c8af0932c05662b97fde1f0d67525773457cd72ddcc670273462767", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Hist Gradient Boosting", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__hist_gradient_boosting.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7831, + "params": { + "learning_rate": 0.017232330428016588, + "max_iter": 299, + "max_leaf_nodes": 11, + "max_depth": 29, + "min_samples_leaf": 8, + "l2_regularization": 0.6713320214175605, + "max_bins": 103, + "early_stopping": false, + "n_iter_no_change": 10 + }, + "metrics": { + "accuracy": 0.7698, + "balanced_accuracy": 0.5317, + "macro_f1": 0.5407, + "weighted_f1": 0.7674, + "quadratic_kappa": 0.8242, + "kappa": 0.6163, + "mcc": 0.6172, + "roc_auc_weighted_ovr": 0.9569 + }, + "bytes": 645934, + "sha256": "2bf42d2ad81b2b130b6d295e9d97480d9ada674e89d701575c2bf7be6d379ecb", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "LightGBM", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__lightgbm.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7749, + "params": { + "boosting_type": "gbdt", + "num_leaves": 234, + "max_depth": 36, + "learning_rate": 0.03878772651508437, + "n_estimators": 380, + "min_child_weight": 3.6500492398306026, + "min_child_samples": 29, + "subsample": 0.5671329236007874, + "subsample_freq": 4, + "colsample_bytree": 0.9308753250964105, + "reg_alpha": 4.430439770434747, + "reg_lambda": 3.2039662929835404 + }, + "metrics": { + "accuracy": 0.7434, + "balanced_accuracy": 0.4387, + "macro_f1": 0.4313, + "weighted_f1": 0.7267, + "quadratic_kappa": 0.8194, + "kappa": 0.5668, + "mcc": 0.5695, + "roc_auc_weighted_ovr": 0.9466 + }, + "bytes": 552411, + "sha256": "2c198a22bf0a01258f0e9196472c74797ae0529ab244b1c3e0fe0d6c40e1d23a", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Linear Discriminant", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__linear_discriminant.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7502, + "params": { + "shrinkage": 0.5, + "n_components": 3, + "tol": 0.000684792009557478 + }, + "metrics": { + "accuracy": 0.7113, + "balanced_accuracy": 0.4198, + "macro_f1": 0.4345, + "weighted_f1": 0.6865, + "quadratic_kappa": 0.6429, + "kappa": 0.4887, + "mcc": 0.494, + "roc_auc_weighted_ovr": 0.9254 + }, + "bytes": 145025, + "sha256": "14d6b11c6b801eef3e7f9fa0c6ad28c0a9366fad15cce208bd00725d313adcb2", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Linear SVM", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__linear_svm.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7695, + "params": { + "loss": "hinge", + "tol": 0.0017730095882880273, + "C": 0.28331414232062857, + "fit_intercept": true, + "intercept_scaling": 0.15066341859805293, + "max_iter": 3874, + "class_weight": "balanced" + }, + "metrics": { + "accuracy": 0.7208, + "balanced_accuracy": 0.4457, + "macro_f1": 0.4531, + "weighted_f1": 0.7032, + "quadratic_kappa": 0.7005, + "kappa": 0.5166, + "mcc": 0.52 + }, + "bytes": 5535, + "sha256": "6f41c3e869a8250cbbf74ea42271cd3a07684d46794b48a1ff042f29cf8cd9d9", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Logistic Regression", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__logistic_regression.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7566, + "params": { + "penalty": "l2", + "tol": 0.0010434843362977706, + "C": 2.9482840286713903, + "fit_intercept": true, + "solver": "lbfgs", + "max_iter": 1695 + }, + "metrics": { + "accuracy": 0.7151, + "balanced_accuracy": 0.4051, + "macro_f1": 0.405, + "weighted_f1": 0.6845, + "quadratic_kappa": 0.6747, + "kappa": 0.4962, + "mcc": 0.5017, + "roc_auc_weighted_ovr": 0.9248 + }, + "bytes": 6535, + "sha256": "fe67a6655375a6e0bfcc706115cc992ed566ba87e57a5696f22843b1b681c1a9", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Logistic Regression (balanced)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__logistic_regression_balanced.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7535, + "params": { + "penalty": null, + "tol": 0.006999971755699955, + "C": 0.22829596483959813, + "fit_intercept": false, + "solver": "lbfgs", + "max_iter": 1490 + }, + "metrics": { + "accuracy": 0.7245, + "balanced_accuracy": 0.4798, + "macro_f1": 0.4665, + "weighted_f1": 0.7287, + "quadratic_kappa": 0.809, + "kappa": 0.5462, + "mcc": 0.5499, + "roc_auc_weighted_ovr": 0.9354 + }, + "bytes": 6514, + "sha256": "fc90e1018ef9d648de7adb5da1b60e267f4b1e357f538b8fdaa5c6b246c0c97d", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "MLP (256-128)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__mlp_256_128.pkl", + "source_fold": "random_holdout", + "inner_score": 0.768, + "params": { + "hidden_layer_sizes": "128_64", + "activation": "logistic", + "solver": "adam", + "alpha": 0.012656977485848033, + "learning_rate": "invscaling", + "learning_rate_init": 0.00019998095347852762, + "max_iter": 964, + "tol": 2.4837224679225704e-05, + "early_stopping": false + }, + "metrics": { + "accuracy": 0.7302, + "balanced_accuracy": 0.4305, + "macro_f1": 0.4271, + "weighted_f1": 0.703, + "quadratic_kappa": 0.7048, + "kappa": 0.5288, + "mcc": 0.5332, + "roc_auc_weighted_ovr": 0.9242 + }, + "bytes": 877150, + "sha256": "2f4bf03e58aea3bb7c171b22d4bf03077652236328dcbf30317765bd28c95a35", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Nearest Centroid", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__nearest_centroid.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7277, + "params": { + "metric": "euclidean", + "shrink_threshold": 0.9941279891975694 + }, + "metrics": { + "accuracy": 0.6962, + "balanced_accuracy": 0.4824, + "macro_f1": 0.4397, + "weighted_f1": 0.679, + "quadratic_kappa": 0.6847, + "kappa": 0.4876, + "mcc": 0.4986, + "roc_auc_weighted_ovr": 0.9253 + }, + "bytes": 7171, + "sha256": "579188d8f4730741cc6d4fcec2d042de26c5f1c4e9810ab23851e2152ec467e3", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Passive Aggressive", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__passive_aggressive.pkl", + "source_fold": "random_holdout", + "inner_score": 0.767, + "params": { + "C": 0.013425018130283161, + "fit_intercept": false, + "max_iter": 2475, + "tol": 3.355037266594036e-05, + "early_stopping": false, + "validation_fraction": 0.27798997875789383, + "n_iter_no_change": 5, + "shuffle": true, + "loss": "hinge", + "class_weight": "balanced", + "average": true + }, + "metrics": { + "accuracy": 0.7151, + "balanced_accuracy": 0.4313, + "macro_f1": 0.4351, + "weighted_f1": 0.696, + "quadratic_kappa": 0.6917, + "kappa": 0.5053, + "mcc": 0.5091 + }, + "bytes": 12296, + "sha256": "6d8c577687544c0044204267fce8e94a8fcd695be0e7d8e4660e029bf2b409f7", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Perceptron", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__perceptron.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7248, + "params": { + "penalty": "elasticnet", + "alpha": 5.1407142801356526e-05, + "l1_ratio": 0.6344887536320425, + "fit_intercept": true, + "max_iter": 1082, + "tol": 0.0005236045454094717, + "shuffle": false, + "eta0": 0.4787761815206933, + "early_stopping": false, + "validation_fraction": 0.29793290974018816, + "n_iter_no_change": 9, + "class_weight": null + }, + "metrics": { + "accuracy": 0.6906, + "balanced_accuracy": 0.3888, + "macro_f1": 0.3847, + "weighted_f1": 0.6549, + "quadratic_kappa": 0.6081, + "kappa": 0.4438, + "mcc": 0.453 + }, + "bytes": 4111, + "sha256": "12bd23ecb4a5e58d8a3ba47a549bc38b7e9d027a1dde92c474a5e673b8cd3d34", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Quadratic Discriminant", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__quadratic_discriminant.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7694, + "params": { + "pca__n_components": 13, + "reg_param": 0.01803192183395734, + "store_covariance": true, + "tol": 0.0061904445700914235 + }, + "metrics": { + "accuracy": 0.7509, + "balanced_accuracy": 0.5069, + "macro_f1": 0.5131, + "weighted_f1": 0.7494, + "quadratic_kappa": 0.816, + "kappa": 0.5854, + "mcc": 0.5857, + "roc_auc_weighted_ovr": 0.9348 + }, + "bytes": 29521, + "sha256": "006ecba15ba6131d1dff15163c6168615363be3716e8eb3fc96a4b63b0f44fc7", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Random Forest", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__random_forest.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7382, + "params": { + "n_estimators": 300, + "criterion": "entropy", + "max_depth": 23, + "min_samples_split": 6, + "min_samples_leaf": 8, + "min_weight_fraction_leaf": 0.13609734250171107, + "max_features": null, + "bootstrap": false, + "ccp_alpha": 0.019326628857371634, + "max_samples": null + }, + "metrics": { + "accuracy": 0.7321, + "balanced_accuracy": 0.3988, + "macro_f1": 0.3641, + "weighted_f1": 0.7002, + "quadratic_kappa": 0.7967, + "kappa": 0.5457, + "mcc": 0.5558, + "roc_auc_weighted_ovr": 0.9055 + }, + "bytes": 4994, + "sha256": "1b5b4c7ddd69ecf0575e2cad3dc3b94992ded2934f1fbc74498182984e396165", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Random Forest (balanced)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__random_forest_balanced.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7736, + "params": { + "n_estimators": 500, + "criterion": "log_loss", + "max_depth": 10, + "min_samples_split": 3, + "min_samples_leaf": 4, + "min_weight_fraction_leaf": 0.003049996444172705, + "max_features": "sqrt", + "bootstrap": false, + "ccp_alpha": 0.00027927046656537474, + "max_samples": 0.8 + }, + "metrics": { + "accuracy": 0.7642, + "balanced_accuracy": 0.6028, + "macro_f1": 0.5605, + "weighted_f1": 0.7663, + "quadratic_kappa": 0.8182, + "kappa": 0.6154, + "mcc": 0.6194, + "roc_auc_weighted_ovr": 0.9464 + }, + "bytes": 3902841, + "sha256": "7be9e347e9d4921977931954bf9d2326544452d96d7bcd2e9ddbfae163a95b77", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Ridge Classifier", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__ridge_classifier.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7086, + "params": { + "alpha": 0.01699839043018258, + "fit_intercept": true, + "max_iter": 1413, + "tol": 1.1595408255619176e-05, + "solver": "saga" + }, + "metrics": { + "accuracy": 0.6906, + "balanced_accuracy": 0.3754, + "macro_f1": 0.3745, + "weighted_f1": 0.6479, + "quadratic_kappa": 0.6137, + "kappa": 0.4362, + "mcc": 0.4471 + }, + "bytes": 6651, + "sha256": "887429d6d2f49ef7c671d9be75c29bb94bc1c7e3abbe202dba13596533c96af9", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "SGD (hinge)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__sgd_hinge.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7583, + "params": { + "penalty": "l1", + "alpha": 7.034984795850037e-05, + "l1_ratio": 0.29856284659902343, + "fit_intercept": true, + "max_iter": 614, + "tol": 4.77764214879311e-05, + "learning_rate": "adaptive", + "eta0": 0.08855603039428027, + "early_stopping": false, + "validation_fraction": 0.1619562341957141, + "n_iter_no_change": 2 + }, + "metrics": { + "accuracy": 0.717, + "balanced_accuracy": 0.4069, + "macro_f1": 0.4061, + "weighted_f1": 0.6864, + "quadratic_kappa": 0.6874, + "kappa": 0.5004, + "mcc": 0.506 + }, + "bytes": 4886, + "sha256": "0070b38894cb7ef91f72dae63d7efe23ce835ee369e481d3b366062c886d3baa", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "SVM (RBF)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__svm_rbf.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7637, + "params": { + "C": 1.703442725584415, + "gamma": "scale", + "tol": 0.007922017270530962, + "shrinking": true, + "class_weight": null, + "decision_function_shape": "ovo" + }, + "metrics": { + "accuracy": 0.7057, + "balanced_accuracy": 0.3962, + "macro_f1": 0.398, + "weighted_f1": 0.6815, + "quadratic_kappa": 0.6976, + "kappa": 0.4878, + "mcc": 0.4913, + "roc_auc_weighted_ovr": 0.9219 + }, + "bytes": 66004, + "sha256": "ec357aa39dbb6631b933c1e98e4d4b2df6135cc5237a40b2d24dfb6c7d128e45", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "SVM (polynomial)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__svm_polynomial.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7677, + "params": { + "C": 0.8217470561673981, + "gamma": "scale", + "tol": 0.006748675390170305, + "shrinking": true, + "class_weight": null, + "decision_function_shape": "ovo", + "degree": 2, + "coef0": 0.1543457973837144 + }, + "metrics": { + "accuracy": 0.7151, + "balanced_accuracy": 0.396, + "macro_f1": 0.3932, + "weighted_f1": 0.6846, + "quadratic_kappa": 0.7016, + "kappa": 0.5004, + "mcc": 0.506, + "roc_auc_weighted_ovr": 0.9228 + }, + "bytes": 60088, + "sha256": "bd644c182976274d6ec346169b332e3f18d29912c2152e91f3b6ae17c3155a34", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Soft Voting (RF+XGB+LR)", + "protocol": "random", + "selection": "composed", + "file": "classifiers/random/cell_response__soft_voting_rf_xgb_lr.pkl", + "source_fold": "random_holdout", + "inner_score": null, + "params": { + "composed_from": [ + "Logistic Regression", + "Random Forest", + "XGBoost" + ] + }, + "metrics": { + "accuracy": 0.7585, + "balanced_accuracy": 0.4919, + "macro_f1": 0.5044, + "weighted_f1": 0.7444, + "quadratic_kappa": 0.7885, + "kappa": 0.5881, + "mcc": 0.5914, + "roc_auc_weighted_ovr": 0.95 + }, + "bytes": 5233168, + "sha256": "19f3ea953fb061519b7d0fa42416c8edacffc93f762e87cab7a90f5692643340", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Stacking (RF+XGB+LR -> LR)", + "protocol": "random", + "selection": "composed", + "file": "classifiers/random/cell_response__stacking_rf_xgb_lr_lr.pkl", + "source_fold": "random_holdout", + "inner_score": null, + "params": { + "composed_from": [ + "Logistic Regression", + "Random Forest", + "XGBoost" + ] + }, + "metrics": { + "accuracy": 0.7849, + "balanced_accuracy": 0.5358, + "macro_f1": 0.5542, + "weighted_f1": 0.7735, + "quadratic_kappa": 0.8186, + "kappa": 0.6361, + "mcc": 0.6413, + "roc_auc_weighted_ovr": 0.9486 + }, + "bytes": 5233839, + "sha256": "6ed798ca8edf3a2f54aae8fde0cc0aaa3eba4457897b97ffa19be49c85c035ba", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "XGBoost", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__xgboost.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7738, + "params": { + "n_estimators": 297, + "max_depth": 4, + "learning_rate": 0.07498039486034523, + "gamma": 1.4181682661295807, + "min_child_weight": 1.8432503737904644, + "subsample": 0.524250824250758, + "colsample_bytree": 0.5170505017122972, + "reg_alpha": 0.025940403490796626, + "reg_lambda": 2.6902781605693025 + }, + "metrics": { + "accuracy": 0.7396, + "balanced_accuracy": 0.4447, + "macro_f1": 0.4374, + "weighted_f1": 0.7243, + "quadratic_kappa": 0.8142, + "kappa": 0.5606, + "mcc": 0.5629, + "roc_auc_weighted_ovr": 0.9482 + }, + "bytes": 189666, + "sha256": "e9408add167a4c715a875fd88daf4457c46f058ba91c8fa6f9ca57ce1b7d9bb8", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "k-NN (distance weighted)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__k_nn_distance_weighted.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7492, + "params": { + "n_neighbors": 2, + "algorithm": "kd_tree", + "leaf_size": 30, + "p": 2, + "metric": "minkowski" + }, + "metrics": { + "accuracy": 0.7415, + "balanced_accuracy": 0.5231, + "macro_f1": 0.5237, + "weighted_f1": 0.7338, + "quadratic_kappa": 0.7408, + "kappa": 0.5629, + "mcc": 0.5648, + "roc_auc_weighted_ovr": 0.8354 + }, + "bytes": 127106, + "sha256": "534a360ee86a358052a823d1107c6c002e4e9ef58a3e84f1c2c860f025c2222d", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "k-Nearest Neighbours", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/cell_response__k_nearest_neighbours.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7461, + "params": { + "n_neighbors": 1, + "algorithm": "auto", + "leaf_size": 52, + "p": 2, + "metric": "euclidean" + }, + "metrics": { + "accuracy": 0.7302, + "balanced_accuracy": 0.4945, + "macro_f1": 0.4946, + "weighted_f1": 0.7215, + "quadratic_kappa": 0.742, + "kappa": 0.5434, + "mcc": 0.5449, + "roc_auc_weighted_ovr": 0.8195 + }, + "bytes": 53470, + "sha256": "780fbe925315a38f89bbf907dac7e4b1f587266533df7c0115e0fc04276b40a0", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "AdaBoost", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__adaboost.pkl", + "source_fold": "random_holdout", + "inner_score": 0.6138, + "params": { + "n_estimators": 271, + "learning_rate": 1.7549303968840675 + }, + "metrics": { + "accuracy": 0.6377, + "balanced_accuracy": 0.5121, + "macro_f1": 0.5137, + "weighted_f1": 0.6285, + "quadratic_kappa": 0.5031, + "kappa": 0.4322, + "mcc": 0.4336, + "roc_auc_weighted_ovr": 0.7692 + }, + "bytes": 48212, + "sha256": "61fa142eee65a9a3dab6e40de5ec7715340c56563254ca52623e45f0a3681625", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Bagged Trees", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__bagged_trees.