RLSynC: Offline-Online Reinforcement Learning for Synthon Completion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916184075534336 |
|---|---|
| author | Baker, Frazier N. Chen, Ziqi Adu-Ampratwum, Daniel Ning, Xia |
| author_facet | Baker, Frazier N. Chen, Ziqi Adu-Ampratwum, Daniel Ning, Xia |
| contents | Retrosynthesis is the process of determining the set of reactant molecules that can react to form a desired product. Semi-template-based retrosynthesis methods, which imitate the reverse logic of synthesis reactions, first predict the reaction centers in the products, and then complete the resulting synthons back into reactants. We develop a new offline-online reinforcement learning method RLSynC for synthon completion in semi-template-based methods. RLSynC assigns one agent to each synthon, all of which complete the synthons by conducting actions step by step in a synchronized fashion. RLSynC learns the policy from both offline training episodes and online interactions, which allows RLSynC to explore new reaction spaces. RLSynC uses a standalone forward synthesis model to evaluate the likelihood of the predicted reactants in synthesizing a product, and thus guides the action search. Our results demonstrate that RLSynC can outperform state-of-the-art synthon completion methods with improvements as high as 14.9%, highlighting its potential in synthesis planning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_02671 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | RLSynC: Offline-Online Reinforcement Learning for Synthon Completion Baker, Frazier N. Chen, Ziqi Adu-Ampratwum, Daniel Ning, Xia Machine Learning Artificial Intelligence Retrosynthesis is the process of determining the set of reactant molecules that can react to form a desired product. Semi-template-based retrosynthesis methods, which imitate the reverse logic of synthesis reactions, first predict the reaction centers in the products, and then complete the resulting synthons back into reactants. We develop a new offline-online reinforcement learning method RLSynC for synthon completion in semi-template-based methods. RLSynC assigns one agent to each synthon, all of which complete the synthons by conducting actions step by step in a synchronized fashion. RLSynC learns the policy from both offline training episodes and online interactions, which allows RLSynC to explore new reaction spaces. RLSynC uses a standalone forward synthesis model to evaluate the likelihood of the predicted reactants in synthesizing a product, and thus guides the action search. Our results demonstrate that RLSynC can outperform state-of-the-art synthon completion methods with improvements as high as 14.9%, highlighting its potential in synthesis planning. |
| title | RLSynC: Offline-Online Reinforcement Learning for Synthon Completion |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2309.02671 |