Data augmentation in a triple transformer loop retrosynthesis model

01 August 2024, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

The reaction dataset from the US Patent Office (USPTO), which is used broadly for training computer-assisted synthesis planning (CASP) retrosynthesis models, is biased towards a few over-represented reaction types such as palladium couplings and protecting group operations. Here we applied 14,325 reaction templates extracted from USPTO reactions to 1,505,837 USPTO molecules and used a transformer-based approach derived from our recently reported triple transformer loop (TTL) retrosynthesis model to test and validate up to 5,000 reactions per template. This approach yielded 25.7 million fictive reactions, from which we selected up to 90 reactions per template to form an equilibrated augmented dataset of 1,000,245 reactions. Combining the original USPTO dataset with this augmented dataset by multitask transfer learning produced a new TTL model with increased performance in terms of overall and template averaged single step round-trip accuracy. Further performance increases were obtained by applying a new disconnection-aware forward validation transformer.

Keywords

retrosynthesis
transformer models
synthesis planning
data augmentation

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.