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7677, + "params": { + "n_estimators": 193, + "max_samples": 0.7822899911930258, + "max_features": 0.8617320922989526, + "bootstrap": false, + "estimator__max_depth": 29, + "estimator__min_samples_leaf": 1 + }, + "metrics": { + "accuracy": 0.7943, + "balanced_accuracy": 0.7415, + "macro_f1": 0.7627, + "weighted_f1": 0.7922, + "quadratic_kappa": 0.8012, + "kappa": 0.6763, + "mcc": 0.6775, + "roc_auc_weighted_ovr": 0.915 + }, + "bytes": 3775738, + "sha256": "98d12f997b7e7bcb6789ddbf32dacddcc53c859e265778f18682b7b693397e51", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Bernoulli Naive Bayes", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__bernoulli_naive_bayes.pkl", + "source_fold": "random_holdout", + "inner_score": 0.6176, + "params": { + "alpha": 0.09984303783310336, + "binarize": 0.07979497095883875, + "fit_prior": true + }, + "metrics": { + "accuracy": 0.6415, + "balanced_accuracy": 0.5659, + "macro_f1": 0.5362, + "weighted_f1": 0.6425, + "quadratic_kappa": 0.5704, + "kappa": 0.4592, + "mcc": 0.4628, + "roc_auc_weighted_ovr": 0.8188 + }, + "bytes": 3497, + "sha256": "98d82bc7b87ea7a6e51932768636f4f9cb2e62d7f796d1f1f2aa420230ae0071", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "CatBoost", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__catboost.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7679, + "params": { + "iterations": 483, + "learning_rate": 0.2820482852343135, + "depth": 10, + "l2_leaf_reg": 4.368204366176838, + "bagging_temperature": 0.40835632276528555, + "random_strength": 2.8251241143568477, + "colsample_bylevel": 0.5491147709329218, + "bootstrap_type": "Bayesian" + }, + "metrics": { + "accuracy": 0.7887, + "balanced_accuracy": 0.7369, + "macro_f1": 0.7539, + "weighted_f1": 0.7864, + "quadratic_kappa": 0.7958, + "kappa": 0.6681, + "mcc": 0.6691, + "roc_auc_weighted_ovr": 0.9183 + }, + "bytes": 787008, + "sha256": "45c920875ad42ed56cade9561ab095e950e209819d68f2e061ff68534dd73fd3", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Decision Tree", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__decision_tree.pkl", + "source_fold": "random_holdout", + "inner_score": 0.6996, + "params": { + "criterion": "entropy", + "splitter": "best", + "max_depth": 16, + "min_samples_split": 15, + "min_samples_leaf": 7, + "max_features": null, + "ccp_alpha": 0.0011685585033690445 + }, + "metrics": { + "accuracy": 0.7132, + "balanced_accuracy": 0.6553, + "macro_f1": 0.6534, + "weighted_f1": 0.7116, + "quadratic_kappa": 0.6497, + "kappa": 0.5554, + "mcc": 0.5557, + "roc_auc_weighted_ovr": 0.8866 + }, + "bytes": 10029, + "sha256": "768ec1872e1fc323154af785e6f71d554389de56fb43aa2c0624e6a70852a6b5", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Extra Tree", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__extra_tree.pkl", + "source_fold": "random_holdout", + "inner_score": 0.6466, + "params": { + "criterion": "log_loss", + "max_depth": 33, + "min_samples_split": 7, + "min_samples_leaf": 12, + "max_features": null, + "ccp_alpha": 0.0003790042628302472 + }, + "metrics": { + "accuracy": 0.6585, + "balanced_accuracy": 0.5668, + "macro_f1": 0.5563, + "weighted_f1": 0.6487, + "quadratic_kappa": 0.5113, + "kappa": 0.4652, + "mcc": 0.4683, + "roc_auc_weighted_ovr": 0.8628 + }, + "bytes": 9601, + "sha256": "591f152e86031f04d9d92a5cd88164dcb636509e63d6726010c6814b512bfa75", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Extra Trees", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__extra_trees.pkl", + "source_fold": "random_holdout", + "inner_score": 0.735, + "params": { + "n_estimators": 61, + "criterion": "entropy", + "max_depth": 60, + "min_samples_split": 17, + "min_samples_leaf": 1, + "max_features": null, + "bootstrap": false, + "ccp_alpha": 0.0020050460186222235 + }, + "metrics": { + "accuracy": 0.7604, + "balanced_accuracy": 0.701, + "macro_f1": 0.7131, + "weighted_f1": 0.7602, + "quadratic_kappa": 0.6732, + "kappa": 0.6269, + "mcc": 0.6282, + "roc_auc_weighted_ovr": 0.9098 + }, + "bytes": 487961, + "sha256": "e152e1e7423d5e3306b7abe26ee13ed67596433b1e910f818ed6840a284fffa7", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Gaussian Naive Bayes", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__gaussian_naive_bayes.pkl", + "source_fold": "random_holdout", + "inner_score": 0.3059, + "params": { + "var_smoothing": 9.936989689136058e-06 + }, + "metrics": { + "accuracy": 0.2792, + "balanced_accuracy": 0.4067, + "macro_f1": 0.2763, + "weighted_f1": 0.3055, + "quadratic_kappa": 0.1707, + "kappa": 0.1353, + "mcc": 0.1813, + "roc_auc_weighted_ovr": 0.7057 + }, + "bytes": 6142, + "sha256": "d806b6407b0cc8ab12d7fa836dee8811e349c8e740b7983016111b02d2239223", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Gradient Boosting", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__gradient_boosting.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7396, + "params": { + "learning_rate": 0.029956893008933304, + "n_estimators": 378, + "subsample": 0.753883338314261, + "criterion": "squared_error", + "min_samples_split": 2, + "min_samples_leaf": 6, + "max_depth": 12, + "max_features": "sqrt", + "ccp_alpha": 0.0001345429344379672 + }, + "metrics": { + "accuracy": 0.766, + "balanced_accuracy": 0.6972, + "macro_f1": 0.7126, + "weighted_f1": 0.7629, + "quadratic_kappa": 0.6859, + "kappa": 0.6314, + "mcc": 0.6331, + "roc_auc_weighted_ovr": 0.9137 + }, + "bytes": 955239, + "sha256": "47a1931819018e107c00db7279b2e46722b92606c7d7fc1bf95f5f2728e9e7fa", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Hist Gradient Boosting", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__hist_gradient_boosting.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7669, + "params": { + "learning_rate": 0.3649609080693064, + "max_iter": 124, + "max_leaf_nodes": 67, + "max_depth": 24, + "min_samples_leaf": 6, + "l2_regularization": 0.5274651728863381, + "max_bins": 214, + "early_stopping": false, + "n_iter_no_change": 5 + }, + "metrics": { + "accuracy": 0.7868, + "balanced_accuracy": 0.7487, + "macro_f1": 0.7576, + "weighted_f1": 0.7843, + "quadratic_kappa": 0.8126, + "kappa": 0.6664, + "mcc": 0.6672, + "roc_auc_weighted_ovr": 0.9169 + }, + "bytes": 1555799, + "sha256": "8503f4f620cc539db9e017106b8df556958c3e3191c60da4568d428ac0e2f64f", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "LightGBM", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__lightgbm.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7554, + "params": { + "boosting_type": "gbdt", + "num_leaves": 98, + "max_depth": 31, + "learning_rate": 0.13822583920308426, + "n_estimators": 377, + "min_child_weight": 1.6897274615450322, + "min_child_samples": 30, + "subsample": 0.6668421259112413, + "subsample_freq": 5, + "colsample_bytree": 0.6742471046707172, + "reg_alpha": 0.19261465401965583, + "reg_lambda": 1.2666428268293457 + }, + "metrics": { + "accuracy": 0.7642, + "balanced_accuracy": 0.7082, + "macro_f1": 0.7119, + "weighted_f1": 0.7619, + "quadratic_kappa": 0.7879, + "kappa": 0.6328, + "mcc": 0.6332, + "roc_auc_weighted_ovr": 0.9139 + }, + "bytes": 1783453, + "sha256": "59b18f86de402feafc810534cd093c2fe77af87772a1a20c37d050fbc643a1cc", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Linear Discriminant", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__linear_discriminant.pkl", + "source_fold": "random_holdout", + "inner_score": 0.6221, + "params": { + "shrinkage": 0.1, + "n_components": 10, + "tol": 0.00788671412999049 + }, + "metrics": { + "accuracy": 0.6755, + "balanced_accuracy": 0.5515, + "macro_f1": 0.5591, + "weighted_f1": 0.6605, + "quadratic_kappa": 0.5274, + "kappa": 0.4807, + "mcc": 0.4852, + "roc_auc_weighted_ovr": 0.8344 + }, + "bytes": 142568, + "sha256": "7fc2a8a5bf25dc66cabbcc83dc091e8e36d9f7457ca09595f0ca7abc8086342f", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Linear SVM", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__linear_svm.pkl", + "source_fold": "random_holdout", + "inner_score": 0.6268, + "params": { + "loss": "squared_hinge", + "tol": 0.0004337854257719927, + "C": 5.266137427449793, + "fit_intercept": false, + "intercept_scaling": 0.16317458581616753, + "max_iter": 1287, + "class_weight": "balanced" + }, + "metrics": { + "accuracy": 0.634, + "balanced_accuracy": 0.6027, + "macro_f1": 0.5509, + "weighted_f1": 0.6458, + "quadratic_kappa": 0.5861, + "kappa": 0.463, + "mcc": 0.4694 + }, + "bytes": 5296, + "sha256": "5003a237f95531955627e47a8b231ebc28e5ac24a3e4a9ba7d6f36b63d2ee226", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Logistic Regression", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__logistic_regression.pkl", + "source_fold": "random_holdout", + "inner_score": 0.6363, + "params": { + "penalty": null, + "tol": 0.00010976829592516031, + "C": 91.0497240599568, + "fit_intercept": false, + "solver": "lbfgs", + "max_iter": 735 + }, + "metrics": { + "accuracy": 0.6717, + "balanced_accuracy": 0.5905, + "macro_f1": 0.5744, + "weighted_f1": 0.6652, + "quadratic_kappa": 0.5528, + "kappa": 0.4876, + "mcc": 0.4921, + "roc_auc_weighted_ovr": 0.8286 + }, + "bytes": 5402, + "sha256": "e997dcc201a4019f483df41d3c34b500e5ddc28a3c07fa6127a484128f49ce14", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Logistic Regression (balanced)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__logistic_regression_balanced.pkl", + "source_fold": "random_holdout", + "inner_score": 0.6029, + "params": { + "penalty": null, + "tol": 0.0027612366691185343, + "C": 0.01894372701657312, + "fit_intercept": true, + "solver": "saga", + "max_iter": 1069 + }, + "metrics": { + "accuracy": 0.6189, + "balanced_accuracy": 0.6111, + "macro_f1": 0.552, + "weighted_f1": 0.6365, + "quadratic_kappa": 0.5808, + "kappa": 0.4519, + "mcc": 0.4602, + "roc_auc_weighted_ovr": 0.8164 + }, + "bytes": 5487, + "sha256": "6f60a3bf8190a0775b7e2cea7a65e037e9ead9001675af5ff2ed8c10e672749f", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "MLP (256-128)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__mlp_256_128.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7367, + "params": { + "hidden_layer_sizes": "256_128_64", + "activation": "tanh", + "solver": "adam", + "alpha": 9.245123544012322e-05, + "learning_rate": "constant", + "learning_rate_init": 0.0026461810673864042, + "max_iter": 816, + "tol": 1.0723297771337903e-06, + "early_stopping": false + }, + "metrics": { + "accuracy": 0.7415, + "balanced_accuracy": 0.6977, + "macro_f1": 0.7058, + "weighted_f1": 0.7417, + "quadratic_kappa": 0.7449, + "kappa": 0.5998, + "mcc": 0.6, + "roc_auc_weighted_ovr": 0.8765 + }, + "bytes": 2479623, + "sha256": "a8aa16d753eb9aa0e2cb19177aec37ed56c01e9e714fd41977a4a9ddc303c892", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Nearest Centroid", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__nearest_centroid.pkl", + "source_fold": "random_holdout", + "inner_score": 0.4894, + "params": { + "metric": "euclidean", + "shrink_threshold": 0.005770218291259177 + }, + "metrics": { + "accuracy": 0.4642, + "balanced_accuracy": 0.4687, + "macro_f1": 0.4043, + "weighted_f1": 0.4995, + "quadratic_kappa": 0.3778, + "kappa": 0.269, + "mcc": 0.2855, + "roc_auc_weighted_ovr": 0.8096 + }, + "bytes": 10675, + "sha256": "3168f56946288cec73141c20b257408f14c852bd82c626b3387d35427b76297e", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Passive Aggressive", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__passive_aggressive.pkl", + "source_fold": "random_holdout", + "inner_score": 0.6302, + "params": { + "C": 25.273624580658733, + "fit_intercept": false, + "max_iter": 2073, + "tol": 0.08200442203212223, + "early_stopping": true, + "validation_fraction": 0.161658483756386, + "n_iter_no_change": 6, + "shuffle": true, + "loss": "squared_hinge", + "class_weight": "balanced", + "average": true + }, + "metrics": { + "accuracy": 0.6453, + "balanced_accuracy": 0.5998, + "macro_f1": 0.5594, + "weighted_f1": 0.6503, + "quadratic_kappa": 0.5455, + "kappa": 0.469, + "mcc": 0.4737 + }, + "bytes": 10140, + "sha256": "6be8bfb9c6800ce38759f3d005afa519170f8cb4aa0f32239f1e9c42e5b29bc8", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Perceptron", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__perceptron.pkl", + "source_fold": "random_holdout", + "inner_score": 0.5555, + "params": { + "penalty": "l1", + "alpha": 4.311623825732279e-05, + "l1_ratio": 0.959436622288464, + "fit_intercept": true, + "max_iter": 1691, + "tol": 6.119417887934741e-05, + "shuffle": true, + "eta0": 0.19986619824419047, + "early_stopping": false, + "validation_fraction": 0.27280241755001244, + "n_iter_no_change": 6, + "class_weight": null + }, + "metrics": { + "accuracy": 0.5358, + "balanced_accuracy": 0.3435, + "macro_f1": 0.3197, + "weighted_f1": 0.4388, + "quadratic_kappa": 0.2399, + "kappa": 0.1433, + "mcc": 0.1985 + }, + "bytes": 3788, + "sha256": "495b685690763c2aab0212fa584ce4e145709cf8a44479b760a320f1e13a8f25", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Quadratic Discriminant", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__quadratic_discriminant.pkl", + "source_fold": "random_holdout", + "inner_score": 0.5975, + "params": { + "pca__n_components": 50, + "reg_param": 0.3046137691733707, + "store_covariance": false, + "tol": 4.3743644399390745e-05 + }, + "metrics": { + "accuracy": 0.6189, + "balanced_accuracy": 0.5362, + "macro_f1": 0.513, + "weighted_f1": 0.6204, + "quadratic_kappa": 0.5446, + "kappa": 0.4306, + "mcc": 0.4389, + "roc_auc_weighted_ovr": 0.8164 + }, + "bytes": 140334, + "sha256": "7424e80ca7b551781302e507fe091b26669c442d5fb984ae60b456cd23d50f6b", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Random Forest", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__random_forest.pkl", + "source_fold": "random_holdout", + "inner_score": 0.5634, + "params": { + "n_estimators": 300, + "criterion": "log_loss", + "max_depth": 8, + "min_samples_split": 5, + "min_samples_leaf": 10, + "min_weight_fraction_leaf": 0.06238413725820846, + "max_features": null, + "bootstrap": true, + "ccp_alpha": 0.007654621119809567, + "max_samples": 0.8 + }, + "metrics": { + "accuracy": 0.6321, + "balanced_accuracy": 0.4528, + "macro_f1": 0.4351, + "weighted_f1": 0.5928, + "quadratic_kappa": 0.3945, + "kappa": 0.4081, + "mcc": 0.4229, + "roc_auc_weighted_ovr": 0.8216 + }, + "bytes": 262948, + "sha256": "733cbf8260af6d48d37e4957131e63a12c3f97a0f8af09d7dd4671c27084bbd3", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Random Forest (balanced)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__random_forest_balanced.pkl", + "source_fold": "random_holdout", + "inner_score": 0.6913, + "params": { + "n_estimators": 450, + "criterion": "entropy", + "max_depth": 16, + "min_samples_split": 5, + "min_samples_leaf": 4, + "min_weight_fraction_leaf": 0.0037799050709445034, + "max_features": null, + "bootstrap": true, + "ccp_alpha": 0.006897076648491601, + "max_samples": 0.8 + }, + "metrics": { + "accuracy": 0.7208, + "balanced_accuracy": 0.7199, + "macro_f1": 0.675, + "weighted_f1": 0.7293, + "quadratic_kappa": 0.6495, + "kappa": 0.5893, + "mcc": 0.5942, + "roc_auc_weighted_ovr": 0.8944 + }, + "bytes": 2364519, + "sha256": "1d3ca33c2d3fa2f80dd020a52e2f9aa734426a255039ddbeb26978294b1b056d", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Ridge Classifier", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__ridge_classifier.pkl", + "source_fold": "random_holdout", + "inner_score": 0.6116, + "params": { + "alpha": 3.64511667400448, + "fit_intercept": false, + "max_iter": 1522, + "tol": 6.319915276046356e-05, + "solver": "sag" + }, + "metrics": { + "accuracy": 0.6491, + "balanced_accuracy": 0.4847, + "macro_f1": 0.4923, + "weighted_f1": 0.6138, + "quadratic_kappa": 0.4321, + "kappa": 0.4152, + "mcc": 0.4286 + }, + "bytes": 5460, + "sha256": "3ec918b7a29e97eb50805c91628d368fdeb6c69fe8e8e67e22ef11b4e9ec072b", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "SGD (hinge)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__sgd_hinge.pkl", + "source_fold": "random_holdout", + "inner_score": 0.6321, + "params": { + "penalty": "l2", + "alpha": 2.2515499866245612e-06, + "l1_ratio": 0.7576317076071589, + "fit_intercept": true, + "max_iter": 1710, + "tol": 1.6321601585180913e-05, + "learning_rate": "adaptive", + "eta0": 0.6752718370815053, + "early_stopping": false, + "validation_fraction": 0.08311056948401674, + "n_iter_no_change": 4 + }, + "metrics": { + "accuracy": 0.6736, + "balanced_accuracy": 0.5917, + "macro_f1": 0.5715, + "weighted_f1": 0.6606, + "quadratic_kappa": 0.5927, + "kappa": 0.4869, + "mcc": 0.4917 + }, + "bytes": 5438, + "sha256": "52d0ab3869aab543e325f80253801b31222adda8bf462cad90f81aff6c9a5a62", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "SVM (RBF)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__svm_rbf.pkl", + "source_fold": "random_holdout", + "inner_score": 0.687, + "params": { + "C": 87.00416272425284, + "gamma": "scale", + "tol": 0.0008591574935377383, + "shrinking": false, + "class_weight": null, + "decision_function_shape": "ovr" + }, + "metrics": { + "accuracy": 0.6906, + "balanced_accuracy": 0.6336, + "macro_f1": 0.6199, + "weighted_f1": 0.6908, + "quadratic_kappa": 0.6361, + "kappa": 0.5276, + "mcc": 0.5293, + "roc_auc_weighted_ovr": 0.8629 + }, + "bytes": 68766, + "sha256": "11f12577a98883c69cb233a01f3682a2e3846e28c2076e34002cd1293d92c9b1", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "SVM (polynomial)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__svm_polynomial.