Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Recurso digital |
| Langue: | anglais |
| Publié: |
Zenodo
2026
|
| Sujets: | |
| Accès en ligne: | https://doi.org/10.5281/zenodo.19946459 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866901555148488704 |
|---|---|
| author | Agarwal, Arjun |
| author_facet | Agarwal, Arjun |
| contents | <p>Trained model checkpoints, normalization statistics, fitted ensemble stacker,<br>and preprocessed graph cache supporting the HIV bioactivity prediction<br>preprint by Agarwal (2026).</p> <p>Contents:<br>- best_molformer_fold{0..4}.pth: Five MolFormer-XL checkpoints fine-tuned<br> on MoleculeNet HIV scaffold-CV folds. Each ~170 MB.<br>- best_gnn_fold{0..4}_v5_desc.pth: Five GATv2-based GNN ("v5b") checkpoints<br> trained from scratch on the same folds.<br>- global_feature_stats_v5_desc_fold{0..4}.pt: Per-fold means/stds for the<br> RDKit global descriptors (z-score normalization).<br>- ensemble_stacker.pt: Logistic stacker coefficients, three principled<br> decision thresholds (Youden's J / F1-max / base-rate), and raw out-of-<br> fold prediction arrays for n=24,391 molecules.<br>- hiv_preprocessed_cache_v5_desc.pt: 41,119 RDKit-parsed molecules as<br> PyTorch Geometric Data objects with atom features (23-dim), bond features<br> (8-dim), global descriptors, and Bemis-Murcko scaffolds. Reproduces the<br> exact deterministic 5-fold scaffold split used in training.</p> <p>These artifacts reproduce the headline test AUC of 0.806 ± 0.018 on the<br>MoleculeNet HIV scaffold-split benchmark. Source code is at<br>https://github.com/v659/HIV-drug-discovery.</p> <p>License: MIT (matches the source repository).</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19946459 |
| institution | Zenodo |
| language | eng |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Trained checkpoints and preprocessed data for "Closing the gap on a $0 budget: ensembling public molecular foundation models for HIV bioactivity prediction" Agarwal, Arjun molecular property prediction MoleculeNet HIV graph neural networks MolFormer-XL ensemble learning scaffold splits drug discovery low-resource ML <p>Trained model checkpoints, normalization statistics, fitted ensemble stacker,<br>and preprocessed graph cache supporting the HIV bioactivity prediction<br>preprint by Agarwal (2026).</p> <p>Contents:<br>- best_molformer_fold{0..4}.pth: Five MolFormer-XL checkpoints fine-tuned<br> on MoleculeNet HIV scaffold-CV folds. Each ~170 MB.<br>- best_gnn_fold{0..4}_v5_desc.pth: Five GATv2-based GNN ("v5b") checkpoints<br> trained from scratch on the same folds.<br>- global_feature_stats_v5_desc_fold{0..4}.pt: Per-fold means/stds for the<br> RDKit global descriptors (z-score normalization).<br>- ensemble_stacker.pt: Logistic stacker coefficients, three principled<br> decision thresholds (Youden's J / F1-max / base-rate), and raw out-of-<br> fold prediction arrays for n=24,391 molecules.<br>- hiv_preprocessed_cache_v5_desc.pt: 41,119 RDKit-parsed molecules as<br> PyTorch Geometric Data objects with atom features (23-dim), bond features<br> (8-dim), global descriptors, and Bemis-Murcko scaffolds. Reproduces the<br> exact deterministic 5-fold scaffold split used in training.</p> <p>These artifacts reproduce the headline test AUC of 0.806 ± 0.018 on the<br>MoleculeNet HIV scaffold-split benchmark. Source code is at<br>https://github.com/v659/HIV-drug-discovery.</p> <p>License: MIT (matches the source repository).</p> |
| title | Trained checkpoints and preprocessed data for "Closing the gap on a $0 budget: ensembling public molecular foundation models for HIV bioactivity prediction" |
| topic | molecular property prediction MoleculeNet HIV graph neural networks MolFormer-XL ensemble learning scaffold splits drug discovery low-resource ML |
| url | https://doi.org/10.5281/zenodo.19946459 |