Upload 3 files

Home.py

@@ -13,34 +13,51 @@ logo_data_uri = ""
 if logo_path.exists():
     logo_data_uri = "data:image/png;base64," + base64.b64encode(logo_path.read_bytes()).decode("ascii")
 
-logo_html = (
-    f'<img src="{logo_data_uri}" style="width:120px; height:120px; object-fit:contain; border-radius:10px;" />'
-    if logo_data_uri
-    else ""
+st.markdown(
+    """
+<div style="margin: 0.15rem 0 0.4rem 0;">
+  <span class="pp-badge">Home</span>
+</div>
+""",
+    unsafe_allow_html=True,
 )
 
 st.markdown(
     f"""
-<div style="background:#123a69; border-radius:14px; padding:16px 22px; margin: 4px 0 12px 0;">
-  <div style="display:flex; align-items:center; gap:18px;">
-    {logo_html}
-    <div style="color:#ffffff; font-size:2.8rem; line-height:1.05; font-weight:800;">
-      Polymer Discovery Platform
+<section class="pp-main-card">
+  <div class="pp-main-grid">
+    <div>
+      <h1 class="pp-main-title">Polymer Discovery Platform</h1>
+      <p class="pp-main-copy">
+        A unified platform for polymer research that combines property prediction, molecular visualization, and objective-driven candidate discovery to support faster, data-backed screening and selection decisions.
+      </p>
+    </div>
+    <div class="pp-main-logo">
+      {"<img src='" + logo_data_uri + "' alt='Platform logo' />" if logo_data_uri else ""}
     </div>
   </div>
-</div>
+</section>
 """,
     unsafe_allow_html=True,
 )
 
-st.markdown(
-    """
-This platform provides an end-to-end workflow for polymer screening and selection: quick single-polymer checks,
-bulk property prediction, 2D/3D molecular visualization, and multi-objective discovery with Pareto analysis,
-trust scoring, and diversity-aware candidate selection. You can run the process with manual controls or
-AI-assisted setup to accelerate exploration from requirements to shortlisted candidates.
+stats = [
+    ("25+", "Properties"),
+    ("13K+", "Real Polymers"),
+    ("1M", "Virtual Polymers"),
+]
+stats_html = "".join(
+    [
+        f"""
+<div class="pp-kpi-item">
+  <p class="pp-kpi-value">{value}</p>
+  <p class="pp-kpi-label">{label}</p>
+</div>
 """
+        for value, label in stats
+    ]
 )
+st.markdown(f'<section class="pp-kpi-strip">{stats_html}</section>', unsafe_allow_html=True)
 
 st.divider()
 st.markdown("### Platform Modules")
@@ -93,28 +110,44 @@ cards = [
 ]
 
 for i, (title, desc, page_path) in enumerate(cards, start=1):
-    box = st.container(border=True)
-    with box:
-        c1, c2 = st.columns([5, 1.2])
-        with c1:
-            st.markdown(f"**{title}**")
-            st.caption(desc)
-        with c2:
-            if st.button("Go", type="primary", key=f"home_go_{i}"):
-                st.switch_page(page_path)
+    c1, c2 = st.columns([5, 1.1], vertical_alignment="center")
+    page_exists = (Path(__file__).resolve().parent / page_path).exists()
+    with c1:
+        st.markdown(
+            f"""
+<div class="pp-module-card">
+  <p class="pp-module-title">{title}</p>
+  <p class="pp-module-copy">{desc}</p>
+</div>
+""",
+            unsafe_allow_html=True,
+        )
+    with c2:
+        if st.button("Open", type="primary", key=f"home_go_{i}", disabled=not page_exists):
+            st.switch_page(page_path)
 
 st.divider()
-st.markdown("**Developed by**")
-st.markdown("### MONSTER Lab")
-st.markdown("**Molecular/Nano-Scale Transport & Energy Research Laboratory**")
-st.markdown("**College of Engineering, University of Notre Dame**")
 st.markdown(
-    "The MÖNSTER Lab (MOlecular/Nano-Scale Transport & Energy Research Laboratory) "
-    "studies the fundamental physics of energy and mass transport from the molecular and "
-    "nano-scale using theories, simulations, data-driven approaches and experiments, and "
-    "apply the knowledge toward engineering materials with tailored thermal properties, "
-    "thermal management of electronics, improving efficiency of energy devices, designing "
-    "molecules and system for water desalination, high-sensitivity bio-sensing and additive "
-    "manufacturing."
+    """
+<section class="pp-lab-card">
+  <div class="pp-lab-head">
+    <span class="pp-lab-kicker">Research Partner</span>
+    <h3 class="pp-lab-title">Developed by MONSTER Lab</h3>
+    <p class="pp-lab-subtitle">
+      Molecular/Nano-Scale Transport &amp; Energy Research Laboratory | College of Engineering, University of Notre Dame
+    </p>
+  </div>
+  <p class="pp-lab-copy">
+    The MONSTER Lab studies the
+    physics of energy and mass transport across molecular and nano-scales using theory, simulation,
+    data-driven methods, and experiments. The team translates these insights into materials and
+    systems for thermal management, energy efficiency, water desalination, high-sensitivity biosensing,
+    and additive manufacturing.
+  </p>
+  <a class="pp-lab-link" href="https://monsterlab.nd.edu/" target="_blank" rel="noopener noreferrer">
+    Visit MONSTER Lab Website
+  </a>
+</section>
+""",
+    unsafe_allow_html=True,
 )
-st.markdown("[Visit MONSTER Lab Website](https://monsterlab.nd.edu/)")