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7232, + "params": { + "C": 86.06977879918506, + "gamma": "scale", + "tol": 0.00012235878835636325, + "shrinking": false, + "class_weight": null, + "decision_function_shape": "ovr", + "degree": 5, + "coef0": 0.5911404803031264 + }, + "metrics": { + "accuracy": 0.7302, + "balanced_accuracy": 0.6844, + "macro_f1": 0.67, + "weighted_f1": 0.7324, + "quadratic_kappa": 0.6756, + "kappa": 0.589, + "mcc": 0.5895, + "roc_auc_weighted_ovr": 0.881 + }, + "bytes": 67092, + "sha256": "e1c73dda1047c5a30d2849fff8b56d610e76c04d4f4435bf3bdc294b3c536720", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Soft Voting (RF+XGB+LR)", + "protocol": "random", + "selection": "composed", + "file": "classifiers/random/printability__soft_voting_rf_xgb_lr.pkl", + "source_fold": "random_holdout", + "inner_score": null, + "params": { + "composed_from": [ + "Logistic Regression", + "Random Forest", + "XGBoost" + ] + }, + "metrics": { + "accuracy": 0.7604, + "balanced_accuracy": 0.6936, + "macro_f1": 0.7027, + "weighted_f1": 0.7562, + "quadratic_kappa": 0.7042, + "kappa": 0.6226, + "mcc": 0.6249, + "roc_auc_weighted_ovr": 0.9003 + }, + "bytes": 6042980, + "sha256": "157f10b8830b617c7ceaddde35d625713c2dd4e0dfef8066a2ebfde00560f578", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Stacking (RF+XGB+LR -> LR)", + "protocol": "random", + "selection": "composed", + "file": "classifiers/random/printability__stacking_rf_xgb_lr_lr.pkl", + "source_fold": "random_holdout", + "inner_score": null, + "params": { + "composed_from": [ + "Logistic Regression", + "Random Forest", + "XGBoost" + ] + }, + "metrics": { + "accuracy": 0.7755, + "balanced_accuracy": 0.7187, + "macro_f1": 0.7297, + "weighted_f1": 0.7731, + "quadratic_kappa": 0.7802, + "kappa": 0.6487, + "mcc": 0.6493, + "roc_auc_weighted_ovr": 0.9159 + }, + "bytes": 6043500, + "sha256": "42d86a8fced6c364b61c8a5bff18beeae49c1e11accb2fffc2c52322c6743db6", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "XGBoost", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__xgboost.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7482, + "params": { + "n_estimators": 289, + "max_depth": 9, + "learning_rate": 0.159977753367693, + "gamma": 0.1197890583572232, + "min_child_weight": 5.624222262042716, + "subsample": 0.83878685458189, + "colsample_bytree": 0.6808004828060145, + "reg_alpha": 0.5208355522870847, + "reg_lambda": 0.04085587711752425 + }, + "metrics": { + "accuracy": 0.7623, + "balanced_accuracy": 0.7081, + "macro_f1": 0.7093, + "weighted_f1": 0.7605, + "quadratic_kappa": 0.7784, + "kappa": 0.6306, + "mcc": 0.631, + "roc_auc_weighted_ovr": 0.9142 + }, + "bytes": 651415, + "sha256": "456035d8a5b709323c9025021c4cc405b320ef19c12922d5343d3544f5e31fda", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "k-NN (distance weighted)", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__k_nn_distance_weighted.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7379, + "params": { + "n_neighbors": 9, + "algorithm": "brute", + "leaf_size": 19, + "p": 1, + "metric": "manhattan" + }, + "metrics": { + "accuracy": 0.7491, + "balanced_accuracy": 0.7151, + "macro_f1": 0.7137, + "weighted_f1": 0.7492, + "quadratic_kappa": 0.75, + "kappa": 0.6122, + "mcc": 0.6129, + "roc_auc_weighted_ovr": 0.8495 + }, + "bytes": 53689, + "sha256": "09f59127db7f4e8d30b7ad810bcdd3eda19749fb13b10ac68fe4e14a32991767", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "k-Nearest Neighbours", + "protocol": "random", + "selection": "weighted", + "file": "classifiers/random/printability__k_nearest_neighbours.pkl", + "source_fold": "random_holdout", + "inner_score": 0.7282, + "params": { + "n_neighbors": 1, + "algorithm": "auto", + "leaf_size": 11, + "p": 1, + "metric": "minkowski" + }, + "metrics": { + "accuracy": 0.7358, + "balanced_accuracy": 0.7028, + "macro_f1": 0.7067, + "weighted_f1": 0.7352, + "quadratic_kappa": 0.7489, + "kappa": 0.5903, + "mcc": 0.5905, + "roc_auc_weighted_ovr": 0.797 + }, + "bytes": 53695, + "sha256": "454d01feb6c9b0927614bf2537641b445aac81664bb0df17b33a7472fccceb49", + "reused": true + }, + { + "family": "dl", + "task": "cell_response", + "model": "1D_CNN", + "protocol": "random", + "selection": "weighted", + "file": "deep/random/cell_response__1d_cnn.pt", + "source_fold": "random_holdout", + "inner_score": 0.8076, + "params": { + "n_layers": 6, + "hidden_dim": 192, + "lr": 0.004709568232612032, + "weight_decay": 0.0030186778322337827, + "dropout": 0.24554495469106954, + "batch_size": 32, + "activation": "GELU", + "optimizer": "AdamW", + "max_epochs": 210, + "class_weight": null + }, + "metrics": { + "accuracy": 0.7208, + "balanced_accuracy": 0.409, + "macro_f1": 0.4026, + "weighted_f1": 0.689, + "quadratic_kappa": 0.7004, + "kappa": 0.5113, + "mcc": 0.5172, + "roc_auc_weighted_ovr": 0.9178 + }, + "bytes": 2255387, + "sha256": "3c8f12a5c725035f14226225d60bda49a4340889d2d5d7701e81f0fece22c60f", + "reused": true + }, + { + "family": "dl", + "task": "cell_response", + "model": "FT_Transformer", + "protocol": "random", + "selection": "weighted", + "file": "deep/random/cell_response__ft_transformer.pt", + "source_fold": "random_holdout", + "inner_score": 0.7965, + "params": { + "n_layers": 3, + "hidden_dim": 320, + "lr": 0.00011600050472444694, + "weight_decay": 0.0008107184270673576, + "dropout": 0.17217609657257732, + "batch_size": 64, + "activation": "SiLU", + "optimizer": "Adam", + "max_epochs": 282, + "class_weight": null + }, + "metrics": { + "accuracy": 0.7585, + "balanced_accuracy": 0.4926, + "macro_f1": 0.5026, + "weighted_f1": 0.754, + "quadratic_kappa": 0.8259, + "kappa": 0.5974, + "mcc": 0.6001, + "roc_auc_weighted_ovr": 0.9514 + }, + "bytes": 10286706, + "sha256": "5ae43a34114cd48bd3e3c699cbd5a4f008554a9f0ff4b29c085786a248a617bc", + "reused": true + }, + { + "family": "dl", + "task": "cell_response", + "model": "MLP", + "protocol": "random", + "selection": "weighted", + "file": "deep/random/cell_response__mlp.pt", + "source_fold": "random_holdout", + "inner_score": 0.7853, + "params": { + "n_layers": 3, + "hidden_dim": 512, + "lr": 0.0004466908989057944, + "weight_decay": 0.0006688035071110994, + "dropout": 0.10450128119701933, + "batch_size": 32, + "activation": "GELU", + "optimizer": "AdamW", + "max_epochs": 339, + "class_weight": null + }, + "metrics": { + "accuracy": 0.7226, + "balanced_accuracy": 0.4451, + "macro_f1": 0.4471, + "weighted_f1": 0.7092, + "quadratic_kappa": 0.7326, + "kappa": 0.529, + "mcc": 0.5308, + "roc_auc_weighted_ovr": 0.9334 + }, + "bytes": 2459549, + "sha256": "f89dec0eab3df20f4030b36d6d270d27578b3eeb5959638f00cc0f13094fa8ad", + "reused": true + }, + { + "family": "dl", + "task": "cell_response", + "model": "NODE_Lite", + "protocol": "random", + "selection": "weighted", + "file": "deep/random/cell_response__node_lite.pt", + "source_fold": "random_holdout", + "inner_score": 0.7863, + "params": { + "n_layers": 5, + "hidden_dim": 288, + "lr": 0.007752946303449436, + "weight_decay": 1.0581114308038657e-05, + "dropout": 0.29416310309183125, + "batch_size": 256, + "activation": "GELU", + "optimizer": "AdamW", + "max_epochs": 271, + "class_weight": "balanced" + }, + "metrics": { + "accuracy": 0.7189, + "balanced_accuracy": 0.4225, + "macro_f1": 0.4211, + "weighted_f1": 0.69, + "quadratic_kappa": 0.6882, + "kappa": 0.5052, + "mcc": 0.5104, + "roc_auc_weighted_ovr": 0.9256 + }, + "bytes": 745231, + "sha256": "037bb2ce02a8e9a2cdf5289e95dc70715a31581df37ae8de8723cb03b83220c3", + "reused": true + }, + { + "family": "dl", + "task": "cell_response", + "model": "ResNet", + "protocol": "random", + "selection": "weighted", + "file": "deep/random/cell_response__resnet.pt", + "source_fold": "random_holdout", + "inner_score": 0.7921, + "params": { + "n_layers": 1, + "hidden_dim": 224, + "lr": 0.0071137895547408935, + "weight_decay": 1.1764249709986261e-05, + "dropout": 0.1393661397532897, + "batch_size": 32, + "activation": "tanh", + "optimizer": "AdamW", + "max_epochs": 144, + "class_weight": null + }, + "metrics": { + "accuracy": 0.7623, + "balanced_accuracy": 0.5313, + "macro_f1": 0.5303, + "weighted_f1": 0.7533, + "quadratic_kappa": 0.786, + "kappa": 0.5983, + "mcc": 0.5999, + "roc_auc_weighted_ovr": 0.9495 + }, + "bytes": 357543, + "sha256": "5035fd746ebd5a80842e547a74ef84b9b6b7839b84f90a387130b0f3f68ec0f9", + "reused": true + }, + { + "family": "dl", + "task": "cell_response", + "model": "TabNet_Lite", + "protocol": "random", + "selection": "weighted", + "file": "deep/random/cell_response__tabnet_lite.pt", + "source_fold": "random_holdout", + "inner_score": 0.7967, + "params": { + "n_layers": 6, + "hidden_dim": 416, + "lr": 0.0002263980232546724, + "weight_decay": 0.00602456409460787, + "dropout": 0.3753007065384213, + "batch_size": 32, + "activation": "ELU", + "optimizer": "Adam", + "max_epochs": 256, + "class_weight": null + }, + "metrics": { + "accuracy": 0.7151, + "balanced_accuracy": 0.463, + "macro_f1": 0.4725, + "weighted_f1": 0.7085, + "quadratic_kappa": 0.7028, + "kappa": 0.5203, + "mcc": 0.5217, + "roc_auc_weighted_ovr": 0.905 + }, + "bytes": 3162629, + "sha256": "f64e7187426e3c8235da619d36604c80f02880b86b973bc701111459818d7a5d", + "reused": true + }, + { + "family": "dl", + "task": "printability", + "model": "1D_CNN", + "protocol": "random", + "selection": "weighted", + "file": "deep/random/printability__1d_cnn.pt", + "source_fold": "random_holdout", + "inner_score": 0.7167, + "params": { + "n_layers": 5, + "hidden_dim": 384, + "lr": 0.004098777940402098, + "weight_decay": 0.00022317484183128537, + "dropout": 0.3307896801523583, + "batch_size": 64, + "activation": "GELU", + "optimizer": "AdamW", + "max_epochs": 224, + "class_weight": null + }, + "metrics": { + "accuracy": 0.6566, + "balanced_accuracy": 0.5884, + "macro_f1": 0.5582, + "weighted_f1": 0.6538, + "quadratic_kappa": 0.5338, + "kappa": 0.4743, + "mcc": 0.4792, + "roc_auc_weighted_ovr": 0.8497 + }, + "bytes": 7139363, + "sha256": "9ef3649953646a55eae781c730477fffe126874fc5737ecd3b923ab350f0a652", + "reused": true + }, + { + "family": "dl", + "task": "printability", + "model": "FT_Transformer", + "protocol": "random", + "selection": "weighted", + "file": "deep/random/printability__ft_transformer.pt", + "source_fold": "random_holdout", + "inner_score": 0.7351, + "params": { + "n_layers": 3, + "hidden_dim": 192, + "lr": 0.00010351308939753292, + "weight_decay": 0.002069805688069605, + "dropout": 0.26799093540873087, + "batch_size": 64, + "activation": "SELU", + "optimizer": "AdamW", + "max_epochs": 318, + "class_weight": null + }, + "metrics": { + "accuracy": 0.7264, + "balanced_accuracy": 0.6849, + "macro_f1": 0.6776, + "weighted_f1": 0.728, + "quadratic_kappa": 0.6707, + "kappa": 0.5815, + "mcc": 0.5825, + "roc_auc_weighted_ovr": 0.8687 + }, + "bytes": 3817667, + "sha256": "2efe5b49d2317a1eb319c72c4608da81c25ea0988f30084607ff02e2e5ca9cc8", + "reused": true + }, + { + "family": "dl", + "task": "printability", + "model": "MLP", + "protocol": "random", + "selection": "weighted", + "file": "deep/random/printability__mlp.pt", + "source_fold": "random_holdout", + "inner_score": 0.7386, + "params": { + "n_layers": 3, + "hidden_dim": 480, + "lr": 0.0007485765201520371, + "weight_decay": 0.00011124061899236904, + "dropout": 0.17010524647081268, + "batch_size": 32, + "activation": "tanh", + "optimizer": "AdamW", + "max_epochs": 227, + "class_weight": "balanced" + }, + "metrics": { + "accuracy": 0.6849, + "balanced_accuracy": 0.6652, + "macro_f1": 0.6308, + "weighted_f1": 0.6938, + "quadratic_kappa": 0.6367, + "kappa": 0.5341, + "mcc": 0.5378, + "roc_auc_weighted_ovr": 0.8671 + }, + "bytes": 2181568, + "sha256": "24e5457124f01955414b7b080793e93f9b6efe1b9ec8adddcc8d2bfd80d5b692", + "reused": true + }, + { + "family": "dl", + "task": "printability", + "model": "NODE_Lite", + "protocol": "random", + "selection": "weighted", + "file": "deep/random/printability__node_lite.pt", + "source_fold": "random_holdout", + "inner_score": 0.7194, + "params": { + "n_layers": 5, + "hidden_dim": 224, + "lr": 0.0074723976893329375, + "weight_decay": 2.5856088907313374e-05, + "dropout": 0.20231990531507757, + "batch_size": 64, + "activation": "tanh", + "optimizer": "AdamW", + "max_epochs": 205, + "class_weight": "balanced" + }, + "metrics": { + "accuracy": 0.6849, + "balanced_accuracy": 0.6638, + "macro_f1": 0.6221, + "weighted_f1": 0.6967, + "quadratic_kappa": 0.64, + "kappa": 0.5376, + "mcc": 0.5426, + "roc_auc_weighted_ovr": 0.8632 + }, + "bytes": 576316, + "sha256": "c6cfab0ad5fb11fb0974e8b6c65e36fbfa099c13d0e665e5610fa0f3a4aa4bce", + "reused": true + }, + { + "family": "dl", + "task": "printability", + "model": "ResNet", + "protocol": "random", + "selection": "weighted", + "file": "deep/random/printability__resnet.pt", + "source_fold": "random_holdout", + "inner_score": 0.7632, + "params": { + "n_layers": 6, + "hidden_dim": 160, + "lr": 0.0022093834415066287, + "weight_decay": 0.0019268985325226215, + "dropout": 0.17129126319771992, + "batch_size": 32, + "activation": "GELU", + "optimizer": "AdamW", + "max_epochs": 168, + "class_weight": null + }, + "metrics": { + "accuracy": 0.7396, + "balanced_accuracy": 0.6957, + "macro_f1": 0.6903, + "weighted_f1": 0.7406, + "quadratic_kappa": 0.6685, + "kappa": 0.6022, + "mcc": 0.6036, + "roc_auc_weighted_ovr": 0.8765 + }, + "bytes": 753903, + "sha256": "3d4f4f7faa7b5a231e834c8a691601c8e80bb5694adbba815f27be1653ba5b05", + "reused": true + }, + { + "family": "dl", + "task": "printability", + "model": "TabNet_Lite", + "protocol": "random", + "selection": "weighted", + "file": "deep/random/printability__tabnet_lite.pt", + "source_fold": "random_holdout", + "inner_score": 0.7658, + "params": { + "n_layers": 4, + "hidden_dim": 288, + "lr": 0.003059113634053077, + "weight_decay": 0.00152153896959905, + "dropout": 0.22295374856479444, + "batch_size": 64, + "activation": "GELU", + "optimizer": "Adam", + "max_epochs": 286, + "class_weight": null + }, + "metrics": { + "accuracy": 0.7208, + "balanced_accuracy": 0.6659, + "macro_f1": 0.6555, + "weighted_f1": 0.7207, + "quadratic_kappa": 0.6541, + "kappa": 0.5704, + "mcc": 0.5728, + "roc_auc_weighted_ovr": 0.8648 + }, + "bytes": 1472384, + "sha256": "65e43d38242eea53dd7709d714d052368c13984a1dfb1bb1c1b7e6c2a55f7c42", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "AdaBoost", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__adaboost.