Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search

Retrosynthetic planning is a critical task in organic chemistry which identifies a series of reactions that can lead to the synthesis of a target product. The vast number of possible chemical transformations makes the size of the search space very big, and retrosynthetic planning is challenging even for experienced chemists. However, existing methods either require expensive return estimation by rollout with high variance, or optimize for search speed rather than the quality. In this paper, we propose Retro*, a neural-based A*-like algorithm that finds high-quality synthetic routes efficiently. It maintains the search as an AND-OR tree, and learns a neural search bias with off-policy data. Then guided by this neural network, it performs best-first search efficiently during new planning episodes. Experiments on benchmark USPTO datasets show that, our proposed method outperforms existing state-of-the-art with respect to both the success rate and solution quality, while being more efficient at the same time.

[1]  Akihiro Kishimoto,et al.  Depth-First Proof-Number Search with Heuristic Edge Cost and Application to Chemical Synthesis Planning , 2019, NeurIPS.

[2]  Csaba Szepesvári,et al.  Bandit Based Monte-Carlo Planning , 2006, ECML.

[3]  Le Song,et al.  Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees , 2020, ICLR.

[4]  Marwin H. S. Segler,et al.  Neural-Symbolic Machine Learning for Retrosynthesis and Reaction Prediction. , 2017, Chemistry.

[5]  Mike Preuss,et al.  Towards "AlphaChem": Chemical Synthesis Planning with Tree Search and Deep Neural Network Policies , 2017, ICLR.

[6]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[7]  H. Jaap van den Herik,et al.  Proof-Number Search , 1994, Artif. Intell..

[8]  Mike Preuss,et al.  Planning chemical syntheses with deep neural networks and symbolic AI , 2017, Nature.

[9]  John S. Schreck,et al.  Learning Retrosynthetic Planning through Simulated Experience , 2019, ACS central science.

[10]  Rémi Munos,et al.  Learning to Search with MCTSnets , 2018, ICML.

[11]  Jia Deng,et al.  Learning to Prove Theorems via Interacting with Proof Assistants , 2019, ICML.

[12]  Le Song,et al.  Retrosynthesis Prediction with Conditional Graph Logic Network , 2020, NeurIPS.

[13]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[14]  Nils J. Nilsson,et al.  A Formal Basis for the Heuristic Determination of Minimum Cost Paths , 1968, IEEE Trans. Syst. Sci. Cybern..

[15]  William H. Green,et al.  Computer-Assisted Retrosynthesis Based on Molecular Similarity , 2017, ACS central science.

[16]  Kutluhan Erol,et al.  Hierarchical task network planning: formalization, analysis, and implementation , 1996 .

[17]  Igor V. Tetko,et al.  A Transformer Model for Retrosynthesis , 2019, ICANN.

[18]  Bowen Liu,et al.  Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models , 2017, ACS central science.

[19]  David Rogers,et al.  Extended-Connectivity Fingerprints , 2010, J. Chem. Inf. Model..