README.md

@@ -1,8 +1,139 @@
 ---
-title: Polymer Property Predictor
+title: Polymer Discovery Platform
 sdk: streamlit
 python_version: "3.10"
 app_file: Home.py
 ---
 
-Polymer property prediction platform.
+# Polymer Discovery Platform
+
+An integrated Streamlit platform for polymer screening and candidate discovery. The application combines property lookup, machine-learning prediction, molecular visualization, multi-objective discovery, AI-assisted query translation, novel polymer SMILES generation, and export to an automated molecular dynamics workflow.
+
+## What The Platform Does
+
+The website is organized into seven modules:
+
+- `Property Probe`: query a single polymer by SMILES or name and retrieve available database values with prediction fallback.
+- `Batch Prediction`: run multi-property prediction for pasted, uploaded, or built-in polymer sets.
+- `Molecular View`: render 2D and 3D molecular structures and export structure assets.
+- `Discovery (Manual)`: perform explicit constraint-based and multi-objective polymer screening.
+- `Discovery (AI)`: translate natural-language design requests into structured discovery settings with bring-your-own-key LLM support.
+- `Novel SMILES Generation`: sample new polymer candidates with the pretrained RNN and filter against local datasets.
+- `Feedback`: submit issue reports and feature requests through a webhook-backed form.
+
+## Core Capabilities
+
+- Multi-source property lookup from `EXP`, `MD`, `DFT`, `GC`, and `POLYINFO`
+- Property prediction across 28 polymer properties
+- Large-scale screening over real and virtual candidate libraries
+- Exact Pareto ranking with trust and diversity-aware selection
+- AI-assisted prompt-to-spec generation for discovery workflows
+- Novelty-filtered polymer SMILES generation
+- ADEPT handoff for downstream molecular dynamics workflow packaging
+
+## Repository Layout
+
+```text
+.
+├── Home.py                      # Main Streamlit homepage
+├── app.py                       # Compatibility entrypoint
+├── pages/                       # User-facing application modules
+├── src/                         # Prediction, discovery, lookup, and UI logic
+├── literature/                  # Literature-mining pipeline components
+├── scripts/                     # Utility and workflow scripts
+├── data/                        # Lookup tables, discovery datasets, ADEPT files
+├── models/                      # Trained prediction and generation assets
+├── RNN/                         # Generator training/inference code
+└── icons/                       # Application icons and branding assets
+```
+
+## Data And Model Assets
+
+This repository expects pretrained models and local data tables to be present. The application uses:
+
+- source datasets such as `EXP.csv`, `MD.csv`, `DFT.csv`, `GC.csv`, `POLYINFO.csv`, and `PI1M.csv`
+- derived property tables such as `POLYINFO_PROPERTY.parquet` and `PI1M_PROPERTY.parquet`
+- trained checkpoint files under `models/`
+- pretrained RNN assets under `RNN/pretrained_model/` and `models/rnn/pretrained_model/`
+
+If you clone only the code without the large assets, several app modules will not run correctly.
+
+## Local Development
+
+Use Python `3.10`.
+
+```bash
+python3 -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+streamlit run Home.py
+```
+
+Open `http://localhost:8501`.
+
+## Optional Literature Pipeline Dependencies
+
+The literature workflow is separated from the main app dependencies.
+
+```bash
+pip install -r requirements-literature.txt
+```
+
+This is only required if you plan to use or extend the literature-mining workflow.
+
+## Environment Configuration
+
+Create a local `.env` file if needed. The template is provided in `.env.example`.
+
+Key variables used by the platform include:
+
+### LLM / Discovery AI
+
+- `CRC_OPENWEBUI_API_KEY`
+- `OPENWEBUI_API_KEY`
+- `OPENAI_API_KEY`
+- `CRC_OPENWEBUI_BASE_URL`
+- `OPENWEBUI_BASE_URL`
+- `CRC_OPENWEBUI_MODEL`
+- `OPENWEBUI_MODEL`
+- `OPENAI_MODEL`
+
+The Discovery AI page also supports direct bring-your-own-key usage against supported providers from the UI.
+
+### Literature Pipeline
+
+- `PUBMED_EMAIL`
+- `PUBMED_API_KEY`
+- `SEMANTIC_SCHOLAR_API_KEY`
+- `PAGEINDEX_API_KEY`
+- `LITERATURE_MODEL_OPTIONS`
+
+### Feedback / Analytics
+
+- `FEEDBACK_WEBHOOK_URL`
+- `FEEDBACK_WEBHOOK_TOKEN`
+- `APP_DEPLOYMENT_SOURCE`
+
+## Running With Docker
+
+```bash
+docker build -t polymer-discovery .
+docker run --rm -p 8501:8501 polymer-discovery
+```
+
+The container launches:
+
+```bash
+streamlit run Home.py --server.port=8501 --server.address=0.0.0.0 --server.headless=true
+```
+
+## Notes For Deployment
+
+- The app is designed as a Streamlit website.
+- Heavy modules depend on local datasets and pretrained checkpoints being available at the expected paths.
+- The AI-assisted discovery page requires a valid API key when using in-app LLM generation.
+- The feedback page requires a configured webhook to receive submissions.
+
+## Citation And Use
+
+If you use this platform in research or build on top of it, cite the associated paper once published. Until then, reference the repository and the MONSTER Lab platform description.

app.py

@@ -0,0 +1,7 @@
+"""Compatibility entrypoint.
+
+Keeps legacy `streamlit run app.py` working by delegating to the actual
+homepage implementation in `Home.py`.
+"""
+
+from Home import *  # noqa: F401,F403