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7174, + "params": { + "n_estimators": 114, + "learning_rate": 1.1118095995028556 + }, + "metrics": { + "accuracy": 0.7439, + "balanced_accuracy": 0.3812, + "macro_f1": 0.3713, + "weighted_f1": 0.7065, + "quadratic_kappa": 0.6718, + "kappa": 0.5168, + "mcc": 0.5255, + "roc_auc_weighted_ovr": 0.9209 + }, + "bytes": 22910, + "sha256": "6718b55ac9002c567ead988ac4122e5efd5a93b159c6cfa6a05e9deb86f0c2d4", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Bagged Trees", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__bagged_trees.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7321, + "params": { + "n_estimators": 164, + "max_samples": 0.8465207974838976, + "max_features": 0.5236732743909801, + "bootstrap": true, + "estimator__max_depth": 6, + "estimator__min_samples_leaf": 5 + }, + "metrics": { + "accuracy": 0.7927, + "balanced_accuracy": 0.4018, + "macro_f1": 0.3678, + "weighted_f1": 0.7505, + "quadratic_kappa": 0.8452, + "kappa": 0.6244, + "mcc": 0.6443, + "roc_auc_weighted_ovr": 0.9296 + }, + "bytes": 382728, + "sha256": "ea64fd33edab665f7b1d506a26dabf4a14dc1489cb0f9306673f4913f488a5d9", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Bernoulli Naive Bayes", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__bernoulli_naive_bayes.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7463, + "params": { + "alpha": 1.1463059609830264, + "binarize": 0.4415823418588022, + "fit_prior": true + }, + "metrics": { + "accuracy": 0.6481, + "balanced_accuracy": 0.3105, + "macro_f1": 0.2974, + "weighted_f1": 0.6178, + "quadratic_kappa": 0.5896, + "kappa": 0.3433, + "mcc": 0.3522, + "roc_auc_weighted_ovr": 0.8892 + }, + "bytes": 3258, + "sha256": "ecec1c0860c02a066cc8ac05df680dc1b1f3212fee7f03becf85cef41a4f92c5", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "CatBoost", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__catboost.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7279, + "params": { + "iterations": 421, + "learning_rate": 0.032989969655395635, + "depth": 3, + "l2_leaf_reg": 1.345164254063931, + "bagging_temperature": 0.5622089857656744, + "random_strength": 0.4793067180743533, + "colsample_bylevel": 0.7499628787296093, + "bootstrap_type": "Bayesian" + }, + "metrics": { + "accuracy": 0.7909, + "balanced_accuracy": 0.4062, + "macro_f1": 0.3784, + "weighted_f1": 0.7544, + "quadratic_kappa": 0.8406, + "kappa": 0.6223, + "mcc": 0.6383, + "roc_auc_weighted_ovr": 0.934 + }, + "bytes": 121222, + "sha256": "267c4d295077c0d39cb88e1fe210e89532dba5d70ab8542d0d7245f52d97ecb2", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Decision Tree", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__decision_tree.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7242, + "params": { + "criterion": "log_loss", + "splitter": "random", + "max_depth": 6, + "min_samples_split": 19, + "min_samples_leaf": 2, + "max_features": null, + "ccp_alpha": 0.007283697002116443 + }, + "metrics": { + "accuracy": 0.7753, + "balanced_accuracy": 0.4062, + "macro_f1": 0.3805, + "weighted_f1": 0.7474, + "quadratic_kappa": 0.8116, + "kappa": 0.5929, + "mcc": 0.598, + "roc_auc_weighted_ovr": 0.8989 + }, + "bytes": 2175, + "sha256": "cef3e394022818f3dddf0c669042ce31ddf3ada27a33dd70ec0855420e810e91", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Extra Tree", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__extra_tree.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.717, + "params": { + "criterion": "log_loss", + "max_depth": 29, + "min_samples_split": 13, + "min_samples_leaf": 4, + "max_features": null, + "ccp_alpha": 0.008232729123756432 + }, + "metrics": { + "accuracy": 0.7718, + "balanced_accuracy": 0.4051, + "macro_f1": 0.3765, + "weighted_f1": 0.7506, + "quadratic_kappa": 0.8342, + "kappa": 0.5939, + "mcc": 0.599, + "roc_auc_weighted_ovr": 0.9147 + }, + "bytes": 2310, + "sha256": "7135c7910a0065842048b019adae927bb3babcc49fbb4056f672e225fae8014e", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Extra Trees", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__extra_trees.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7295, + "params": { + "n_estimators": 167, + "criterion": "entropy", + "max_depth": 55, + "min_samples_split": 18, + "min_samples_leaf": 4, + "max_features": null, + "bootstrap": true, + "ccp_alpha": 0.0031123420497667087 + }, + "metrics": { + "accuracy": 0.7108, + "balanced_accuracy": 0.3146, + "macro_f1": 0.3019, + "weighted_f1": 0.6561, + "quadratic_kappa": 0.5893, + "kappa": 0.4227, + "mcc": 0.4383, + "roc_auc_weighted_ovr": 0.9174 + }, + "bytes": 684133, + "sha256": "a70d107aa98287c1ad1e6db73964474bd4fff09169c048d0febff6afa89103b9", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Gaussian Naive Bayes", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__gaussian_naive_bayes.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.1978, + "params": { + "var_smoothing": 1.767016940294792e-09 + }, + "metrics": { + "accuracy": 0.2038, + "balanced_accuracy": 0.2239, + "macro_f1": 0.1158, + "weighted_f1": 0.2497, + "quadratic_kappa": -0.1297, + "kappa": 0.0033, + "mcc": 0.0042, + "roc_auc_weighted_ovr": 0.6395 + }, + "bytes": 7344, + "sha256": "23630e99b3a4f7d0a488561de7da1b50fdc883fd2bbdc3ec5fbef5b053518a38", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Gradient Boosting", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__gradient_boosting.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.713, + "params": { + "learning_rate": 0.05488306594586391, + "n_estimators": 154, + "subsample": 0.5315656901881007, + "criterion": "squared_error", + "min_samples_split": 13, + "min_samples_leaf": 4, + "max_depth": 3, + "max_features": null, + "ccp_alpha": 1.3700690549896082e-05 + }, + "metrics": { + "accuracy": 0.77, + "balanced_accuracy": 0.3844, + "macro_f1": 0.3615, + "weighted_f1": 0.7428, + "quadratic_kappa": 0.8239, + "kappa": 0.5868, + "mcc": 0.5953, + "roc_auc_weighted_ovr": 0.934 + }, + "bytes": 207376, + "sha256": "50f8eb4225619001edf0f2f0aa30a8a2db05420aacfe947cd17e3e5a12ed4c0b", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Hist Gradient Boosting", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__hist_gradient_boosting.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7231, + "params": { + "learning_rate": 0.011865151832183595, + "max_iter": 163, + "max_leaf_nodes": 27, + "max_depth": 25, + "min_samples_leaf": 24, + "l2_regularization": 0.9643179894952475, + "max_bins": 196, + "early_stopping": true, + "n_iter_no_change": 15 + }, + "metrics": { + "accuracy": 0.7666, + "balanced_accuracy": 0.3948, + "macro_f1": 0.3887, + "weighted_f1": 0.7508, + "quadratic_kappa": 0.8318, + "kappa": 0.5832, + "mcc": 0.5861, + "roc_auc_weighted_ovr": 0.9212 + }, + "bytes": 737332, + "sha256": "a4c033e5ed3503f307e0e6ecf6fc937bdd1475eae282e141fa83cbccc2d622a8", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "LightGBM", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__lightgbm.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7318, + "params": { + "boosting_type": "gbdt", + "num_leaves": 227, + "max_depth": 41, + "learning_rate": 0.010732966845902341, + "n_estimators": 452, + "min_child_weight": 5.393883076914592, + "min_child_samples": 42, + "subsample": 0.9480456499617467, + "subsample_freq": 3, + "colsample_bytree": 0.5550259622638384, + "reg_alpha": 2.279351625419417, + "reg_lambda": 4.271077886262563 + }, + "metrics": { + "accuracy": 0.7805, + "balanced_accuracy": 0.4006, + "macro_f1": 0.3799, + "weighted_f1": 0.7534, + "quadratic_kappa": 0.844, + "kappa": 0.6066, + "mcc": 0.6158, + "roc_auc_weighted_ovr": 0.925 + }, + "bytes": 1108048, + "sha256": "9d0edf6f384346206f78d7d4cdfd34b758bfd2beed18e50321b29a2a815aaf10", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Linear Discriminant", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__linear_discriminant.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7187, + "params": { + "shrinkage": 0.1, + "n_components": 10, + "tol": 0.00788671412999049 + }, + "metrics": { + "accuracy": 0.6132, + "balanced_accuracy": 0.2755, + "macro_f1": 0.2659, + "weighted_f1": 0.5827, + "quadratic_kappa": 0.4364, + "kappa": 0.2659, + "mcc": 0.2707, + "roc_auc_weighted_ovr": 0.8455 + }, + "bytes": 145278, + "sha256": "195c7dcdf5dbe59728f7befc0250bbde6d5ebec2ccf5c824a16a49c336fc4a40", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Linear SVM", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__linear_svm.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.722, + "params": { + "loss": "squared_hinge", + "tol": 0.00029696311170881914, + "C": 0.053552055285881764, + "fit_intercept": false, + "intercept_scaling": 0.20937657556695136, + "max_iter": 4806, + "class_weight": "balanced" + }, + "metrics": { + "accuracy": 0.6167, + "balanced_accuracy": 0.2866, + "macro_f1": 0.2867, + "weighted_f1": 0.5938, + "quadratic_kappa": 0.4949, + "kappa": 0.284, + "mcc": 0.2877 + }, + "bytes": 6434, + "sha256": "192ebe26692066d4e3367057136c4c7a9cbeb5fb21e7037d3293526d81f00683", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Logistic Regression", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__logistic_regression.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7232, + "params": { + "penalty": "l2", + "tol": 0.005564258120476742, + "C": 88.6077480618815, + "fit_intercept": false, + "solver": "newton-cg", + "max_iter": 1110 + }, + "metrics": { + "accuracy": 0.6132, + "balanced_accuracy": 0.2747, + "macro_f1": 0.2679, + "weighted_f1": 0.5739, + "quadratic_kappa": 0.3651, + "kappa": 0.2445, + "mcc": 0.2526, + "roc_auc_weighted_ovr": 0.8549 + }, + "bytes": 6499, + "sha256": "7c0ebbb4d081568119ccae0f79501f201124175b55e377d8e72c3889b34d95ec", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Logistic Regression (balanced)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__logistic_regression_balanced.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7212, + "params": { + "penalty": null, + "tol": 0.0035869350871417225, + "C": 1.5566871395196396, + "fit_intercept": false, + "solver": "lbfgs", + "max_iter": 1426 + }, + "metrics": { + "accuracy": 0.6045, + "balanced_accuracy": 0.3021, + "macro_f1": 0.3021, + "weighted_f1": 0.613, + "quadratic_kappa": 0.5986, + "kappa": 0.3189, + "mcc": 0.321, + "roc_auc_weighted_ovr": 0.8334 + }, + "bytes": 6535, + "sha256": "63baa05d194228bad73304348e43ea4ef41af56a6f4765fcd4302ba26c8beec2", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "MLP (256-128)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__mlp_256_128.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.733, + "params": { + "hidden_layer_sizes": "64", + "activation": "logistic", + "solver": "sgd", + "alpha": 0.09315867831843434, + "learning_rate": "constant", + "learning_rate_init": 0.05439034985544032, + "max_iter": 278, + "tol": 4.974931918853955e-06, + "early_stopping": false + }, + "metrics": { + "accuracy": 0.6307, + "balanced_accuracy": 0.2892, + "macro_f1": 0.2853, + "weighted_f1": 0.5897, + "quadratic_kappa": 0.3338, + "kappa": 0.2723, + "mcc": 0.2801, + "roc_auc_weighted_ovr": 0.8725 + }, + "bytes": 240967, + "sha256": "bc9b8b42ee6ad2937743c882e226ebbd9bf3d047764ce57908fae3ecf8cb8644", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Nearest Centroid", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__nearest_centroid.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.6761, + "params": { + "metric": "euclidean", + "shrink_threshold": 0.3463462348151025 + }, + "metrics": { + "accuracy": 0.6568, + "balanced_accuracy": 0.3415, + "macro_f1": 0.3018, + "weighted_f1": 0.5976, + "quadratic_kappa": 0.5054, + "kappa": 0.3489, + "mcc": 0.3724, + "roc_auc_weighted_ovr": 0.8479 + }, + "bytes": 10569, + "sha256": "e776e38fdb8d7aee6eb5d947f2dedaa2f20553d4f84caa934884b9b8a09d0075", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Passive Aggressive", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__passive_aggressive.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7285, + "params": { + "C": 0.011167353585346007, + "fit_intercept": true, + "max_iter": 1015, + "tol": 4.562214920100225e-05, + "early_stopping": false, + "validation_fraction": 0.22818957756882569, + "n_iter_no_change": 7, + "shuffle": true, + "loss": "hinge", + "class_weight": "balanced", + "average": true + }, + "metrics": { + "accuracy": 0.615, + "balanced_accuracy": 0.2802, + "macro_f1": 0.2839, + "weighted_f1": 0.5769, + "quadratic_kappa": 0.283, + "kappa": 0.2422, + "mcc": 0.2491 + }, + "bytes": 12311, + "sha256": "6a81d84328db5be9d5915b22af9428c54e21f8c223b43b4f4615b4d20c3e8ccf", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Perceptron", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__perceptron.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.6938, + "params": { + "penalty": null, + "alpha": 1.3788198614349076e-07, + "l1_ratio": 0.8604135745095509, + "fit_intercept": false, + "max_iter": 1524, + "tol": 0.00043629529299795517, + "shuffle": true, + "eta0": 1.2120210591905518, + "early_stopping": false, + "validation_fraction": 0.27658910543474596, + "n_iter_no_change": 1, + "class_weight": null + }, + "metrics": { + "accuracy": 0.6847, + "balanced_accuracy": 0.2885, + "macro_f1": 0.2701, + "weighted_f1": 0.6397, + "quadratic_kappa": 0.5541, + "kappa": 0.3934, + "mcc": 0.4045 + }, + "bytes": 3872, + "sha256": "7f7db434cabe8b48152863d515bd922bf801460e466240e48a20c45939297efe", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Quadratic Discriminant", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__quadratic_discriminant.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7279, + "params": { + "pca__n_components": 10, + "reg_param": 0.025769677431349825, + "store_covariance": true, + "tol": 0.0009768137391168961 + }, + "metrics": { + "accuracy": 0.6603, + "balanced_accuracy": 0.3805, + "macro_f1": 0.3717, + "weighted_f1": 0.6877, + "quadratic_kappa": 0.7922, + "kappa": 0.4414, + "mcc": 0.4458, + "roc_auc_weighted_ovr": 0.8906 + }, + "bytes": 21301, + "sha256": "37d356139cc35d8d4ed413b81d7ca13bef0a1e7111da9a2878e3899ff80422fb", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Random Forest", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__random_forest.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7128, + "params": { + "n_estimators": 400, + "criterion": "entropy", + "max_depth": 18, + "min_samples_split": 3, + "min_samples_leaf": 1, + "min_weight_fraction_leaf": 0.08163400564338802, + "max_features": null, + "bootstrap": true, + "ccp_alpha": 0.027521175215396168, + "max_samples": 0.9 + }, + "metrics": { + "accuracy": 0.8014, + "balanced_accuracy": 0.4303, + "macro_f1": 0.3995, + "weighted_f1": 0.7691, + "quadratic_kappa": 0.851, + "kappa": 0.6431, + "mcc": 0.6537, + "roc_auc_weighted_ovr": 0.9381 + }, + "bytes": 81920, + "sha256": "e9bd8366e34973589a25f94db606e93fc76661aa79c9fb1bef92c7f9a4f209cd", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Random Forest (balanced)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__random_forest_balanced.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7333, + "params": { + "n_estimators": 350, + "criterion": "entropy", + "max_depth": 35, + "min_samples_split": 7, + "min_samples_leaf": 1, + "min_weight_fraction_leaf": 0.001254715712481154, + "max_features": "sqrt", + "bootstrap": true, + "ccp_alpha": 0.003503213854927241, + "max_samples": 0.8 + }, + "metrics": { + "accuracy": 0.7857, + "balanced_accuracy": 0.4302, + "macro_f1": 0.4245, + "weighted_f1": 0.7668, + "quadratic_kappa": 0.8381, + "kappa": 0.6175, + "mcc": 0.6234, + "roc_auc_weighted_ovr": 0.9229 + }, + "bytes": 3535623, + "sha256": "bb9c43bba7845f687ba285f2ff1e4725813151b71180441daf9be6eab41ea310", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Ridge Classifier", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__ridge_classifier.