Work

Enzyformer: a two-stage pretrained model for enzymatic retrosynthesis

Year: 2026

Type: article

Abstract: Although enzymatic retrosynthesis planning is widely used to accelerate drug synthesis and discovery, it still faces key challenges, including limited knowledge transfer from general chemical space and incomplete enzyme assignment. Here, we introduce Enzyformer, an innovative model that integrates the pretraining of molecules and reactions to capture both the syntax of SMILES and the transformation rules of organic reactions. With this two-stage pretraining strategy, Enzyformer improves top-1 and top-10 accuracies in retrosynthesis prediction by 7.5% and 11.7%, respectively, compared with the baseline R-SMILES. In addition, the incorporation of a contrastive learning model enables the highest reported F1-score of 0.922 for first-level EC number assignment. In conclusion, Enzyformer offers a promising solution for improving the accuracy and interpretability of enzymatic retrosynthesis prediction, which may help to reduce researchers’ workload and cost while accelerating drug design and mitigating the environmental impact of drug synthesis.

Source: Journal of Cheminformatics

DOI: 10.1186/s13321-026-01164-y

Authors: Tiantao Liu, Jiangcheng Xu, Xinke Zhan, Shaolong Lin, Shirley W. I. Siu

Institutions: Macao Polytechnic University, Hangzhou Vocational and Technical College

Language: English

Topic: Computational Drug Discovery Methods

Subfield: Computational Theory and Mathematics

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,390

Funder: Department of Education of Zhejiang Province