Artificial applicability labels for improving policies in retrosynthesis prediction. Issue 1 (24th December 2020)

• Record Type: Journal Article
• Authors: Bjerrum, Esben Jannik; Thakkar, Amol; Engkvist, Ola
• Is Part Of: Machine learning: science and technology. Volume 2:Issue 1(2021)
• Publication Date: 2020-12-24
• Subjects: retrosynthesis prediction -- policy network -- policy guided tree search -- reaction rule applicability; 006.31
• DOI: 10.1088/2632-2153/abcf90
• Languages: English
• ISSNs: 2632-2153

Abstract

Abstract: Automated retrosynthetic planning algorithms are a research area of increasing importance. Automated reaction-template extraction from large datasets, in conjunction with neural-network-enhanced tree-search algorithms, can find plausible routes to target compounds in seconds. However, the current method for training neural networks to predict suitable templates for a given target product leads to many predictions that are not applicable in silico . Most templates in the top 50 suggested templates cannot be applied to the target molecule to perform the virtual reaction. Here, we describe how to generate data and train a neural network policy that predicts whether templates are applicable or not. First, we generate a massive training dataset by applying each retrosynthetic template to each product from our reaction database. Second, we train a neural network to perform near-perfect prediction of the applicability labels on a held-out test set. The trained network is then joined with a policy model trained to predict and prioritize templates using the labels from the original dataset. The combined model was found to outperform the policy model in a route-finding task using 1700 compounds from our internal drug-discovery projects.