Expanding the galactose oxidase substrate repertoire via a multi-modal computational strategy
Abstract
Biocatalysis offers a greener alternative to chemical processes, yet industrial adoption is bottlenecked by the prohibitive cost of enzyme engineering. Here, we report a multi-modal computational framework that integrates synergistic descriptors of substrate binding, protein stability, and aggregation traits. Using galactose oxidase as a model system, this approach achieves 77% precision in identifying active variants across 13 structurally diverse secondary alcohols despite being trained exclusively on a single substrate. By implementing sequence conservation-based filtering, we demonstrate that training data can be reduced by 41% without compromising predictive fidelity. Furthermore, the multi-modal model generalizes to combinatorial variants (2–5 mutations) with 100% precision on a limited library. Experimental validation yields a curated panel of starting points for the synthesis of high-value functional ingredients, including optical brighteners and fragrance stabilizers. Our multi-modal approach facilitates more cost-effective enzyme engineering, supporting the development of biocatalytic routes for sustainable chemical manufacturing.
Related
- Integrated Multi-Omics Analysis of Polygonatum odoratum Polysaccharide in D-Galactose-Treated Mice Reveals Changes in Oxidative Stress Markers and Gut Microbiota.
- Casein Hydrolysate Peptides Attenuate Immunosenescence and Inflammaging in a D-Galactose-Induced Mouse Model of Aging.
- Effects of Fixed-Speed Treadmill Exercise on Oxidative Stress and Sirtuin Biomarkers in Young and D-Galactose-Treated Rats: A Biochemical Study with Exploratory Hippocampal Observations
- The soluble HLA repertoire captures neoantigenic, cryptic, and tumour-associated peptides in melanoma
- Dehydration-Responsive Left-Handed G-Quadruplexes Expandthe Sequence Repertoire
BibTeX
@article{miyajima2026expanding,
title = {{Expanding the galactose oxidase substrate repertoire via a multi-modal computational strategy}},
author = {Jhoann M.T. Miyajima and Dillon W.P. Tay and Wan Lin Yeo and Ying Sin Koo and Shreyas Supekar and Adrielle Xianwen Chen and Charmaine Chia and Nazreen Abdul Muthaliff and Tong Mei Teh and Hao Fan and Yee Hwee Lim and Sebastian Maurer-Stroh and Ee Lui Ang},
journal = {iScience},
year = {2026},
month = oct,
doi = {10.1016/j.isci.2026.118003},
url = {https://www.cell.com/iscience/fulltext/S2589-0042(26)03386-9},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Expanding the galactose oxidase substrate repertoire via a multi-modal computational strategy
AU - Jhoann M.T. Miyajima
AU - Dillon W.P. Tay
AU - Wan Lin Yeo
AU - Ying Sin Koo
AU - Shreyas Supekar
AU - Adrielle Xianwen Chen
AU - Charmaine Chia
AU - Nazreen Abdul Muthaliff
AU - Tong Mei Teh
AU - Hao Fan
AU - Yee Hwee Lim
AU - Sebastian Maurer-Stroh
AU - Ee Lui Ang
PY - 2026
DA - 2026/10/26
JO - iScience
DO - 10.1016/j.isci.2026.118003
UR - https://www.cell.com/iscience/fulltext/S2589-0042(26)03386-9
AB - Biocatalysis offers a greener alternative to chemical processes, yet industrial adoption is bottlenecked by the prohibitive cost of enzyme engineering. Here, we report a multi-modal computational framework that integrates synergistic descriptors of substrate binding, protein stability, and aggregation traits. Using galactose oxidase as a model system, this approach achieves 77% precision in identifying active variants across 13 structurally diverse secondary alcohols despite being trained exclusively on a single substrate. By implementing sequence conservation-based filtering, we demonstrate that training data can be reduced by 41% without compromising predictive fidelity. Furthermore, the multi-modal model generalizes to combinatorial variants (2–5 mutations) with 100% precision on a limited library. Experimental validation yields a curated panel of starting points for the synthesis of high-value functional ingredients, including optical brighteners and fragrance stabilizers. Our multi-modal approach facilitates more cost-effective enzyme engineering, supporting the development of biocatalytic routes for sustainable chemical manufacturing.
SN - 2589-0042
ER -