Enhancing biocatalytic retrosynthesis with a graph-to-graph model
- 1State Key Laboratory of Physical Chemistry of Solid Surfaces and Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry, College of Chemistry and Chemical Engineering, Xiamen University Xiamen 360015 P. R. China
- 2Zhongguancun Academy Beijing 100097 P. R. China
- 3Department of Computer Science and Engineering, Shanghai Jiao Tong University Shanghai 200240 P. R. China
Abstract
Biocatalytic synthesis offers a green and sustainable route for chemical production, yet the rational design of biocatalytic routes remains challenging due to the need to jointly consider reaction feasibility and enzymatic compatibility. Here, we present BioG2G_ESR, a unified framework centered on graph-to-graph modeling for single-step biocatalytic retrosynthesis, with enzyme sequence recommendation as a downstream extension. BioG2G formulates retrosynthesis as a graph-to-graph translation task, directly predicting reactant molecular graphs from product structures while preserving molecular topology and stereochemical consistency. Extensive benchmark evaluations show that BioG2G achieves strong performance across biochemical retrosynthesis benchmarks, reaching Top-1 accuracies of 30.3% on Biochem-Plus and 55.0% on Biochem-Full. Representative literature-derived reactions absent from the Biochem-Plus training set are further examined as qualitative external examples. Building upon the predicted reactions, the enzyme sequence recommender (ESR) ranks candidate enzyme sequences primarily according to reaction similarity, with template–query matching used as an auxiliary signal for confidence stratification. Leave-one-out evaluation shows a clear association between template-match scores and Top-k accuracy across confidence groups. Together, BioG2G_ESR provides a unified and extensible framework for data-driven biocatalytic design, with graph-based retrosynthesis as the central component and enzyme recommendation as a complementary capability.
Related
- Biocatalytic Cascade from Geraniol to Enantiopure (R)-Citronellal Using an Aryl-Alcohol Oxidase and Ene Reductase.
- Exploring the biocatalytic potential of wild-type split transketolases
- Whole-cell biocatalytic acyloin condensation of benzaldehyde by baker's yeast: CC bond formation and
- Evaluation of alternative polymerases for biocatalytic synthesis of modified oligonucleotides
- Transformation of Aromatic Feedstocks into Value-Added Products via Biocatalytic Primary Amination
BibTeX
@article{dong2026enhancing,
title = {{Enhancing biocatalytic retrosynthesis with a graph-to-graph model}},
author = {Lina Dong and Lin Yao and Yucheng Yang and Yuxiang Gao and Zhihui Jiang and Binju Wang},
journal = {Chemical Science},
year = {2026},
month = sep,
doi = {10.1039/d6sc04187f},
url = {https://doi.org/10.1039/d6sc04187f},
note = {CC BY-NC 3.0},
}
RIS
TY - JOUR
TI - Enhancing biocatalytic retrosynthesis with a graph-to-graph model
AU - Lina Dong
AU - Lin Yao
AU - Yucheng Yang
AU - Yuxiang Gao
AU - Zhihui Jiang
AU - Binju Wang
PY - 2026
DA - 2026/09/09
JO - Chemical Science
DO - 10.1039/d6sc04187f
UR - https://doi.org/10.1039/d6sc04187f
AB - Biocatalytic synthesis offers a green and sustainable route for chemical production, yet the rational design of biocatalytic routes remains challenging due to the need to jointly consider reaction feasibility and enzymatic compatibility. Here, we present BioG2G_ESR, a unified framework centered on graph-to-graph modeling for single-step biocatalytic retrosynthesis, with enzyme sequence recommendation as a downstream extension. BioG2G formulates retrosynthesis as a graph-to-graph translation task, directly predicting reactant molecular graphs from product structures while preserving molecular topology and stereochemical consistency. Extensive benchmark evaluations show that BioG2G achieves strong performance across biochemical retrosynthesis benchmarks, reaching Top-1 accuracies of 30.3% on Biochem-Plus and 55.0% on Biochem-Full. Representative literature-derived reactions absent from the Biochem-Plus training set are further examined as qualitative external examples. Building upon the predicted reactions, the enzyme sequence recommender (ESR) ranks candidate enzyme sequences primarily according to reaction similarity, with template–query matching used as an auxiliary signal for confidence stratification. Leave-one-out evaluation shows a clear association between template-match scores and Top-k accuracy across confidence groups. Together, BioG2G_ESR provides a unified and extensible framework for data-driven biocatalytic design, with graph-based retrosynthesis as the central component and enzyme recommendation as a complementary capability.
SN - 2041-6520
SN - 2041-6539
ER -