Valid, Plausible, and Diverse Retrosynthesis Using Tied Two-Way Transformers with Latent Variables
- 7 January 2021
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 61 (1) , 123-133
Abstract
Retrosynthesis is an essential task in organic chemistry for identifying the synthesis pathways of newly discovered materials, and with the recent advances in deep learning, there have been growing attempts to solve the retrosynthesis problem through transformer models, which are the state-of-the-art in neural machine translation, by converting the problem into a machine translation problem. However, the pure transformer provides unsatisfactory results that lack grammatical validity, chemical plausibility, and diversity in reactant candidates. In this study, we develop tied two-way transformers with latent modeling to solve those problems using cycle consistency checks, parameter sharing, and multinomial latent variables. Experimental results obtained using public and in-house datasets demonstrate that the proposed model improves the retrosynthesis accuracy, grammatical error, and diversity, and qualitative evaluation results verify its ability to suggest valid and plausible results.Keywords
This publication has 29 references indexed in Scilit:
- Parallel Optimization of Synthetic Pathways within the Network of Organic ChemistryAngewandte Chemie International Edition, 2012
- Mining Electronic Laboratory Notebooks: Analysis, Retrosynthesis, and Reaction Based EnumerationJournal of Chemical Information and Modeling, 2012
- Route Designer: A Retrosynthetic Analysis Tool Utilizing Automated Retrosynthetic Rule GenerationJournal of Chemical Information and Modeling, 2009
- Computer-aided organic synthesisChemical Society Reviews, 2005
- Computer‐Assisted Planning of Organic Syntheses: The Second Generation of ProgramsAngewandte Chemie International Edition, 1996
- SOPHIA, a Knowledge Base-Guided Reaction Prediction System - Utilization of a Knowledge Base Derived from a Reaction DatabaseJournal of Chemical Information and Computer Sciences, 1995
- SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rulesJournal of Chemical Information and Computer Sciences, 1988
- Computer-Assisted Analysis in Organic SynthesisScience, 1985
- Computer-Assisted Design of Complex Organic SynthesesScience, 1969
- LXIII.—A synthesis of tropinoneJournal of the Chemical Society, Transactions, 1917