Hermes: Large DEL Datasets Train Generalizable Protein-Ligand Binding Prediction Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910022098747392 |
|---|---|
| author | Kleinsasser, Maxwell Halverson, Brayden J. Kraft, Edward Francis-Lyon, Sean Hugo, Sarah E. Roman, Mackenzie R. Miller, Ben Blevins, Andrew D. Quigley, Ian K. |
| author_facet | Kleinsasser, Maxwell Halverson, Brayden J. Kraft, Edward Francis-Lyon, Sean Hugo, Sarah E. Roman, Mackenzie R. Miller, Ben Blevins, Andrew D. Quigley, Ian K. |
| contents | The quality and consistency of training data remain critical bottlenecks for protein-ligand binding prediction. Public affinity datasets, aggregated from thousands of labs and assay formats, introduce biases that limit model generalization and complicate evaluation. DNA-encoded chemical libraries (DELs) offer a potential solution: unified experimental protocols generating massive binding datasets across diverse chemical and protein target space. We present Hermes, a lightweight transformer trained exclusively on DEL data from screens against hundreds of protein targets, representing one of the largest and most protein-diverse DEL training sets applied to protein-ligand interaction (PLI) modeling to date. Despite never seeing traditional affinity measurements during training, Hermes generalizes to held-out targets, novel chemical scaffolds, and external benchmarks derived from public binding data and high-throughput screens. Our results demonstrate that DEL data alone captures transferable protein-ligand interaction representations, while Hermes' minimal architecture enables inference speeds suitable for large-scale virtual screening. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13503 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hermes: Large DEL Datasets Train Generalizable Protein-Ligand Binding Prediction Models Kleinsasser, Maxwell Halverson, Brayden J. Kraft, Edward Francis-Lyon, Sean Hugo, Sarah E. Roman, Mackenzie R. Miller, Ben Blevins, Andrew D. Quigley, Ian K. Biomolecules The quality and consistency of training data remain critical bottlenecks for protein-ligand binding prediction. Public affinity datasets, aggregated from thousands of labs and assay formats, introduce biases that limit model generalization and complicate evaluation. DNA-encoded chemical libraries (DELs) offer a potential solution: unified experimental protocols generating massive binding datasets across diverse chemical and protein target space. We present Hermes, a lightweight transformer trained exclusively on DEL data from screens against hundreds of protein targets, representing one of the largest and most protein-diverse DEL training sets applied to protein-ligand interaction (PLI) modeling to date. Despite never seeing traditional affinity measurements during training, Hermes generalizes to held-out targets, novel chemical scaffolds, and external benchmarks derived from public binding data and high-throughput screens. Our results demonstrate that DEL data alone captures transferable protein-ligand interaction representations, while Hermes' minimal architecture enables inference speeds suitable for large-scale virtual screening. |
| title | Hermes: Large DEL Datasets Train Generalizable Protein-Ligand Binding Prediction Models |
| topic | Biomolecules |
| url | https://arxiv.org/abs/2602.13503 |