Retrosynthetic Planning with Dual Value Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916144045096960 |
|---|---|
| author | Liu, Guoqing Xue, Di Xie, Shufang Xia, Yingce Tripp, Austin Maziarz, Krzysztof Segler, Marwin Qin, Tao Zhang, Zongzhang Liu, Tie-Yan |
| author_facet | Liu, Guoqing Xue, Di Xie, Shufang Xia, Yingce Tripp, Austin Maziarz, Krzysztof Segler, Marwin Qin, Tao Zhang, Zongzhang Liu, Tie-Yan |
| contents | Retrosynthesis, which aims to find a route to synthesize a target molecule from commercially available starting materials, is a critical task in drug discovery and materials design. Recently, the combination of ML-based single-step reaction predictors with multi-step planners has led to promising results. However, the single-step predictors are mostly trained offline to optimize the single-step accuracy, without considering complete routes. Here, we leverage reinforcement learning (RL) to improve the single-step predictor, by using a tree-shaped MDP to optimize complete routes. Specifically, we propose a novel online training algorithm, called Planning with Dual Value Networks (PDVN), which alternates between the planning phase and updating phase. In PDVN, we construct two separate value networks to predict the synthesizability and cost of molecules, respectively. To maintain the single-step accuracy, we design a two-branch network structure for the single-step predictor. On the widely-used USPTO dataset, our PDVN algorithm improves the search success rate of existing multi-step planners (e.g., increasing the success rate from 85.79% to 98.95% for Retro*, and reducing the number of model calls by half while solving 99.47% molecules for RetroGraph). Additionally, PDVN helps find shorter synthesis routes (e.g., reducing the average route length from 5.76 to 4.83 for Retro*, and from 5.63 to 4.78 for RetroGraph). Our code is available at \url{https://github.com/DiXue98/PDVN}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2301_13755 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Retrosynthetic Planning with Dual Value Networks Liu, Guoqing Xue, Di Xie, Shufang Xia, Yingce Tripp, Austin Maziarz, Krzysztof Segler, Marwin Qin, Tao Zhang, Zongzhang Liu, Tie-Yan Artificial Intelligence Machine Learning Retrosynthesis, which aims to find a route to synthesize a target molecule from commercially available starting materials, is a critical task in drug discovery and materials design. Recently, the combination of ML-based single-step reaction predictors with multi-step planners has led to promising results. However, the single-step predictors are mostly trained offline to optimize the single-step accuracy, without considering complete routes. Here, we leverage reinforcement learning (RL) to improve the single-step predictor, by using a tree-shaped MDP to optimize complete routes. Specifically, we propose a novel online training algorithm, called Planning with Dual Value Networks (PDVN), which alternates between the planning phase and updating phase. In PDVN, we construct two separate value networks to predict the synthesizability and cost of molecules, respectively. To maintain the single-step accuracy, we design a two-branch network structure for the single-step predictor. On the widely-used USPTO dataset, our PDVN algorithm improves the search success rate of existing multi-step planners (e.g., increasing the success rate from 85.79% to 98.95% for Retro*, and reducing the number of model calls by half while solving 99.47% molecules for RetroGraph). Additionally, PDVN helps find shorter synthesis routes (e.g., reducing the average route length from 5.76 to 4.83 for Retro*, and from 5.63 to 4.78 for RetroGraph). Our code is available at \url{https://github.com/DiXue98/PDVN}. |
| title | Retrosynthetic Planning with Dual Value Networks |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2301.13755 |