Active Learning on Synthons for Molecular Design
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918025134866432 |
|---|---|
| author | Grigg, Tom George Burlage, Mason Scott, Oliver Brook Taouil, Adam Sydow, Dominique Wilbraham, Liam |
| author_facet | Grigg, Tom George Burlage, Mason Scott, Oliver Brook Taouil, Adam Sydow, Dominique Wilbraham, Liam |
| contents | Exhaustive virtual screening is highly informative but often intractable against the expensive objective functions involved in modern drug discovery. This problem is exacerbated in combinatorial contexts such as multi-vector expansion, where molecular spaces can quickly become ultra-large. Here, we introduce Scalable Active Learning via Synthon Acquisition (SALSA): a simple algorithm applicable to multi-vector expansion which extends pool-based active learning to non-enumerable spaces by factoring modeling and acquisition over synthon or fragment choices. Through experiments on ligand- and structure-based objectives, we highlight SALSA's sample efficiency, and its ability to scale to spaces of trillions of compounds. Further, we demonstrate application toward multi-parameter objective design tasks on three protein targets - finding SALSA-generated molecules have comparable chemical property profiles to known bioactives, and exhibit greater diversity and higher scores over an industry-leading generative approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_12913 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Active Learning on Synthons for Molecular Design Grigg, Tom George Burlage, Mason Scott, Oliver Brook Taouil, Adam Sydow, Dominique Wilbraham, Liam Machine Learning Quantitative Methods Exhaustive virtual screening is highly informative but often intractable against the expensive objective functions involved in modern drug discovery. This problem is exacerbated in combinatorial contexts such as multi-vector expansion, where molecular spaces can quickly become ultra-large. Here, we introduce Scalable Active Learning via Synthon Acquisition (SALSA): a simple algorithm applicable to multi-vector expansion which extends pool-based active learning to non-enumerable spaces by factoring modeling and acquisition over synthon or fragment choices. Through experiments on ligand- and structure-based objectives, we highlight SALSA's sample efficiency, and its ability to scale to spaces of trillions of compounds. Further, we demonstrate application toward multi-parameter objective design tasks on three protein targets - finding SALSA-generated molecules have comparable chemical property profiles to known bioactives, and exhibit greater diversity and higher scores over an industry-leading generative approach. |
| title | Active Learning on Synthons for Molecular Design |
| topic | Machine Learning Quantitative Methods |
| url | https://arxiv.org/abs/2505.12913 |