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.6868, + "params": { + "alpha": 0.16830448420647048, + "fit_intercept": false, + "max_iter": 436, + "tol": 0.00439266117717107, + "solver": "sparse_cg" + }, + "metrics": { + "accuracy": 0.6098, + "balanced_accuracy": 0.2647, + "macro_f1": 0.2549, + "weighted_f1": 0.5645, + "quadratic_kappa": 0.3405, + "kappa": 0.2209, + "mcc": 0.2307 + }, + "bytes": 6533, + "sha256": "060a133f4aaee743437d6e4aa5f025b2ae8873a9a68c723f4c40b864cce6b250", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "SGD (hinge)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__sgd_hinge.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.713, + "params": { + "penalty": "l1", + "alpha": 0.0007653648178811599, + "l1_ratio": 0.5177276835817703, + "fit_intercept": false, + "max_iter": 1426, + "tol": 0.00242346504306506, + "learning_rate": "adaptive", + "eta0": 0.13306525358361757, + "early_stopping": true, + "validation_fraction": 0.10345733844260593, + "n_iter_no_change": 9 + }, + "metrics": { + "accuracy": 0.7021, + "balanced_accuracy": 0.3234, + "macro_f1": 0.3317, + "weighted_f1": 0.6494, + "quadratic_kappa": 0.5366, + "kappa": 0.3892, + "mcc": 0.4119 + }, + "bytes": 2368, + "sha256": "c0bc2affa43a6360cb1828ffee4829c1f431db6fe4e1cc4965c4c36d9765e09a", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "SVM (RBF)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__svm_rbf.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.742, + "params": { + "C": 2.69264691008618, + "gamma": "scale", + "tol": 0.007902619549708232, + "shrinking": true, + "class_weight": null, + "decision_function_shape": "ovo" + }, + "metrics": { + "accuracy": 0.6446, + "balanced_accuracy": 0.3607, + "macro_f1": 0.3299, + "weighted_f1": 0.6381, + "quadratic_kappa": 0.5079, + "kappa": 0.4015, + "mcc": 0.4182, + "roc_auc_weighted_ovr": 0.826 + }, + "bytes": 67710, + "sha256": "7a56cb352999a9427d8329cbda9fb816680600ffce9ce8741b9109032dc01d00", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "SVM (polynomial)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__svm_polynomial.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7336, + "params": { + "C": 1.285048646530307, + "gamma": "scale", + "tol": 0.0016675962972338468, + "shrinking": true, + "class_weight": null, + "decision_function_shape": "ovr", + "degree": 2, + "coef0": 0.5874142617948831 + }, + "metrics": { + "accuracy": 0.7265, + "balanced_accuracy": 0.3436, + "macro_f1": 0.333, + "weighted_f1": 0.6788, + "quadratic_kappa": 0.6426, + "kappa": 0.462, + "mcc": 0.4745, + "roc_auc_weighted_ovr": 0.9331 + }, + "bytes": 60069, + "sha256": "c50b47e260cd1c664dda374ec80d9ff668cc62133c0b368ddb236cc9aba946ff", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Soft Voting (RF+XGB+LR)", + "protocol": "doi", + "selection": "composed", + "file": "classifiers/doi/cell_response__soft_voting_rf_xgb_lr.pkl", + "source_fold": "doi_holdout", + "inner_score": null, + "params": { + "composed_from": [ + "Logistic Regression", + "Random Forest", + "XGBoost" + ] + }, + "metrics": { + "accuracy": 0.777, + "balanced_accuracy": 0.3831, + "macro_f1": 0.3582, + "weighted_f1": 0.7296, + "quadratic_kappa": 0.7862, + "kappa": 0.5792, + "mcc": 0.5915, + "roc_auc_weighted_ovr": 0.925 + }, + "bytes": 5233166, + "sha256": "c8e3ae78518aa32eb858160556780da44b03dc67908a10451c982fd65cce4b14", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "Stacking (RF+XGB+LR -> LR)", + "protocol": "doi", + "selection": "composed", + "file": "classifiers/doi/cell_response__stacking_rf_xgb_lr_lr.pkl", + "source_fold": "doi_holdout", + "inner_score": null, + "params": { + "composed_from": [ + "Logistic Regression", + "Random Forest", + "XGBoost" + ] + }, + "metrics": { + "accuracy": 0.7944, + "balanced_accuracy": 0.3983, + "macro_f1": 0.3646, + "weighted_f1": 0.7476, + "quadratic_kappa": 0.8348, + "kappa": 0.6203, + "mcc": 0.6359, + "roc_auc_weighted_ovr": 0.9259 + }, + "bytes": 5233836, + "sha256": "22b4220df14239c7e42aebc511ec4e182540de964f3443c3360d977861536cfa", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "XGBoost", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__xgboost.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.7295, + "params": { + "n_estimators": 210, + "max_depth": 6, + "learning_rate": 0.2516091128123238, + "gamma": 1.3875949300856911, + "min_child_weight": 3.0361789604162936, + "subsample": 0.5429778885458338, + "colsample_bytree": 0.615265478981264, + "reg_alpha": 3.3505142232585623, + "reg_lambda": 1.8610739664538896 + }, + "metrics": { + "accuracy": 0.7875, + "balanced_accuracy": 0.4102, + "macro_f1": 0.3907, + "weighted_f1": 0.7563, + "quadratic_kappa": 0.838, + "kappa": 0.6176, + "mcc": 0.6301, + "roc_auc_weighted_ovr": 0.933 + }, + "bytes": 53698, + "sha256": "cadcb8c1442dedfa300f009c6b4c7e528cc5082991adf7b0548ca2408aab3c1d", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "k-NN (distance weighted)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__k_nn_distance_weighted.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.6928, + "params": { + "n_neighbors": 11, + "algorithm": "auto", + "leaf_size": 77, + "p": 3, + "metric": "euclidean" + }, + "metrics": { + "accuracy": 0.6463, + "balanced_accuracy": 0.2673, + "macro_f1": 0.2604, + "weighted_f1": 0.5602, + "quadratic_kappa": 0.2347, + "kappa": 0.2176, + "mcc": 0.2588, + "roc_auc_weighted_ovr": 0.7132 + }, + "bytes": 53475, + "sha256": "dcb4c2c85b2380ff5f50900cd4e56b787992f9218edec66cec29ef936e35244c", + "reused": true + }, + { + "family": "ml", + "task": "cell_response", + "model": "k-Nearest Neighbours", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/cell_response__k_nearest_neighbours.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.6785, + "params": { + "n_neighbors": 7, + "algorithm": "kd_tree", + "leaf_size": 98, + "p": 3, + "metric": "manhattan" + }, + "metrics": { + "accuracy": 0.6463, + "balanced_accuracy": 0.2614, + "macro_f1": 0.2524, + "weighted_f1": 0.5594, + "quadratic_kappa": 0.259, + "kappa": 0.2169, + "mcc": 0.258, + "roc_auc_weighted_ovr": 0.7535 + }, + "bytes": 114934, + "sha256": "d48b96126de112c2f87c3fc6a7ba15a088ae26649be6ea8287398fc807073248", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "AdaBoost", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__adaboost.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.5069, + "params": { + "n_estimators": 265, + "learning_rate": 0.09953701633772714 + }, + "metrics": { + "accuracy": 0.5662, + "balanced_accuracy": 0.3893, + "macro_f1": 0.3161, + "weighted_f1": 0.529, + "quadratic_kappa": 0.4157, + "kappa": 0.3297, + "mcc": 0.3875, + "roc_auc_weighted_ovr": 0.7382 + }, + "bytes": 46120, + "sha256": "7a77924a952a29949f0ec6e9e7fe7de18d46b84a79a6c698538eafaf5da9477c", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Bagged Trees", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__bagged_trees.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4768, + "params": { + "n_estimators": 29, + "max_samples": 0.9979389768571496, + "max_features": 0.6861269508008516, + "bootstrap": true, + "estimator__max_depth": 3, + "estimator__min_samples_leaf": 7 + }, + "metrics": { + "accuracy": 0.5575, + "balanced_accuracy": 0.3853, + "macro_f1": 0.312, + "weighted_f1": 0.5217, + "quadratic_kappa": 0.4067, + "kappa": 0.3191, + "mcc": 0.3779, + "roc_auc_weighted_ovr": 0.7481 + }, + "bytes": 23203, + "sha256": "40b8c78b16846ab71b44eae5a56d3ba2998433807fce82e6edabd03238ee85f6", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Bernoulli Naive Bayes", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__bernoulli_naive_bayes.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.5034, + "params": { + "alpha": 7.5873471181147485, + "binarize": 0.04550110514915019, + "fit_prior": true + }, + "metrics": { + "accuracy": 0.5523, + "balanced_accuracy": 0.3473, + "macro_f1": 0.315, + "weighted_f1": 0.5192, + "quadratic_kappa": 0.3927, + "kappa": 0.2662, + "mcc": 0.2749, + "roc_auc_weighted_ovr": 0.7001 + }, + "bytes": 3499, + "sha256": "a3bf4202f8e021bfd4ea6a434500d03be3a691bb764f46a75614fae41bde7b6e", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "CatBoost", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__catboost.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4894, + "params": { + "iterations": 182, + "learning_rate": 0.16137998268604617, + "depth": 4, + "l2_leaf_reg": 3.1118298962854167, + "bagging_temperature": 0.0015529392540532538, + "random_strength": 3.264163026092506, + "colsample_bylevel": 0.994186946913854, + "bootstrap_type": "Bayesian" + }, + "metrics": { + "accuracy": 0.5401, + "balanced_accuracy": 0.3214, + "macro_f1": 0.2979, + "weighted_f1": 0.4923, + "quadratic_kappa": 0.277, + "kappa": 0.2047, + "mcc": 0.2129, + "roc_auc_weighted_ovr": 0.7264 + }, + "bytes": 63112, + "sha256": "0043b33c0a56b401eb218eb194dca4d41b2514282a1f5583b493bdebf4d3120a", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Decision Tree", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__decision_tree.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.5057, + "params": { + "criterion": "gini", + "splitter": "best", + "max_depth": 32, + "min_samples_split": 7, + "min_samples_leaf": 11, + "max_features": null, + "ccp_alpha": 0.037777556927152435 + }, + "metrics": { + "accuracy": 0.5575, + "balanced_accuracy": 0.3853, + "macro_f1": 0.312, + "weighted_f1": 0.5217, + "quadratic_kappa": 0.4067, + "kappa": 0.3191, + "mcc": 0.3779, + "roc_auc_weighted_ovr": 0.7439 + }, + "bytes": 1078, + "sha256": "3e4f1f7d68acc064f9bd93c75ef4b1f919e0d16babdc047be2601e50849ac002", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Extra Tree", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__extra_tree.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4677, + "params": { + "criterion": "log_loss", + "max_depth": 9, + "min_samples_split": 19, + "min_samples_leaf": 11, + "max_features": null, + "ccp_alpha": 0.031782406757632 + }, + "metrics": { + "accuracy": 0.601, + "balanced_accuracy": 0.3872, + "macro_f1": 0.326, + "weighted_f1": 0.5291, + "quadratic_kappa": 0.1874, + "kappa": 0.3158, + "mcc": 0.3359, + "roc_auc_weighted_ovr": 0.7617 + }, + "bytes": 1310, + "sha256": "fe1dbc2a58a675551ef5f91b9abe4890b78bef4cc9626733fff7ad99f9a8bb80", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Extra Trees", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__extra_trees.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.5076, + "params": { + "n_estimators": 331, + "criterion": "gini", + "max_depth": 47, + "min_samples_split": 3, + "min_samples_leaf": 1, + "max_features": null, + "bootstrap": true, + "ccp_alpha": 0.01305999448156043 + }, + "metrics": { + "accuracy": 0.5523, + "balanced_accuracy": 0.3839, + "macro_f1": 0.3098, + "weighted_f1": 0.5172, + "quadratic_kappa": 0.4003, + "kappa": 0.3138, + "mcc": 0.3748, + "roc_auc_weighted_ovr": 0.7496 + }, + "bytes": 103496, + "sha256": "efd2d08153ac73d591c9e078bc441748e7b0aea88b9dc4b7c155c45c45e10bc6", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Gaussian Naive Bayes", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__gaussian_naive_bayes.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.2078, + "params": { + "var_smoothing": 7.48812265223046e-06 + }, + "metrics": { + "accuracy": 0.223, + "balanced_accuracy": 0.2779, + "macro_f1": 0.2233, + "weighted_f1": 0.241, + "quadratic_kappa": 0.0552, + "kappa": 0.0203, + "mcc": 0.0246, + "roc_auc_weighted_ovr": 0.5327 + }, + "bytes": 6137, + "sha256": "4183d69c4b81e2ff38e386a2f0fa1cee1462946b367e129b686fea04d9b2bc67", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Gradient Boosting", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__gradient_boosting.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.5057, + "params": { + "learning_rate": 0.0927163207094897, + "n_estimators": 65, + "subsample": 0.9202948128395309, + "criterion": "friedman_mse", + "min_samples_split": 7, + "min_samples_leaf": 11, + "max_depth": 12, + "max_features": null, + "ccp_alpha": 0.007226700975547 + }, + "metrics": { + "accuracy": 0.5575, + "balanced_accuracy": 0.3853, + "macro_f1": 0.312, + "weighted_f1": 0.5217, + "quadratic_kappa": 0.4067, + "kappa": 0.3191, + "mcc": 0.3779, + "roc_auc_weighted_ovr": 0.7369 + }, + "bytes": 15079, + "sha256": "35c4ec17c771ca1725a3716a166e74da2fd86ca5cf856b49b84ebcf3f9451f11", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Hist Gradient Boosting", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__hist_gradient_boosting.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4758, + "params": { + "learning_rate": 0.01872150773344914, + "max_iter": 403, + "max_leaf_nodes": 14, + "max_depth": 21, + "min_samples_leaf": 25, + "l2_regularization": 0.6991809333892368, + "max_bins": 171, + "early_stopping": false, + "n_iter_no_change": 18 + }, + "metrics": { + "accuracy": 0.5087, + "balanced_accuracy": 0.31, + "macro_f1": 0.3108, + "weighted_f1": 0.4669, + "quadratic_kappa": 0.329, + "kappa": 0.134, + "mcc": 0.1398, + "roc_auc_weighted_ovr": 0.7086 + }, + "bytes": 926648, + "sha256": "aba925654b31f64c58972e00c44be5f6d1fbe62cd3d8c53c5aad7b088b5a769c", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "LightGBM", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__lightgbm.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4882, + "params": { + "boosting_type": "dart", + "num_leaves": 216, + "max_depth": 27, + "learning_rate": 0.15494686217496312, + "n_estimators": 389, + "min_child_weight": 9.246032704766431, + "min_child_samples": 48, + "subsample": 0.7573672206807439, + "subsample_freq": 5, + "colsample_bytree": 0.6498920559104804, + "reg_alpha": 3.5167229267399045, + "reg_lambda": 5.295603666889615 + }, + "metrics": { + "accuracy": 0.4948, + "balanced_accuracy": 0.2914, + "macro_f1": 0.2754, + "weighted_f1": 0.4416, + "quadratic_kappa": 0.2883, + "kappa": 0.1007, + "mcc": 0.1062, + "roc_auc_weighted_ovr": 0.7223 + }, + "bytes": 876702, + "sha256": "bf72cdc2ca5b18281a734a0e21739359d0cb6d763f77432c1b8c347768b116fe", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Linear Discriminant", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__linear_discriminant.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4739, + "params": { + "shrinkage": 0.5, + "n_components": 3, + "tol": 0.000684792009557478 + }, + "metrics": { + "accuracy": 0.4495, + "balanced_accuracy": 0.3263, + "macro_f1": 0.3244, + "weighted_f1": 0.4617, + "quadratic_kappa": 0.4314, + "kappa": 0.1632, + "mcc": 0.1665, + "roc_auc_weighted_ovr": 0.6346 + }, + "bytes": 142358, + "sha256": "496e4da96d3f9abf6c7cd4d88a9d7d33437fecf47e91dcac911bdebecf93f8e3", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Linear SVM", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__linear_svm.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4846, + "params": { + "loss": "squared_hinge", + "tol": 5.342892537395847e-05, + "C": 0.042024885864143345, + "fit_intercept": true, + "intercept_scaling": 2.2738355236928802, + "max_iter": 1405, + "class_weight": "balanced" + }, + "metrics": { + "accuracy": 0.4808, + "balanced_accuracy": 0.3831, + "macro_f1": 0.3716, + "weighted_f1": 0.4876, + "quadratic_kappa": 0.3952, + "kappa": 0.2033, + "mcc": 0.2062 + }, + "bytes": 5349, + "sha256": "b1d6ac4b823fca920139657f1a9ac60e51de98499ce07d8894b5531c6c6b4f7c", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Logistic Regression", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__logistic_regression.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4576, + "params": { + "penalty": "l2", + "tol": 0.0035674973511975678, + "C": 2.60441630415354, + "fit_intercept": false, + "solver": "lbfgs", + "max_iter": 1526 + }, + "metrics": { + "accuracy": 0.4111, + "balanced_accuracy": 0.2227, + "macro_f1": 0.2072, + "weighted_f1": 0.3745, + "quadratic_kappa": 0.1881, + "kappa": -0.0103, + "mcc": -0.0106, + "roc_auc_weighted_ovr": 0.5312 + }, + "bytes": 5349, + "sha256": "8b6ebca01f80d053fe4f58d445d872979bd095d32cab997cede91ce7f636c3b6", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Logistic Regression (balanced)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__logistic_regression_balanced.