Retrosynthesis with Attention-Based NMT Model and Chemical Analysis of the "Wrong" Predictions

TL;DR

This paper presents an attention-based neural machine translation model for retrosynthesis prediction, significantly improving accuracy over previous models, and provides chemical analysis of incorrect predictions to understand their plausibility.

Contribution

Introduces a Tensor2Tensor-based attention model for retrosynthesis that outperforms seq2seq models and offers insights into invalid SMILES and plausible alternative predictions.

Findings

Top-1 accuracy improved to 54.1% from 34.7%.

Chemists identify plausible 'wrong' predictions.

Estimated true accuracy could reach 64.6%.

Abstract

We cast retrosynthesis as a machine translation problem by introducing a special Tensor2Tensor, an entire attention-based and fully data-driven model. Given a data set comprising about 50,000 diverse reactions extracted from USPTO patents, the model significantly outperforms seq2seq model (34.7%) on a top-1 accuracy by achieving 54.1%. For yielding better results, parameters such as batch size and training time are thoroughly investigated to train the model. Additionally, we offer a novel insight into the causes of grammatically invalid SMILES, and conduct a test in which experienced chemists pick out and analyze the "wrong" predictions that may be chemically plausible but differ from the ground truth. Actually, the effectiveness of our model is un-derestimated and the "true" top-1 accuracy can reach to 64.6%.