Move the PDC release into CupOFMoCA-PDC/

Reorganise the repository into one folder per conjugate modality so the PROTAC release can sit beside the PDC one under the same citation URL.

Checkpoints are copied server-side rather than re-uploaded. .gitattributes stays at the root so its LFS rules apply to both trees.

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 assets/CupOFMoCA.gif filter=lfs diff=lfs merge=lfs -text
+CupOFMoCA-PDC/assets/CupOFMoCA.gif filter=lfs diff=lfs merge=lfs -text

CupOFMoCA-PDC/README.md

@@ -0,0 +1,228 @@
+---
+license: apache-2.0
+library_name: pytorch
+tags:
+  - chemistry
+  - drug-discovery
+  - molecular-generation
+  - peptide
+  - discrete-flow
+  - peptide-drug-conjugate
+---
+
+# CupOFMoCA
+
+Code and PDC model artifacts for **CupOFMoCA: Coupled Objective-Guided Discrete Flows for
+Molecular Conjugate Assembly** (NeurIPS 2026).
+
+CupOFMoCA performs coupled, objective-guided discrete-flow generation while enforcing chemical
+assembly constraints. This release supports the paper's peptide-drug conjugate (PDC) experiments
+across SMILES, natural amino-acid (AA), and unnatural amino-acid (UAA) representations.
+
+## Model overview
+
+![CupOFMoCA overview](assets/CupOFMoCA.gif)
+
+CupOFMoCA is a research pipeline for generating peptide-drug conjugate candidates. It couples a
+pretrained discrete-flow generator with property guidance and conjugation-validity checks during
+sampling. This repository contains three generator checkpoints and the property scorers used by the
+released PDC pipeline:
+
+| Checkpoint | Representation | Role |
+|---|---|---|
+| `SMILESReDi_base.ckpt` | peptide SMILES | pretrained SMILES discrete-flow generator |
+| `PepReDi_base.pt` | canonical amino acids | pretrained AA discrete-flow generator |
+| `UAAReDi_base.pt` | extended amino-acid vocabulary | pretrained UAA discrete-flow generator |
+
+The checkpoints are loaded by the repository's custom PyTorch code; this is not a Transformers
+pipeline and does not provide a hosted-inference widget.
+
+### Intended uses
+
+- Reproduce and inspect the paper's PDC generation experiments.
+- Generate computational PDC candidates for research and method development.
+- Extend or compare constrained, multi-objective molecular-generation methods.
+
+The release is not intended for clinical decisions, direct therapeutic use, or as a substitute for
+chemical synthesis, experimental validation, toxicology, or safety assessment.
+
+### Training data
+
+- **AA-PepReDi:** peptides from PepNN and BioLip2, together with 6--49-residue sequences from
+  PPIRef, using an 80:10:10 train/validation/test split.
+- **UAA-PepReDi:** 150,000 synthetic sequences constructed with `p2smi` across combinations of
+  non-canonical and D-amino-acid composition, using an 80:10:10 split.
+- **SMILESReDi:** the released pretrained SMILESReDi weights are used without additional
+  CupOFMoCA fine-tuning.
+
+Architecture, optimization, data construction, and scorer details are reported in Appendix E of
+the paper. Training datasets are not redistributed in this repository.
+
+### Evaluation
+
+The paper evaluates generated PDCs for assembly validity and predicted functional properties across
+ERBB2, GNRHR, and NRP1, using SMILES, AA, and UAA representations. The reported results and
+experimental protocol are in the paper; the submitted evaluation routines are included under
+`smiles/evaluation/`.
+
+### Limitations
+
+- Outputs and objective values are computational predictions, not experimentally validated
+  compounds or guarantees of efficacy, synthesizability, toxicity, or safety.
+- The released configurations cover three receptor targets and fixed target-specific conjugation
+  chemistries; performance outside this scope has not been established.
+- The release contains the paper's PDC stack only. Its PROTAC experiments require separate code and
+  artifacts.
+- Results can vary with hardware, CUDA/PyTorch versions, and revisions of models downloaded at
+  runtime.
+
+## Repository layout
+
+```text
+checkpoints/                 generator weights
+configs/                     paper settings and target sequences
+docs/                        model-artifact details and checksums
+scripts/run_experiment.py    unified experiment runner
+scripts/verify_release.py    release integrity checker
+smiles/
+  generation/               generation entry points
+  evaluation/               metrics and analyzers
+  models/                   ReDi model and data code
+  conjugation/              PDC assembly builders
+  scoring/                  property scorers
+  smiles_tokenizer/         tokenizer code and vocabulary