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4654, + "params": { + "penalty": "l2", + "tol": 0.0004086458374105822, + "C": 0.7075713679745544, + "fit_intercept": false, + "solver": "saga", + "max_iter": 726 + }, + "metrics": { + "accuracy": 0.4094, + "balanced_accuracy": 0.3504, + "macro_f1": 0.3314, + "weighted_f1": 0.4254, + "quadratic_kappa": 0.3412, + "kappa": 0.1311, + "mcc": 0.1349, + "roc_auc_weighted_ovr": 0.5499 + }, + "bytes": 5409, + "sha256": "febcd9de7794eb37e1defb790bcb7c38fdba565d02fa0c422b78b99d57fd7e9a", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "MLP (256-128)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__mlp_256_128.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4747, + "params": { + "hidden_layer_sizes": "128_64", + "activation": "tanh", + "solver": "sgd", + "alpha": 1.518091449100529e-05, + "learning_rate": "invscaling", + "learning_rate_init": 0.07752153512517584, + "max_iter": 831, + "tol": 1.1047078082258689e-06, + "early_stopping": true + }, + "metrics": { + "accuracy": 0.4704, + "balanced_accuracy": 0.3866, + "macro_f1": 0.3824, + "weighted_f1": 0.4852, + "quadratic_kappa": 0.3796, + "kappa": 0.2061, + "mcc": 0.2126, + "roc_auc_weighted_ovr": 0.6448 + }, + "bytes": 436331, + "sha256": "2f54dcee6b5b79afed0e8f06de8e5f780db6810925e3ea7b7b0b811a6686dbb7", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Nearest Centroid", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__nearest_centroid.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4379, + "params": { + "metric": "euclidean", + "shrink_threshold": 0.49371148383200575 + }, + "metrics": { + "accuracy": 0.3275, + "balanced_accuracy": 0.3282, + "macro_f1": 0.2884, + "weighted_f1": 0.3655, + "quadratic_kappa": 0.3072, + "kappa": 0.1197, + "mcc": 0.1347, + "roc_auc_weighted_ovr": 0.6268 + }, + "bytes": 8358, + "sha256": "cd215a76d3a897dfad9e4a9602630ac2e447174d82bcc26914e408eb375a13f7", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Passive Aggressive", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__passive_aggressive.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4889, + "params": { + "C": 4667.462349328399, + "fit_intercept": true, + "max_iter": 1617, + "tol": 0.0002698802952120931, + "early_stopping": true, + "validation_fraction": 0.0777267950828245, + "n_iter_no_change": 1, + "shuffle": true, + "loss": "hinge", + "class_weight": "balanced", + "average": true + }, + "metrics": { + "accuracy": 0.4094, + "balanced_accuracy": 0.2502, + "macro_f1": 0.2527, + "weighted_f1": 0.3989, + "quadratic_kappa": 0.1913, + "kappa": 0.0333, + "mcc": 0.0339 + }, + "bytes": 10098, + "sha256": "b0bfdb195a43b2eb02c0d5a2f1ec00b6cc74c8d4d54c07021cbbad72db0ca9ac", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Perceptron", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__perceptron.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4386, + "params": { + "penalty": null, + "alpha": 1.608166928363465e-07, + "l1_ratio": 0.9093204020787821, + "fit_intercept": false, + "max_iter": 1004, + "tol": 0.0012030178871154666, + "shuffle": true, + "eta0": 7.556810141274429, + "early_stopping": false, + "validation_fraction": 0.2737068376069122, + "n_iter_no_change": 6, + "class_weight": null + }, + "metrics": { + "accuracy": 0.5122, + "balanced_accuracy": 0.2451, + "macro_f1": 0.1898, + "weighted_f1": 0.3871, + "quadratic_kappa": 0.0872, + "kappa": 0.0062, + "mcc": 0.0094 + }, + "bytes": 3790, + "sha256": "d24111b8b0295eebdd59a9e2ac879c46ea9c368d7ca322b4859c34e1558a6f2c", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Quadratic Discriminant", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__quadratic_discriminant.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4987, + "params": { + "pca__n_components": 13, + "reg_param": 0.56021316175996, + "store_covariance": false, + "tol": 0.0003433487371306303 + }, + "metrics": { + "accuracy": 0.547, + "balanced_accuracy": 0.3458, + "macro_f1": 0.2919, + "weighted_f1": 0.4935, + "quadratic_kappa": 0.2891, + "kappa": 0.2446, + "mcc": 0.2627, + "roc_auc_weighted_ovr": 0.7285 + }, + "bytes": 23376, + "sha256": "7900d9df6f932ba74aa1a8e47316a9a8cab1217ba046e14c7c1fed0622e43ee0", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Random Forest", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__random_forest.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.5301, + "params": { + "n_estimators": 200, + "criterion": "log_loss", + "max_depth": 13, + "min_samples_split": 6, + "min_samples_leaf": 6, + "min_weight_fraction_leaf": 0.18869030979403617, + "max_features": null, + "bootstrap": false, + "ccp_alpha": 0.0061748614666293205, + "max_samples": 0.8 + }, + "metrics": { + "accuracy": 0.5348, + "balanced_accuracy": 0.3872, + "macro_f1": 0.3557, + "weighted_f1": 0.5403, + "quadratic_kappa": 0.3637, + "kappa": 0.3017, + "mcc": 0.3202, + "roc_auc_weighted_ovr": 0.7257 + }, + "bytes": 4532, + "sha256": "1e7d47bfecacf241774aff763cbec7e09e8ec3340eab16a36302351f74a47452", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Random Forest (balanced)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__random_forest_balanced.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4899, + "params": { + "n_estimators": 100, + "criterion": "entropy", + "max_depth": 37, + "min_samples_split": 5, + "min_samples_leaf": 10, + "min_weight_fraction_leaf": 0.06100948759139501, + "max_features": "sqrt", + "bootstrap": true, + "ccp_alpha": 0.05482745624204204, + "max_samples": 0.7 + }, + "metrics": { + "accuracy": 0.5714, + "balanced_accuracy": 0.5239, + "macro_f1": 0.4888, + "weighted_f1": 0.6055, + "quadratic_kappa": 0.5091, + "kappa": 0.3866, + "mcc": 0.4006, + "roc_auc_weighted_ovr": 0.746 + }, + "bytes": 15369, + "sha256": "609212dcb35a64da848914e46ed9ddd38d57f2b9dee38b629bd566878da342dc", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Ridge Classifier", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__ridge_classifier.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.453, + "params": { + "alpha": 0.16830448420647048, + "fit_intercept": false, + "max_iter": 436, + "tol": 0.00439266117717107, + "solver": "sparse_cg" + }, + "metrics": { + "accuracy": 0.4861, + "balanced_accuracy": 0.2645, + "macro_f1": 0.2417, + "weighted_f1": 0.4246, + "quadratic_kappa": 0.2537, + "kappa": 0.0684, + "mcc": 0.0735 + }, + "bytes": 5391, + "sha256": "0fb73e9bee81cf54e33a13fc7a581c404dc9ea05d412e8bd00ca8d406865241b", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "SGD (hinge)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__sgd_hinge.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4722, + "params": { + "penalty": "l2", + "alpha": 4.6146396163090724e-05, + "l1_ratio": 0.3894491613327526, + "fit_intercept": true, + "max_iter": 697, + "tol": 0.0011109430612901588, + "learning_rate": "invscaling", + "eta0": 0.2725124444154003, + "early_stopping": true, + "validation_fraction": 0.2650539661157578, + "n_iter_no_change": 3 + }, + "metrics": { + "accuracy": 0.5052, + "balanced_accuracy": 0.2586, + "macro_f1": 0.224, + "weighted_f1": 0.4116, + "quadratic_kappa": 0.1934, + "kappa": 0.0532, + "mcc": 0.0665 + }, + "bytes": 5129, + "sha256": "5b498b2975c80deca53c322917fa4e29a4d178bfdf21d8df5cc8c8e18cc56738", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "SVM (RBF)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__svm_rbf.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4913, + "params": { + "C": 2.0206264305920913, + "gamma": "scale", + "tol": 0.00010228834000617092, + "shrinking": true, + "class_weight": "balanced", + "decision_function_shape": "ovr" + }, + "metrics": { + "accuracy": 0.4216, + "balanced_accuracy": 0.3155, + "macro_f1": 0.31, + "weighted_f1": 0.4235, + "quadratic_kappa": 0.2179, + "kappa": 0.101, + "mcc": 0.1037, + "roc_auc_weighted_ovr": 0.6178 + }, + "bytes": 70810, + "sha256": "1a26de893dbe4ce1d79dbcdf43270c9c4c66be5a385c9c2577b2fd15ed237647", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "SVM (polynomial)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__svm_polynomial.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4899, + "params": { + "C": 0.013930395693114054, + "gamma": "scale", + "tol": 0.0027672535040671182, + "shrinking": true, + "class_weight": null, + "decision_function_shape": "ovo", + "degree": 3, + "coef0": 0.9805317255080246 + }, + "metrics": { + "accuracy": 0.5732, + "balanced_accuracy": 0.3816, + "macro_f1": 0.3337, + "weighted_f1": 0.5338, + "quadratic_kappa": 0.4026, + "kappa": 0.3119, + "mcc": 0.3269, + "roc_auc_weighted_ovr": 0.7245 + }, + "bytes": 64700, + "sha256": "4360d5904237809e9f44857acb0e33b92db78ff0f95b8749ac89c52324d0d4fe", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Soft Voting (RF+XGB+LR)", + "protocol": "doi", + "selection": "composed", + "file": "classifiers/doi/printability__soft_voting_rf_xgb_lr.pkl", + "source_fold": "doi_holdout", + "inner_score": null, + "params": { + "composed_from": [ + "Logistic Regression", + "Random Forest", + "XGBoost" + ] + }, + "metrics": { + "accuracy": 0.4861, + "balanced_accuracy": 0.2705, + "macro_f1": 0.2529, + "weighted_f1": 0.4449, + "quadratic_kappa": 0.382, + "kappa": 0.115, + "mcc": 0.1181, + "roc_auc_weighted_ovr": 0.7047 + }, + "bytes": 6042977, + "sha256": "b46d562fa35e5eb6b39c8bfdcb9248f099384de348385d957ac8529f78b08605", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "Stacking (RF+XGB+LR -> LR)", + "protocol": "doi", + "selection": "composed", + "file": "classifiers/doi/printability__stacking_rf_xgb_lr_lr.pkl", + "source_fold": "doi_holdout", + "inner_score": null, + "params": { + "composed_from": [ + "Logistic Regression", + "Random Forest", + "XGBoost" + ] + }, + "metrics": { + "accuracy": 0.5366, + "balanced_accuracy": 0.3463, + "macro_f1": 0.2896, + "weighted_f1": 0.4803, + "quadratic_kappa": 0.1446, + "kappa": 0.2265, + "mcc": 0.2431, + "roc_auc_weighted_ovr": 0.7475 + }, + "bytes": 6043495, + "sha256": "c54d27d4ecc2300577c78667b3ea5d1c13abe76517ddca841279deeb0de5245f", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "XGBoost", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__xgboost.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.4787, + "params": { + "n_estimators": 468, + "max_depth": 3, + "learning_rate": 0.2925636669623597, + "gamma": 3.7005024190423357, + "min_child_weight": 2.822653000800327, + "subsample": 0.5118183820822848, + "colsample_bytree": 0.5843582204720735, + "reg_alpha": 0.6635717690098635, + "reg_lambda": 9.533061755694554 + }, + "metrics": { + "accuracy": 0.5714, + "balanced_accuracy": 0.3584, + "macro_f1": 0.3403, + "weighted_f1": 0.5202, + "quadratic_kappa": 0.2412, + "kappa": 0.2472, + "mcc": 0.2581, + "roc_auc_weighted_ovr": 0.7467 + }, + "bytes": 70459, + "sha256": "d49d951cff64d17471162366c10f0d17ee0220c41a57dc3e18090b4bb9c580f0", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "k-NN (distance weighted)", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__k_nn_distance_weighted.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.438, + "params": { + "n_neighbors": 39, + "algorithm": "kd_tree", + "leaf_size": 76, + "p": 4, + "metric": "euclidean" + }, + "metrics": { + "accuracy": 0.3554, + "balanced_accuracy": 0.2527, + "macro_f1": 0.2217, + "weighted_f1": 0.3443, + "quadratic_kappa": -0.0109, + "kappa": 0.0197, + "mcc": 0.0206, + "roc_auc_weighted_ovr": 0.603 + }, + "bytes": 119318, + "sha256": "3471e296d0e832cb03cd800c5d4d3c3ac38c46b24e4cb06eaf848b6a4be06354", + "reused": true + }, + { + "family": "ml", + "task": "printability", + "model": "k-Nearest Neighbours", + "protocol": "doi", + "selection": "weighted", + "file": "classifiers/doi/printability__k_nearest_neighbours.pkl", + "source_fold": "doi_holdout", + "inner_score": 0.438, + "params": { + "n_neighbors": 40, + "algorithm": "auto", + "leaf_size": 84, + "p": 5, + "metric": "minkowski" + }, + "metrics": { + "accuracy": 0.3449, + "balanced_accuracy": 0.2635, + "macro_f1": 0.2463, + "weighted_f1": 0.3667, + "quadratic_kappa": 0.0292, + "kappa": 0.0646, + "mcc": 0.0687, + "roc_auc_weighted_ovr": 0.6093 + }, + "bytes": 53696, + "sha256": "84ac69a25645b01f3013259103ee4ab8e3f70b37a49702df451fbb59f55bd0de", + "reused": true + }, + { + "family": "dl", + "task": "cell_response", + "model": "1D_CNN", + "protocol": "doi", + "selection": "weighted", + "file": "deep/doi/cell_response__1d_cnn.pt", + "source_fold": "doi_holdout", + "inner_score": 0.5875, + "params": { + "n_layers": 6, + "hidden_dim": 160, + "lr": 0.0022093834415066287, + "weight_decay": 0.0019268985325226215, + "dropout": 0.17129126319771992, + "batch_size": 32, + "activation": "GELU", + "optimizer": "AdamW", + "max_epochs": 168, + "class_weight": null + }, + "metrics": { + "accuracy": 0.5697, + "balanced_accuracy": 0.3697, + "macro_f1": 0.3404, + "weighted_f1": 0.6198, + "quadratic_kappa": 0.7724, + "kappa": 0.3482, + "mcc": 0.3649, + "roc_auc_weighted_ovr": 0.7886 + }, + "bytes": 1574683, + "sha256": "7f095da78e83abc96530b1d0f0f3552bd667002ee6a7fa5b887be9ce9028b353", + "reused": true + }, + { + "family": "dl", + "task": "cell_response", + "model": "FT_Transformer", + "protocol": "doi", + "selection": "weighted", + "file": "deep/doi/cell_response__ft_transformer.pt", + "source_fold": "doi_holdout", + "inner_score": 0.6168, + "params": { + "n_layers": 1, + "hidden_dim": 352, + "lr": 0.00011743525676125396, + "weight_decay": 0.005467630013091895, + "dropout": 0.3981692691675482, + "batch_size": 32, + "activation": "SELU", + "optimizer": "Adam", + "max_epochs": 154, + "class_weight": null + }, + "metrics": { + "accuracy": 0.7439, + "balanced_accuracy": 0.3921, + "macro_f1": 0.3739, + "weighted_f1": 0.7359, + "quadratic_kappa": 0.8202, + "kappa": 0.5504, + "mcc": 0.552, + "roc_auc_weighted_ovr": 0.9169 + }, + "bytes": 4426730, + "sha256": "1c54a866e50ffa88cda31b15c06a58a0b78332f20d655acc6b8f066a309cd0ad", + "reused": true + }, + { + "family": "dl", + "task": "cell_response", + "model": "MLP", + "protocol": "doi", + "selection": "weighted", + "file": "deep/doi/cell_response__mlp.pt", + "source_fold": "doi_holdout", + "inner_score": 0.6093, + "params": { + "n_layers": 5, + "hidden_dim": 448, + "lr": 0.0038377717552575347, + "weight_decay": 0.00034632526053519463, + "dropout": 0.11731103383390191, + "batch_size": 256, + "activation": "GELU", + "optimizer": "RMSprop", + "max_epochs": 216, + "class_weight": null + }, + "metrics": { + "accuracy": 0.5993, + "balanced_accuracy": 0.2724, + "macro_f1": 0.26, + "weighted_f1": 0.5585, + "quadratic_kappa": 0.2395, + "kappa": 0.218, + "mcc": 0.2235, + "roc_auc_weighted_ovr": 0.8217 + }, + "bytes": 3551373, + "sha256": "b3662c1fa368ff33f17d0cb6bbf016faa0b03a71a6c11af5fcdcd703284d6b18", + "reused": true + }, + { + "family": "dl", + "task": "cell_response", + "model": "NODE_Lite", + "protocol": "doi", + "selection": "weighted", + "file": "deep/doi/cell_response__node_lite.pt", + "source_fold": "doi_holdout", + "inner_score": 0.6241, + "params": { + "n_layers": 6, + "hidden_dim": 96, + "lr": 0.009842695582692119, + "weight_decay": 3.2006448599035196e-05, + "dropout": 0.1627390340258759, + "batch_size": 64, + "activation": "tanh", + "optimizer": "AdamW", + "max_epochs": 157, + "class_weight": "balanced" + }, + "metrics": { + "accuracy": 0.6098, + "balanced_accuracy": 0.3008, + "macro_f1": 0.3041, + "weighted_f1": 0.5942, + "quadratic_kappa": 0.4373, + "kappa": 0.284, + "mcc": 0.2888, + "roc_auc_weighted_ovr": 0.7939 + }, + "bytes": 494015, + "sha256": "f80f39fefd83008c8aece1f5e60dfcafdaef800a7d77771569922aac8a36df17", + "reused": true + }, + { + "family": "dl", + "task": "cell_response", + "model": "ResNet", + "protocol": "doi", + "selection": "weighted", + "file": "deep/doi/cell_response__resnet.pt", + "source_fold": "doi_holdout", + "inner_score": 0.5976, + "params": { + "n_layers": 1, + "hidden_dim": 448, + "lr": 0.00014096175149815865, + "weight_decay": 0.009133995846860976, + "dropout": 0.33167343078899725, + "batch_size": 128, + "activation": "SiLU", + "optimizer": "Adam", + "max_epochs": 197, + "class_weight": null + }, + "metrics": { + "accuracy": 0.6202, + "balanced_accuracy": 0.2858, + "macro_f1": 0.2763, + "weighted_f1": 0.5909, + "quadratic_kappa": 0.3867, + "kappa": 0.2834, + "mcc": 0.2868, + "roc_auc_weighted_ovr": 0.8074 + }, + "bytes": 1110183, + "sha256": "2b5bdcb36cd5555cf145afac8f8ea8a20a5ef478cb11b21191116eec41c7c907", + "reused": true + }, + { + "family": "dl", + "task": "cell_response", + "model": "TabNet_Lite", + "protocol": "doi", + "selection": "weighted", + "file": "deep/doi/cell_response__tabnet_lite.pt", + "source_fold": "doi_holdout", + "inner_score": 0.603, + "params": { + "n_layers": 3, + "hidden_dim": 480, + "lr": 0.006346577282966738, + "weight_decay": 0.0006593465821488544, + "dropout": 0.15630959598318916, + "batch_size": 128, + "activation": "GELU", + "optimizer": "Adam", + "max_epochs": 245, + "class_weight": null + }, + "metrics": { + "accuracy": 0.6167, + "balanced_accuracy": 0.3121, + "macro_f1": 0.2975, + "weighted_f1": 0.6163, + "quadratic_kappa": 0.5331, + "kappa": 0.3345, + "mcc": 0.3409, + "roc_auc_weighted_ovr": 0.8028 + }, + "bytes": 1828453, + "sha256": "6ee1895edc9370e00d1030c4722a13528362647fb1f54998a0202ffbc2c40fee", + "reused": true + }, + { + "family": "dl", + "task": "printability", + "model": "1D_CNN", + "protocol": "doi", + "selection": "weighted", + "file": "deep/doi/printability__1d_cnn.pt", + "source_fold": "doi_holdout", + "inner_score": 0.6418, + "params": { + "n_layers": 2, + "hidden_dim": 192, + "lr": 0.0004371440922464809, + "weight_decay": 0.0007604663958409753, + "dropout": 0.19075177963373807, + "batch_size": 256, + "activation": "ELU", + "optimizer": "RMSprop", + "max_epochs": 323, + "class_weight": null + }, + "metrics": { + "accuracy": 0.4181, + "balanced_accuracy": 0.2862, + "macro_f1": 0.2795, + "weighted_f1": 0.3997, + "quadratic_kappa": 0.0301, + "kappa": 0.0377, + "mcc": 0.0399, + "roc_auc_weighted_ovr": 0.5337 + }, + "bytes": 461649, + "sha256": "40276fcb8dedda1da9dc1d0df395d5ad0890dfede1afcf1b11881f0ee4ea4b0c", + "reused": true + }, + { + "family": "dl", + "task": "printability", + "model": "FT_Transformer", + "protocol": "doi", + "selection": "weighted", + "file": "deep/doi/printability__ft_transformer.pt", + "source_fold": "doi_holdout", + "inner_score": 0.6849, + "params": { + "n_layers": 1, + "hidden_dim": 448, + "lr": 0.00014096175149815865, + "weight_decay": 0.009133995846860976, + "dropout": 0.33167343078899725, + "batch_size": 128, + "activation": "SiLU", + "optimizer": "Adam", + "max_epochs": 197, + "class_weight": null + }, + "metrics": { + "accuracy": 0.5279, + "balanced_accuracy": 0.3434, + "macro_f1": 0.3386, + "weighted_f1": 0.5033, + "quadratic_kappa": 0.3773, + "kappa": 0.2106, + "mcc": 0.2137, + "roc_auc_weighted_ovr": 0.6997 + }, + "bytes": 7006547, + "sha256": "519bf6a0dd0666f4d9d80a7b9a02fb45ad87c6e02e0a9eecf2ab903b094b4075", + "reused": true + }, + { + "family": "dl", + "task": "printability", + "model": "MLP", + "protocol": "doi", + "selection": "weighted", + "file": "deep/doi/printability__mlp.pt", + "source_fold": "doi_holdout", + "inner_score": 0.6358, + "params": { + "n_layers": 4, + "hidden_dim": 320, + "lr": 0.0063193263783952215, + "weight_decay": 0.00012507787479502943, + "dropout": 0.34737533026378065, + "batch_size": 64, + "activation": "relu", + "optimizer": "Adam", + "max_epochs": 125, + "class_weight": null + }, + "metrics": { + "accuracy": 0.4443, + "balanced_accuracy": 0.3013, + "macro_f1": 0.2775, + "weighted_f1": 0.4236, + "quadratic_kappa": 0.1223, + "kappa": 0.0987, + "mcc": 0.1002, + "roc_auc_weighted_ovr": 0.5697 + }, + "bytes": 1465393, + "sha256": "6b8dc0b0db9c473caea70e344121fea265664fc1527a72e87226d33ddbc1561d", + "reused": true + }, + { + "family": "dl", + "task": "printability", + "model": "NODE_Lite", + "protocol": "doi", + "selection": "weighted", + "file": "deep/doi/printability__node_lite.pt", + "source_fold": "doi_holdout", + "inner_score": 0.6542, + "params": { + "n_layers": 6, + "hidden_dim": 512, + "lr": 0.007235342779315474, + "weight_decay": 2.7809192169581745e-05, + "dropout": 0.17325163380941638, + "batch_size": 32, + "activation": "SiLU", + "optimizer": "AdamW", + "max_epochs": 214, + "class_weight": "balanced" + }, + "metrics": { + "accuracy": 0.4338, + "balanced_accuracy": 0.3402, + "macro_f1": 0.3272, + "weighted_f1": 0.4351, + "quadratic_kappa": 0.3554, + "kappa": 0.1271, + "mcc": 0.1299, + "roc_auc_weighted_ovr": 0.5865 + }, + "bytes": 2609680, + "sha256": "187c094b621b4326cac4929a5bba7be896181fac88068451f0d9fc57b4746097", + "reused": true + }, + { + "family": "dl", + "task": "printability", + "model": "ResNet", + "protocol": "doi", + "selection": "weighted", + "file": "deep/doi/printability__resnet.pt", + "source_fold": "doi_holdout", + "inner_score": 0.6452, + "params": { + "n_layers": 2, + "hidden_dim": 128, + "lr": 0.007234279845665418, + "weight_decay": 0.002656813924114493, + "dropout": 0.2900211269531271, + "batch_size": 256, + "activation": "GELU", + "optimizer": "RMSprop", + "max_epochs": 253, + "class_weight": null + }, + "metrics": { + "accuracy": 0.5244, + "balanced_accuracy": 0.3739, + "macro_f1": 0.3777, + "weighted_f1": 0.5172, + "quadratic_kappa": 0.4254, + "kappa": 0.2311, + "mcc": 0.2315, + "roc_auc_weighted_ovr": 0.5963 + }, + "bytes": 227351, + "sha256": "5e314f0082ecb8d579c92c0a7a0968c9e5b9f7c1fc5ddb0482e6051628b541f8", + "reused": true + }, + { + "family": "dl", + "task": "printability", + "model": "TabNet_Lite", + "protocol": "doi", + "selection": "weighted", + "file": "deep/doi/printability__tabnet_lite.pt", + "source_fold": "doi_holdout", + "inner_score": 0.6531, + "params": { + "n_layers": 6, + "hidden_dim": 288, + "lr": 0.00017345566642360953, + "weight_decay": 0.0013795402040204172, + "dropout": 0.3282355145850693, + "batch_size": 64, + "activation": "ELU", + "optimizer": "AdamW", + "max_epochs": 327, + "class_weight": null + }, + "metrics": { + "accuracy": 0.4164, + "balanced_accuracy": 0.2299, + "macro_f1": 0.2115, + "weighted_f1": 0.3681, + "quadratic_kappa": -0.0354, + "kappa": -0.0455, + "mcc": -0.0482, + "roc_auc_weighted_ovr": 0.4257 + }, + "bytes": 2203428, + "sha256": "1b43f1e2c66f4a1743eae51e52b75fbb32274a2c0547409e7c838b7374a5957c", + "reused": true + }, + { + "family": "foundation", + "task": "printability", + "model": "TabPFN", + "protocol": "n/a", + "selection": "zero_shot", + "file": "foundation/printability__tabpfn.pkl", + "checkpoint": "tabpfn-v2.6-classifier-v2.6_default.ckpt", + "n_estimators": 8, + "context_rows": 2646, + "classes": [ + 0, + 1, + 2, + 3 + ], + "metrics": { + "accuracy": 0.7698, + "macro_f1": 0.7192, + "weighted_f1": 0.7696, + "mcc": 0.6443 + }, + "bytes": 21578, + "sha256": "f69c3b9604651aa3e4789a69d59a7544eeb31074e6277ea7a4763926aae86d4c", + "reused": true + }, + { + "family": "foundation", + "task": "printability", + "model": "TabPFN (thinking)", + "protocol": "n/a", + "selection": "zero_shot", + "file": "foundation/printability__tabpfn_thinking.pkl", + "checkpoint": "tabpfn-v2.6-classifier-v2.6_default.ckpt", + "n_estimators": 8, + "context_rows": 2646, + "classes": [ + 0, + 1, + 2, + 3 + ], + "metrics": { + "accuracy": 0.7792, + "macro_f1": 0.7383, + "weighted_f1": 0.7793, + "mcc": 0.6586 + }, + "bytes": 21590, + "sha256": "e7d5e330c3c552da1177c203502df36ad34823bf553a547e7a34b5328e1256ac", + "reused": true + }, + { + "family": "foundation", + "task": "printability", + "model": "TabICL", + "protocol": "n/a", + "selection": "zero_shot", + "file": "foundation/printability__tabicl.pkl", + "checkpoint": null, + "n_estimators": 8, + "context_rows": 2646, + "classes": [ + 0, + 1, + 2, + 3 + ], + "metrics": { + "accuracy": 0.8057, + "macro_f1": 0.7708, + "weighted_f1": 0.8065, + "mcc": 0.7024 + }, + "bytes": 21534, + "sha256": "f986088d0b6c6de01fe08ee2907db7ab123460bf5c25ac0348bbfbb772b8c3ca", + "reused": true + }, + { + "family": "foundation", + "task": "cell_response", + "model": "TabPFN", + "protocol": "n/a", + "selection": "zero_shot", + "file": "foundation/cell_response__tabpfn.pkl", + "checkpoint": "tabpfn-v2.6-classifier-v2.6_default.ckpt", + "n_estimators": 8, + "context_rows": 2646, + "classes": [ + 1, + 2, + 3, + 4, + 5 + ], + "metrics": { + "accuracy": 0.7811, + "macro_f1": 0.5345, + "weighted_f1": 0.7725, + "mcc": 0.6359 + }, + "bytes": 21466, + "sha256": "841200261e2e7838aa4026136523253e574dea2c98089460a8eb947705fbd04d", + "reused": true + }, + { + "family": "foundation", + "task": "cell_response", + "model": "TabPFN (thinking)", + "protocol": "n/a", + "selection": "zero_shot", + "file": "foundation/cell_response__tabpfn_thinking.pkl", + "checkpoint": "tabpfn-v2.6-classifier-v2.6_default.ckpt", + "n_estimators": 8, + "context_rows": 2646, + "classes": [ + 1, + 2, + 3, + 4, + 5 + ], + "metrics": { + "accuracy": 0.7736, + "macro_f1": 0.555, + "weighted_f1": 0.773, + "mcc": 0.6249 + }, + "bytes": 21479, + "sha256": "2ec859089ccbd723cb79eaa88807071b4db3bccf717bc98fdffde51288ae6210", + "reused": true + }, + { + "family": "foundation", + "task": "cell_response", + "model": "TabICL", + "protocol": "n/a", + "selection": "zero_shot", + "file": "foundation/cell_response__tabicl.pkl", + "checkpoint": null, + "n_estimators": 8, + "context_rows": 2646, + "classes": [ + 1, + 2, + 3, + 4, + 5 + ], + "metrics": { + "accuracy": 0.7698, + "macro_f1": 0.5456, + "weighted_f1": 0.7661, + "mcc": 0.6147 + }, + "bytes": 21429, + "sha256": "2baa4df60428ba939c88bb2395875331e17d38c905750940b2f7093b150538b9", + "reused": true + } + ] +} \ No newline at end of file diff --git a/deploy/models/foundation/cell_response__tabicl.pkl b/deploy/models/foundation/cell_response__tabicl.pkl new file mode 100644 index 0000000000000000000000000000000000000000..cbccd7e261c4248e168b38cac43b633394568740 --- /dev/null +++ b/deploy/models/foundation/cell_response__tabicl.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2baa4df60428ba939c88bb2395875331e17d38c905750940b2f7093b150538b9 +size 21429 diff --git a/deploy/models/foundation/cell_response__tabpfn.pkl b/deploy/models/foundation/cell_response__tabpfn.pkl new file mode 100644 index 0000000000000000000000000000000000000000..414be0ff53a99463867db39b6c9f78c34f9a2df3 --- /dev/null +++ b/deploy/models/foundation/cell_response__tabpfn.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:841200261e2e7838aa4026136523253e574dea2c98089460a8eb947705fbd04d +size 21466 diff --git a/deploy/models/foundation/cell_response__tabpfn_thinking.pkl b/deploy/models/foundation/cell_response__tabpfn_thinking.pkl new file mode 100644 index 0000000000000000000000000000000000000000..325f6a24a2a7c6c52b98e844dcd106447d1fd1dc --- /dev/null +++ b/deploy/models/foundation/cell_response__tabpfn_thinking.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec859089ccbd723cb79eaa88807071b4db3bccf717bc98fdffde51288ae6210 +size 21479 diff --git a/deploy/models/foundation/printability__tabicl.pkl b/deploy/models/foundation/printability__tabicl.pkl new file mode 100644 index 0000000000000000000000000000000000000000..b0f92a94dc57bb08827d32745487c4eeb8b7c198 --- /dev/null +++ b/deploy/models/foundation/printability__tabicl.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f986088d0b6c6de01fe08ee2907db7ab123460bf5c25ac0348bbfbb772b8c3ca +size 21534 diff --git a/deploy/models/foundation/printability__tabpfn.pkl b/deploy/models/foundation/printability__tabpfn.pkl new file mode 100644 index 0000000000000000000000000000000000000000..3fef3e20ee8a24223262699caf3719017da3ddc7 --- /dev/null +++ b/deploy/models/foundation/printability__tabpfn.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f69c3b9604651aa3e4789a69d59a7544eeb31074e6277ea7a4763926aae86d4c +size 21578 diff --git a/deploy/models/foundation/printability__tabpfn_thinking.pkl b/deploy/models/foundation/printability__tabpfn_thinking.pkl new file mode 100644 index 0000000000000000000000000000000000000000..47bb46d3635bfe2a04fd06b4a4d0360860073ba5 --- /dev/null +++ b/deploy/models/foundation/printability__tabpfn_thinking.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7d5e330c3c552da1177c203502df36ad34823bf553a547e7a34b5328e1256ac +size 21590 diff --git a/deploy/models/preprocessors/feature_names.pkl b/deploy/models/preprocessors/feature_names.pkl new file mode 100644 index 0000000000000000000000000000000000000000..cd93bcc7b4d3afe6d9cc0e144eca6ca121d53628 --- /dev/null +++ b/deploy/models/preprocessors/feature_names.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de846baea9ea14454cadf5e04a965975074c4cb8413a8a745e8fcbd33a4b7f3c +size 1531 diff --git a/deploy/models/preprocessors/input_columns.pkl b/deploy/models/preprocessors/input_columns.pkl new file mode 100644 index 0000000000000000000000000000000000000000..3790432dac7b109a5962ecedc26676a3deb6ad29 --- /dev/null +++ b/deploy/models/preprocessors/input_columns.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9505e1cc75563f88d19f125511f19c113180c4174551192ecbfdce5391dc117 +size 1454 diff --git a/deploy/models/preprocessors/manifest.json b/deploy/models/preprocessors/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..e7611414d302291257cb1198c6e361f1062898ee --- /dev/null +++ b/deploy/models/preprocessors/manifest.json @@ -0,0 +1,38 @@ +{ + "created_utc": "2026-09-02T17:42:00+00:00", + "python": "3.14.3", + "sklearn": "1.8.0", + "numpy": "2.4.4", + "pandas": "2.3.3", + "config": { + "imputer_estimator": "extra_trees", + "imputer_max_iter": 10, + "ambient_strategy": "constant", + "ambient_temperature_c": 22.0, + "random_state": 42 + }, + "dataset": { + "rows": 2646, + "input_columns": 139, + "output_features": 153, + "indicator_features": 7 + }, + "files": { + "feature_names.pkl": { + "bytes": 1531, + "sha256": "de846baea9ea14454cadf5e04a965975074c4cb8413a8a745e8fcbd33a4b7f3c" + }, + "input_columns.pkl": { + "bytes": 1454, + "sha256": "c9505e1cc75563f88d19f125511f19c113180c4174551192ecbfdce5391dc117" + }, + "preprocessor.pkl": { + "bytes": 10079, + "sha256": "bc836520d819ab28bc4720dbb76130086b4da9932f5204bd41fd6efb213812a5" + }, + "target_schema.json": { + "bytes": 494, + "sha256": "63f239029b5935e444800fd38d4c90c93153ec937cd7d0d2726c56c734fd83c0" + } + } +} \ No newline at end of file diff --git a/deploy/models/preprocessors/preprocessor.pkl b/deploy/models/preprocessors/preprocessor.pkl new file mode 100644 index 0000000000000000000000000000000000000000..c8fa741f2ecf284192da8a020114f4b1fb917805 --- /dev/null +++ b/deploy/models/preprocessors/preprocessor.pkl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc836520d819ab28bc4720dbb76130086b4da9932f5204bd41fd6efb213812a5 +size 10079 diff --git a/deploy/models/preprocessors/target_schema.json b/deploy/models/preprocessors/target_schema.json new file mode 100644 index 0000000000000000000000000000000000000000..2f394642dff56ae6fe0dbf1c2c52883edc23d316 --- /dev/null +++ b/deploy/models/preprocessors/target_schema.json @@ -0,0 +1,16 @@ +{ + "Printability": { + "0": "the ink was not extruded", + "1": "the ink behaved like a liquid, formed beads", + "2": "extrudable but not optimised", + "3": "extrudable and optimised" + }, + "Cell Response": { + "1": "no cells included - not applicable", + "2": "inadequate short-term response", + "3": "good short-term response", + "4": "good short-term, poor long-term", + "5": "good short- and long-term response" + }, + "acellular_token": "NoCellCultured" +} \ No newline at end of file diff --git a/mlate/__init__.py b/mlate/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/mlate/artifacts.py b/mlate/artifacts.py new file mode 100644 index 0000000000000000000000000000000000000000..a1a6520e8007ff2d22941288be0a0b4038c779f9 --- /dev/null +++ b/mlate/artifacts.py @@ -0,0 +1,204 @@ +""" +Fitted-artefact persistence +=========================== + +Fitting a preprocessor is expensive, so it is done once and reused. Two kinds +of artefact, with different purposes: + +fold preprocessors + Fitted on one fold's TRAINING rows only, cached under results/. Every model + scored on that fold reuses the same object, so the imputer is fitted once + per fold rather than once per model per hyper-parameter trial. Cached by a + hash of the training row set, so tasks that share a partition - printability + and cell_response run on the same 2,646 rows - share one artefact. + These are working files and are NOT committed. + +deployment preprocessor + Fitted on the whole dataset and shipped with the release. This is what the + web application loads to transform a user's formulation, and what a reader + needs to reproduce inference. Committed, alongside the feature-name list and + a manifest recording library versions and file hashes. + +A note on size: IterativeImputer keeps every fitted sub-model so it can replay +the imputation sequence at transform time, so an artefact grows linearly with +max_iter (roughly 8 MB per iteration here). Keep cfg.IMPUTER_MAX_ITER at a value +justified by preprocessing/sweep_iterations.py, or the release becomes +undistributable. +""" + +from __future__ import annotations + +import hashlib +import json +import platform +from datetime import datetime, timezone +from pathlib import Path + +import joblib +import numpy as np +import pandas as pd +import sklearn + +from mlate import config as cfg +from mlate.dataset import Columns +from mlate.pipeline import build_preprocessor, feature_names + +CACHE_DIR = cfg.step_dir("02_preprocessing", "models") / "fold_cache" +RELEASE_DIR = cfg.PREPROCESSOR_DIR +COMPRESS = 3 # joblib zlib level; trees compress well + + +def _config_fingerprint() -> str: + """Anything that changes the fitted object must change the cache key.""" + payload = { + "estimator": cfg.IMPUTER_ESTIMATOR, + "max_iter": cfg.IMPUTER_MAX_ITER, + "ambient_strategy": cfg.AMBIENT_STRATEGY, + "ambient_value": cfg.AMBIENT_TEMPERATURE_C, + "seed": cfg.RANDOM_STATE, + "sklearn": sklearn.