RGFN: Synthesizable Molecular Generation Using GFlowNets
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912107888377856 |
|---|---|
| author | Koziarski, Michał Rekesh, Andrei Shevchuk, Dmytro van der Sloot, Almer Gaiński, Piotr Bengio, Yoshua Liu, Cheng-Hao Tyers, Mike Batey, Robert A. |
| author_facet | Koziarski, Michał Rekesh, Andrei Shevchuk, Dmytro van der Sloot, Almer Gaiński, Piotr Bengio, Yoshua Liu, Cheng-Hao Tyers, Mike Batey, Robert A. |
| contents | Generative models hold great promise for small molecule discovery, significantly increasing the size of search space compared to traditional in silico screening libraries. However, most existing machine learning methods for small molecule generation suffer from poor synthesizability of candidate compounds, making experimental validation difficult. In this paper we propose Reaction-GFlowNet (RGFN), an extension of the GFlowNet framework that operates directly in the space of chemical reactions, thereby allowing out-of-the-box synthesizability while maintaining comparable quality of generated candidates. We demonstrate that with the proposed set of reactions and building blocks, it is possible to obtain a search space of molecules orders of magnitude larger than existing screening libraries coupled with low cost of synthesis. We also show that the approach scales to very large fragment libraries, further increasing the number of potential molecules. We demonstrate the effectiveness of the proposed approach across a range of oracle models, including pretrained proxy models and GPU-accelerated docking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08506 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RGFN: Synthesizable Molecular Generation Using GFlowNets Koziarski, Michał Rekesh, Andrei Shevchuk, Dmytro van der Sloot, Almer Gaiński, Piotr Bengio, Yoshua Liu, Cheng-Hao Tyers, Mike Batey, Robert A. Chemical Physics Machine Learning Biomolecules Generative models hold great promise for small molecule discovery, significantly increasing the size of search space compared to traditional in silico screening libraries. However, most existing machine learning methods for small molecule generation suffer from poor synthesizability of candidate compounds, making experimental validation difficult. In this paper we propose Reaction-GFlowNet (RGFN), an extension of the GFlowNet framework that operates directly in the space of chemical reactions, thereby allowing out-of-the-box synthesizability while maintaining comparable quality of generated candidates. We demonstrate that with the proposed set of reactions and building blocks, it is possible to obtain a search space of molecules orders of magnitude larger than existing screening libraries coupled with low cost of synthesis. We also show that the approach scales to very large fragment libraries, further increasing the number of potential molecules. We demonstrate the effectiveness of the proposed approach across a range of oracle models, including pretrained proxy models and GPU-accelerated docking. |
| title | RGFN: Synthesizable Molecular Generation Using GFlowNets |
| topic | Chemical Physics Machine Learning Biomolecules |
| url | https://arxiv.org/abs/2406.08506 |