+third_party/                 peptide-to-SMILES conversion helper
+```
+
+The release currently covers the PDC implementation. The PROTAC experiments described in the paper
+use a separate code and artifact stack that is not included here.
+
+## 1. Environment
+
+A CUDA GPU is strongly recommended. The tested environment used Python 3.9, PyTorch 2.5.1, and
+CUDA 12.1.
+
+```bash
+conda env create -f environment.yml
+conda activate cupofmoca
+```
+
+Alternatively, install a PyTorch build appropriate for your CUDA driver and then install the pinned
+packages:
+
+```bash
+pip install -r requirements.txt
+```
+
+On first use, Transformers downloads `facebook/esm2_t33_650M_UR50D` and
+`aaronfeller/PeptideCLM-23M-all` from Hugging Face. Set `HF_HOME` to a persistent cache if needed.
+
+Verify the bundled artifacts and source paths before running an experiment:
+
+```bash
+python scripts/verify_release.py
+```
+
+## 2. Run PDC generation
+
+Run commands from the repository root. Preview a configured command without loading models:
+
+```bash
+python scripts/run_experiment.py \
+  --representation uaa \
+  --variant cupofmoca \
+  --method guided \
+  --target NRP1 \
+  --dry-run
+```
+
+Run the experiment:
+
+```bash
+python scripts/run_experiment.py \
+  --representation uaa \
+  --variant cupofmoca \
+  --method guided \
+  --target NRP1
+```
+
+Run a small smoke test:
+
+```bash
+python scripts/run_experiment.py \
+  --representation aa --variant baseline --method staged --target ERBB2 \
+  --num-candidates 1
+```
+
+Outputs are written under `outputs/` in separate run directories. Existing outputs are protected
+unless `--force` is supplied. Arguments after `--` are passed to the underlying generator:
+
+```bash
+python scripts/run_experiment.py \
+  --representation smiles --variant cupofmoca --method guided --target GNRHR \
+  -- --top_k 100
+```
+
+### Configurations
+
+| Target | Protein | Conjugation builder | Default SMILES length |
+|---|---|---|---:|
+| ERBB2 | receptor tyrosine-protein kinase erbB-2 | `SSCpt` | 80 |
+| GNRHR | gonadotropin-releasing hormone receptor | `AoaDau` | 80 |
+| NRP1 | neuropilin-1 | `DSPASN38` | 100 |
+
+AA and UAA runs use length 10. Shared settings include 128 optimization steps, top-p 1.0,
+objective weights `[1, 1]`, and acceptance sampling with beta 50 for CupOFMoCA. The machine-readable
+configuration is in `configs/paper.json`; target sequences are in `configs/targets.fasta`.
+
+### Direct entry points
+
+The full argument surfaces remain available under `smiles/generation/`:
+
+```text
+guided.py                   cupofmoca_guided.py
+guided_aa.py                cupofmoca_guided_aa.py
+guided_uaa.py               cupofmoca_guided_uaa.py
+staged.py                   cupofmoca_staged.py
+staged_aa.py                cupofmoca_staged_aa.py
+staged_uaa.py               cupofmoca_staged_uaa.py
+```
+
+Run one directly as a module, for example:
+
+```bash
+python -m smiles.generation.cupofmoca_guided_uaa --help
+```
+
+`smiles/evaluation/run_metrics.py` and `smiles/evaluation/run_metrics_uaa.py` contain the submitted evaluation routines.
+Use `python <file> --help` to inspect their arguments.
+
+## 3. Included checkpoints
+
+The release includes the SMILES, AA, and UAA generator weights together with the binding,
+hemolysis, non-fouling, and solubility scorers needed by the PDC pipeline. Artifact roles, sizes, and
+SHA-256 values are listed in [docs/ARTIFACTS.md](docs/ARTIFACTS.md).
+
+The AA-input affinity predictor is not included because the PDC generation configuration uses the
+bundled SMILES-input scorer (`--affinity_type smiles`).
+
+Large `*.pt` and `*.ckpt` files are configured for Git LFS. The repository is approximately 1.9 GB
+before environment and model-cache downloads.
+
+The checkpoint formats are loaded through PyTorch. As with any pickle-backed PyTorch artifact,
+only load weights obtained from a source you trust.
+
+## 4. Notes
+
+- The paper reports NVIDIA RTX A6000 48 GB GPUs. Lower-memory devices may require smaller batches.
+- Exact bitwise output can vary across CUDA, PyTorch, GPU, and downloaded model revisions.
+- Generated structures are computational hypotheses that require experimental validation. Property
+  models are predictors, not clinical or safety guarantees.
+- The peptide-to-SMILES helper used by the experiments is vendored under `third_party/` with its
+  upstream license notice.
+
+## 5. Citation and license
+
+Citation metadata is provided in `CITATION.cff`. The repository code is released under Apache-2.0;
+see `LICENSE` and `NOTICE`. Third-party components and downloaded model artifacts retain their
+respective terms.