__version__, + } + return hashlib.sha256( + json.dumps(payload, sort_keys=True).encode()).hexdigest()[:12] + + +def cache_key(train_idx: np.ndarray, columns: Columns | None = None) -> str: + """ + Cache identity of a fitted fold preprocessor. + + The predictor list is part of the key, not just the rows and the imputation + settings. A preprocessor is fitted against a specific column contract, so + two runs that disagree about which columns are predictors must not share an + artefact - otherwise changing the input set silently reloads a transformer + fitted on the old one, and the mismatch surfaces much later as a shape + error, or does not surface at all. + """ + rows = hashlib.sha256( + np.asarray(sorted(train_idx), dtype=np.int64).tobytes()).hexdigest()[:16] + if columns is None: + return f"{rows}_{_config_fingerprint()}" + cols = hashlib.sha256( + json.dumps(list(columns.predictors)).encode()).hexdigest()[:8] + return f"{rows}_{_config_fingerprint()}_{cols}" + + +def fold_preprocessor(df: pd.DataFrame, columns: Columns, + train_idx: np.ndarray, use_cache: bool = True): + """ + Fitted preprocessor for one fold's training rows. + + Returns (preprocessor, path, was_cached). Fitting uses training rows only, + so the cached object can be reused for every model scored on that fold + without leaking anything. + """ + CACHE_DIR.mkdir(parents=True, exist_ok=True) + path = CACHE_DIR / f"pre_{cache_key(train_idx, columns)}.pkl" + if use_cache and path.exists(): + return joblib.load(path), path, True + + pre = build_preprocessor(columns) + pre.fit(df[columns.predictors].iloc[train_idx]) + joblib.dump(pre, path, compress=COMPRESS) + return pre, path, False + + +def build_release(df: pd.DataFrame, columns: Columns) -> dict: + """ + Fit and save the artefacts that ship with the paper. + + The deployment preprocessor is fitted on every row on purpose: at inference + time there is no held-out set to protect, and a user's formulation should be + transformed using everything the dataset knows. It is never used to score a + model - that is what the fold preprocessors are for. + """ + RELEASE_DIR.mkdir(parents=True, exist_ok=True) + + # Exactly the same object the models were trained behind, fitted on every + # row. There was once a separate lightweight deployment variant, needed + # only because an IterativeImputer-based pipeline weighed hundreds of + # megabytes; with median imputation the real pipeline is ~10 kB, so keeping + # a second implementation in step would only invite the two to drift apart. + pre = build_preprocessor(columns).fit(df[columns.predictors]) + names = feature_names(pre) + + joblib.dump(pre, RELEASE_DIR / "preprocessor.pkl", compress=COMPRESS) + joblib.dump(list(columns.predictors), RELEASE_DIR / "input_columns.pkl", + compress=COMPRESS) + joblib.dump(names, RELEASE_DIR / "feature_names.pkl", compress=COMPRESS) + + # Targets are already integer-coded; ship the human-readable meanings so the + # application never has to hard-code them. + schema = { + "Printability": { + "0": "the ink was not extruded", + "1": "the ink behaved like a liquid, formed beads", + "2": "extrudable but not optimised", + "3": "extrudable and optimised", + }, + "Cell Response": { + "1": "no cells included - not applicable", + "2": "inadequate short-term response", + "3": "good short-term response", + "4": "good short-term, poor long-term", + "5": "good short- and long-term response", + }, + "acellular_token": cfg.ACELLULAR_TOKEN, + } + (RELEASE_DIR / "target_schema.json").write_text( + json.dumps(schema, indent=2), encoding="utf-8") + + manifest = { + "created_utc": datetime.now(timezone.utc).isoformat(timespec="seconds"), + "python": platform.python_version(), + "sklearn": sklearn.__version__, + "numpy": np.__version__, + "pandas": pd.__version__, + "config": { + "imputer_estimator": cfg.IMPUTER_ESTIMATOR, + "imputer_max_iter": cfg.IMPUTER_MAX_ITER, + "ambient_strategy": cfg.AMBIENT_STRATEGY, + "ambient_temperature_c": cfg.AMBIENT_TEMPERATURE_C, + "random_state": cfg.RANDOM_STATE, + }, + "dataset": { + "rows": int(len(df)), + "input_columns": len(columns.predictors), + "output_features": len(names), + "indicator_features": sum("[reported]" in n for n in names), + }, + "files": {}, + } + for p in sorted(RELEASE_DIR.iterdir()): + if p.name == "manifest.json": + continue + manifest["files"][p.name] = { + "bytes": p.stat().st_size, + "sha256": hashlib.sha256(p.read_bytes()).hexdigest(), + } + (RELEASE_DIR / "manifest.json").write_text( + json.dumps(manifest, indent=2), encoding="utf-8") + return manifest + + +def load_release(): + """Load the shipped preprocessor. Used by the web application.""" + pre = joblib.load(RELEASE_DIR / "preprocessor.pkl") + cols = joblib.load(RELEASE_DIR / "input_columns.pkl") + names = joblib.load(RELEASE_DIR / "feature_names.pkl") + schema = json.loads((RELEASE_DIR / "target_schema.json").read_text("utf-8")) + return pre, cols, names, schema + + +if __name__ == "__main__": + from mlate.dataset import load_dataset + + frame, cols = load_dataset() + info = build_release(frame, cols) + total = sum(f["bytes"] for f in info["files"].values()) + print(f"release artefacts -> {RELEASE_DIR}") + for name, meta in info["files"].items(): + print(f" {name:<28} {meta['bytes'] / 2**20:8.1f} MB") + print(f" {'TOTAL':<28} {total / 2**20:8.1f} MB" + + (" << exceeds GitHub's 100 MB file limit" + if any(f["bytes"] > 100 * 2**20 for f in info["files"].values()) + else "")) diff --git a/mlate/clustering.py b/mlate/clustering.py new file mode 100644 index 0000000000000000000000000000000000000000..14e5a56ded34aa6f43d403e4ccded4474153baf6 --- /dev/null +++ b/mlate/clustering.py @@ -0,0 +1,198 @@ +""" +Clustering helpers shared by step 03 +==================================== + +The feature matrix is 153 columns, but 130 of them are biomaterial +concentrations that are zero in roughly 95% of rows, so Euclidean distance +risks being dominated by the sparse block: two formulations judged similar +mostly because they both omit the same 120 materials. + +An earlier version of this module applied PCA first and justified it on exactly +that ground. The justification did not survive being tested. Measuring the +Spearman correlation between pairwise distance and the number of jointly-zero +columns gives -0.775 in the raw space and -0.770 after PCA - the projection +does not decouple distance from sparsity, because the leading components are +themselves built out of the sparsity pattern. `reduce()` is therefore offered +but is no longer the default, and the raw space, which is also what the +submitted manuscript used, is primary. 03_clustering/optimal_k.py recomputes +that diagnostic on every run. + +Nothing here selects a clustering. It provides the algorithms, the internal +indices and a resampling-based stability score; the choice is made in +03_clustering/run.py from the table these produce. +""" + +from __future__ import annotations + +import numpy as np +import pandas as pd +from sklearn.cluster import (AgglomerativeClustering, BisectingKMeans, + KMeans, MiniBatchKMeans) +from sklearn.decomposition import PCA +from sklearn.metrics import (adjusted_mutual_info_score, adjusted_rand_score, + calinski_harabasz_score, davies_bouldin_score, + silhouette_score) +from sklearn.mixture import GaussianMixture + +from mlate import config as cfg + +PCA_VARIANCE = 0.95 +K_RANGE = range(2, 31) +N_BOOTSTRAP = 20 +BOOTSTRAP_FRACTION = 0.80 + + +def reduce(matrix: np.ndarray, variance: float = PCA_VARIANCE, + seed: int = cfg.RANDOM_STATE) -> tuple[np.ndarray, PCA]: + """PCA to a fixed explained-variance target.""" + pca = PCA(n_components=variance, svd_solver="full", random_state=seed) + return pca.fit_transform(matrix), pca + + +def algorithms(seed: int = cfg.RANDOM_STATE, space: str = "raw") -> dict: + """ + k-parameterised algorithms. HDBSCAN chooses its own k and is separate. + + The four of the submitted manuscript - KMeans, MiniBatchKMeans, + BisectingKMeans and Agglomerative/Ward - plus GaussianMixture. MiniBatch + appears in the published Table S3, so omitting it would leave a published + row with no counterpart in the revision. + + GaussianMixture takes full covariance only in a reduced space. In the raw + 153-column matrix, where 130 columns are zero in ~95% of rows, a full + per-component covariance is rank-deficient: it either fails or is rescued + by regularisation into a number that means nothing. Diagonal covariance is + the honest choice there, and the restriction is a property of the space + rather than a tuning preference. + """ + cov = "full" if space == "pca" else "diag" + return { + "KMeans": lambda k: KMeans(n_clusters=k, n_init=20, random_state=seed), + "MiniBatchKMeans": lambda k: MiniBatchKMeans( + n_clusters=k, n_init=10, random_state=seed, batch_size=1024), + "BisectingKMeans": lambda k: BisectingKMeans( + n_clusters=k, n_init=10, random_state=seed), + "AgglomerativeWard": lambda k: AgglomerativeClustering( + n_clusters=k, linkage="ward"), + "GaussianMixture": lambda k: GaussianMixture( + n_components=k, covariance_type=cov, n_init=5, random_state=seed, + reg_covar=1e-5), + } + + +def fit_predict(model, X: np.ndarray) -> np.ndarray: + """GaussianMixture splits fit and predict; the cluster estimators do not.""" + if hasattr(model, "fit_predict"): + return np.asarray(model.fit_predict(X)) + return np.asarray(model.fit(X).predict(X)) + + +def indices(X: np.ndarray, labels: np.ndarray) -> dict: + """Internal validity indices, or NaN where a single cluster makes them undefined.""" + uniq = np.unique(labels[labels >= 0]) + if len(uniq) < 2: + return {"silhouette": np.nan, "davies_bouldin": np.nan, + "calinski_harabasz": np.nan} + keep = labels >= 0 # HDBSCAN marks noise as -1 + return { + "silhouette": float(silhouette_score(X[keep], labels[keep])), + "davies_bouldin": float(davies_bouldin_score(X[keep], labels[keep])), + "calinski_harabasz": float(calinski_harabasz_score(X[keep], labels[keep])), + } + + +def _assign_by_centroid(X: np.ndarray, centres: np.ndarray) -> np.ndarray: + d = ((X[:, None, :] - centres[None, :, :]) ** 2).sum(axis=2) + return d.argmin(axis=1) + + +def stability(X: np.ndarray, make, k: int, n_boot: int = N_BOOTSTRAP, + fraction: float = BOOTSTRAP_FRACTION, + seed: int = cfg.RANDOM_STATE) -> float: + """ + Mean adjusted Rand index between the full-data labelling and labellings + refitted on resampled subsets. + + A high silhouette on one fit says the partition is compact; it does not say + the partition would reappear if the corpus had been assembled slightly + differently. For a literature-mined dataset that second question is the + important one, so it gets its own number. Subset labels are carried back to + all rows by nearest centroid, which lets the linkage methods - which have no + predict() - be scored the same way as the rest. + """ + rng = np.random.default_rng(seed) + reference = fit_predict(make(k), X) + scores = [] + for _ in range(n_boot): + idx = rng.choice(len(X), size=int(fraction * len(X)), replace=False) + sub = fit_predict(make(k), X[idx]) + centres = np.vstack([X[idx][sub == c].mean(axis=0) + for c in np.unique(sub)]) + scores.append(adjusted_rand_score(reference, + _assign_by_centroid(X, centres))) + return float(np.mean(scores)) + + + +# The plane every clustering figure is drawn in +# -------------------------------------------- +REFERENCE_ALGORITHM = "BisectingKMeans" +REFERENCE_K = 4 + + +def reference_plane(X: np.ndarray, seed: int = cfg.RANDOM_STATE): + """ + One two-dimensional view, shared by Figures 4, 5, S15 and S17. + + Every clustering figure must place a given formulation at the same point, + or a reader comparing two figures is comparing coordinate systems rather + than partitions. Fitting each figure's own discriminants - as an earlier + version did - satisfied nobody: it showed each partition at its best but + made the figures mutually incomparable. + + The plane chosen is the discriminants of the secondary partition, bisecting + k-means at k = 4, and the choice is empirical rather than aesthetic. It is + the only candidate that keeps BOTH reported partitions clearly separated: + + in the k=3 plane in the k=4 plane + k-means k = 3 0.703 0.589 + bisecting k = 4 0.529 0.745 + + The k = 3 plane costs the four-cluster partition 0.216 of silhouette; the + k = 4 plane costs the three-cluster partition 0.114 and still separates it + plainly. Neither UMAP nor the leading principal components is usable here - + UMAP scores -0.063 on the reported partition, and two principal components + of a 153-column matrix collapse the corpus into an overplotted band. + + Because the plane is fitted to labels it flatters the partition it came + from, so no partition is judged by its appearance in it. Separability is + always reported from each partition's own discriminants instead. + """ + from sklearn.cluster import BisectingKMeans + from sklearn.discriminant_analysis import LinearDiscriminantAnalysis + + labels = BisectingKMeans(n_clusters=REFERENCE_K, n_init=10, + random_state=seed).fit_predict(X) + return (LinearDiscriminantAnalysis(n_components=2) + .fit(X, labels).transform(X)) + + +def agreement(labels: np.ndarray, other: pd.Series) -> dict: + """ + How much of a partition is explained by an external label. + + ARI is reported alongside AMI because DOI has 222 categories against a + handful of clusters, a regime where ARI is pulled toward zero regardless of + the real association. Purity is the plainest of the three: the share of rows + sitting in the most common external category of their own cluster. + """ + other = pd.Series(other).astype(str).to_numpy() + keep = labels >= 0 + lab, oth = labels[keep], other[keep] + purity = (pd.DataFrame({"c": lab, "o": oth}) + .groupby("c")["o"].agg(lambda s: s.value_counts().iloc[0]).sum()) + return { + "ARI": float(adjusted_rand_score(oth, lab)), + "AMI": float(adjusted_mutual_info_score(oth, lab)), + "purity": float(purity / len(lab)), + } diff --git a/mlate/config.py b/mlate/config.py new file mode 100644 index 0000000000000000000000000000000000000000..f3dcc50f7a05a92e898fbc5a8e1a711686a992b1 --- /dev/null +++ b/mlate/config.py @@ -0,0 +1,165 @@ +""" +MLATE V3 β paths and global constants +===================================== + +Every stage imports from here. Nothing else hard-codes a path. +""" + +from __future__ import annotations + +import os +from pathlib import Path + +ROOT = Path(__file__).resolve().parent.parent + +# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ +# PATHS +# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ +DATA_DIR = ROOT / "01_data" +RAW_DIR = DATA_DIR / "raw" +PROCESSED_DIR = DATA_DIR / "processed" +REFERENCE_DIR = DATA_DIR / "reference" + +RESULTS_DIR = ROOT / "results" + +# Pipeline steps. Each has one results folder holding its figures, tables and +# models, so an output is always next to the step that produced it. +STEPS = ("01_data", "02_preprocessing", "03_clustering", + "04_machine_learning", "05_deep_learning", "06_webapp", + "07_wssq") + + +def step_dir(step: str, kind: str | None = None) -> Path: + """results/