Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.00802 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915528345387008 |
|---|---|
| author | Milon-Harnois, Gaelle Touhami, Chaimaa Gutowski, Nicolas Da Mota, Benoit Cauchy, Thomas |
| author_facet | Milon-Harnois, Gaelle Touhami, Chaimaa Gutowski, Nicolas Da Mota, Benoit Cauchy, Thomas |
| contents | The efficient exploration of chemical space remains a central challenge, as many generative models still produce unstable or non-synthesizable compounds. To address these limitations, we present EvoMol-RL, a significant extension of the EvoMol evolutionary algorithm that integrates reinforcement learning to guide molecular mutations based on local structural context. By leveraging Extended Connectivity Fingerprints (ECFPs), EvoMol-RL learns context-aware mutation policies that prioritize chemically plausible transformations. This approach significantly improves the generation of valid and realistic molecules, reducing the frequency of structural artifacts and enhancing optimization performance. The results demonstrate that EvoMol-RL consistently outperforms its baseline in molecular pre-filtering realism. These results emphasize the effectiveness of combining reinforcement learning with molecular fingerprints to generate chemically relevant molecular structures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00802 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Guiding Evolutionary Molecular Design: Adding Reinforcement Learning for Mutation Selection Milon-Harnois, Gaelle Touhami, Chaimaa Gutowski, Nicolas Da Mota, Benoit Cauchy, Thomas Machine Learning The efficient exploration of chemical space remains a central challenge, as many generative models still produce unstable or non-synthesizable compounds. To address these limitations, we present EvoMol-RL, a significant extension of the EvoMol evolutionary algorithm that integrates reinforcement learning to guide molecular mutations based on local structural context. By leveraging Extended Connectivity Fingerprints (ECFPs), EvoMol-RL learns context-aware mutation policies that prioritize chemically plausible transformations. This approach significantly improves the generation of valid and realistic molecules, reducing the frequency of structural artifacts and enhancing optimization performance. The results demonstrate that EvoMol-RL consistently outperforms its baseline in molecular pre-filtering realism. These results emphasize the effectiveness of combining reinforcement learning with molecular fingerprints to generate chemically relevant molecular structures. |
| title | Guiding Evolutionary Molecular Design: Adding Reinforcement Learning for Mutation Selection |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.00802 |