A guide for active learning in synergistic drug discovery
Abstract Synergistic drug combination screening is a promising strategy in drug discovery, but it involves navigating a costly and complex search space. While AI, particularly deep learning, has advanced synergy predictions, its effectiveness is limited by the low occurrence of synergistic drug pair...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-85600-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571731326271488 |
|---|---|
| author | Shuhui Wang Alexandre Allauzen Philippe Nghe Vaitea Opuu |
| author_facet | Shuhui Wang Alexandre Allauzen Philippe Nghe Vaitea Opuu |
| author_sort | Shuhui Wang |
| collection | DOAJ |
| description | Abstract Synergistic drug combination screening is a promising strategy in drug discovery, but it involves navigating a costly and complex search space. While AI, particularly deep learning, has advanced synergy predictions, its effectiveness is limited by the low occurrence of synergistic drug pairs. Active learning, which integrates experimental testing into the learning process, has been proposed to address this challenge. In this work, we explore the key components of active learning to provide recommendations for its implementation. We find that molecular encoding has a limited impact on performance, while the cellular environment features significantly enhance predictions. Additionally, active learning can discover 60% of synergistic drug pairs with only exploring 10% of combinatorial space. The synergy yield ratio is observed to be even higher with smaller batch sizes, where dynamic tuning of the exploration-exploitation strategy can further enhance performance. The code can be found at https://github.com/LBiophyEvo/DrugSynergy |
| format | Article |
| id | doaj-art-731a77b52a8b49eda4af2ae0a3d46939 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-731a77b52a8b49eda4af2ae0a3d469392025-02-02T12:22:53ZengNature PortfolioScientific Reports2045-23222025-01-0115111610.1038/s41598-025-85600-3A guide for active learning in synergistic drug discoveryShuhui Wang0Alexandre Allauzen1Philippe Nghe2Vaitea Opuu3Laboratoire de Biophysique et Evolution, UMR CNRS-ESPCI 8231 Chimie Biologie Innovation, PSL UniversityLaboratoire de Biophysique et Evolution, UMR CNRS-ESPCI 8231 Chimie Biologie Innovation, PSL UniversityLaboratoire de Biophysique et Evolution, UMR CNRS-ESPCI 8231 Chimie Biologie Innovation, PSL UniversityLaboratoire de Biophysique et Evolution, UMR CNRS-ESPCI 8231 Chimie Biologie Innovation, PSL UniversityAbstract Synergistic drug combination screening is a promising strategy in drug discovery, but it involves navigating a costly and complex search space. While AI, particularly deep learning, has advanced synergy predictions, its effectiveness is limited by the low occurrence of synergistic drug pairs. Active learning, which integrates experimental testing into the learning process, has been proposed to address this challenge. In this work, we explore the key components of active learning to provide recommendations for its implementation. We find that molecular encoding has a limited impact on performance, while the cellular environment features significantly enhance predictions. Additionally, active learning can discover 60% of synergistic drug pairs with only exploring 10% of combinatorial space. The synergy yield ratio is observed to be even higher with smaller batch sizes, where dynamic tuning of the exploration-exploitation strategy can further enhance performance. The code can be found at https://github.com/LBiophyEvo/DrugSynergyhttps://doi.org/10.1038/s41598-025-85600-3 |
| spellingShingle | Shuhui Wang Alexandre Allauzen Philippe Nghe Vaitea Opuu A guide for active learning in synergistic drug discovery Scientific Reports |
| title | A guide for active learning in synergistic drug discovery |
| title_full | A guide for active learning in synergistic drug discovery |
| title_fullStr | A guide for active learning in synergistic drug discovery |
| title_full_unstemmed | A guide for active learning in synergistic drug discovery |
| title_short | A guide for active learning in synergistic drug discovery |
| title_sort | guide for active learning in synergistic drug discovery |
| url | https://doi.org/10.1038/s41598-025-85600-3 |
| work_keys_str_mv | AT shuhuiwang aguideforactivelearninginsynergisticdrugdiscovery AT alexandreallauzen aguideforactivelearninginsynergisticdrugdiscovery AT philippenghe aguideforactivelearninginsynergisticdrugdiscovery AT vaiteaopuu aguideforactivelearninginsynergisticdrugdiscovery AT shuhuiwang guideforactivelearninginsynergisticdrugdiscovery AT alexandreallauzen guideforactivelearninginsynergisticdrugdiscovery AT philippenghe guideforactivelearninginsynergisticdrugdiscovery AT vaiteaopuu guideforactivelearninginsynergisticdrugdiscovery |