Joint enzyme–reaction retrieval and catalytic optima prediction via multimodal fusion
Bioinformatics · 02.10.2026 · 42 (10)
DOI: 10.1093/bioinformatics/btag764 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 12.10.2026. Verfasst von Yueyi Cai und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, Wuhan University, No. 299, Bayi Road, Luojia Hill Street, Wuhan, Hubei, 430072, China. Hauptthemen laut MEDLINE: Enzymes, Computational Biology, Software. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Intelligent Computing Center of the National Cybersecurity Talent and Innovation Base, Wuhan.
Abstract (Originalsprache)
Motivation Enzyme–reaction retrieval prioritizes candidate biocatalysts for experimental follow-up, where recommendations should indicate catalytic compatibility and suitable pH and temperature conditions. Existing retrieval models optimize matching scores, whereas catalytic optima predictors are typically enzyme-level regressors because condition annotations are sparse. This separation leaves ranked pairs unevaluated for condition suitability and optima predictions without reaction context. Results We present GERO, a multimodal fusion framework integrating enzyme sequence semantics, sequence-derived pocket geometry, and molecular reaction representations through feature-gated fusion for condition-aware retrieval and catalytic optima estimation. We define the tolerance-restricted hit rate (Hit@k-TR), which requires both correct top-k retrieval and condition predictions within predefined tolerances. Across enzyme- and reaction-similarity splits, GERO improves Hit@k-TR over two-stage baselines under the primary tolerances. Benchmark examples and an iodinin biosynthesis case study illustrate candidate ranking and assay-condition estimation for experimental prioritization. Availability and implementation Source code is available at https://github.com/ykxhs/GERO.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Artificial Intelligence, Wuhan University, No. 299, Bayi Road, Luojia Hill Street, Wuhan, Hubei, 430072, China.
- School of Computer Science, Wuhan University, No. 299, Bayi Road, Luojia Hill Street, Wuhan, Hubei, 430072, China.
Förderung
- Intelligent Computing Center of the National Cybersecurity Talent and Innovation Base, Wuhan
Zitieren
APA
Cai, Y., Yang, F., & Liu, J. (2026). Joint enzyme–reaction retrieval and catalytic optima prediction via multimodal fusion. Bioinformatics, 42(10). https://doi.org/10.1093/bioinformatics/btag764
Vancouver
Cai Y, Yang F, Liu J. Joint enzyme–reaction retrieval and catalytic optima prediction via multimodal fusion. Bioinformatics. 2026;42(10). doi:10.1093/bioinformatics/btag764
BibTeX
@article{Cai2026,
author = {Cai, Yueyi and Yang, Feng and Liu, Juan},
title = {Joint enzyme–reaction retrieval and catalytic optima prediction via multimodal fusion},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {10},
doi = {10.1093/bioinformatics/btag764}
}
EUVIMED