Enregistré dans:
Détails bibliographiques
Auteur principal: Agarwal, Arjun
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