Retro-BLEU: Quantifying Chemical Plausibility of Retrosynthesis Routes through Reaction Template Sequence Analysis

TL;DR

Retro-BLEU is a novel statistical metric inspired by BLEU score, designed to evaluate the chemical plausibility of retrosynthesis routes by analyzing reaction template sequences, aiding in better route assessment.

Contribution

Introduces Retro-BLEU, a new metric for quantifying retrosynthesis route plausibility based on reaction template sequences, improving evaluation accuracy over existing methods.

Findings

Retro-BLEU effectively differentiates plausible from implausible routes.

It outperforms other evaluation metrics in accuracy.

Provides insights for future improvements in retrosynthesis evaluation.

Abstract

Computer-assisted methods have emerged as valuable tools for retrosynthesis analysis. However, quantifying the plausibility of generated retrosynthesis routes remains a challenging task. We introduce Retro-BLEU, a statistical metric adapted from the well-established BLEU score in machine translation, to evaluate the plausibility of retrosynthesis routes based on reaction template sequences analysis. We demonstrate the effectiveness of Retro-BLEU by applying it to a diverse set of retrosynthesis routes generated by state-of-the-art algorithms and compare the performance with other evaluation metrics. The results show that Retro-BLEU is capable of differentiating between plausible and implausible routes. Furthermore, we provide insights into the strengths and weaknesses of Retro-BLEU, paving the way for future developments and improvements in this field.