Fine-grained structural classification of biosynthetic gene cluster-encoded products
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag559 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Vladimir Porokhin und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Tufts University, Medford, MA 02155, United States. Hauptthemen laut MEDLINE: Multigene Family, Computational Biology, Biological Products, Biosynthetic Pathways. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Army Research Office, Multidisciplinary University Research Initiative (MURI) program.
Abstract (Originalsprache)
Motivation Biosynthetic gene clusters (BGCs) are responsible the biosynthesis of many natural products, including a multitude of effective therapeutics and their precursors. Advances in genomic data collection as well as computational techniques have made it possible to identify BGCs at scale. However, accurately determining the types of BGC-encoded products from genomic content remains elusive. Results Here, we introduce BGC annotation tool (BGCat), a machine learning method for fine-grained structural classification of BGC-encoded products, leveraging the NPClassifier natural product nomenclature. Our method leverages a pre-trained protein language model for creating meaningful gene representations and a deep neural network for class label prediction. We show the method outperforms state-of-the-art approaches in coarse-grained product classification and is effective for detailed classification. We implement a clustering-based augmentation strategy for BGC-product relationships, addressing a crucial gap in the available datasets. We then introduce the concept of product class profiles of gene cluster families (GCFs), associating each GCF with a probabilistic distribution of product types and offering a new perspective on GCF functions. Lastly, we use BGCat to provide new product class labels for over 100k BGCs in antiSMASH DB that presently have minimal information about their products. Availability and implementation The source code and trained model weights are freely available at https://github.com/HassounLab/BGCat.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Computer Science, Tufts University, Medford, MA 02155, United States.
- Department of Chemistry, Virginia Tech, Blacksburg, VA 24061, United States.
- Bioinformatics Group, Wageningen University & Research, Wageningen 6708PB, The Netherlands.
- Department of Biochemistry, University of Johannesburg, Johannesburg 2006, South Africa.
- Department of Chemical and Biological Engineering, Tufts University, Medford, MA 02155, United States.
ORCID-Profile: Justin J J van der Hooft, Soha Hassoun
Förderung
- Army Research Office, Multidisciplinary University Research Initiative (MURI) program
Zitieren
APA
Porokhin, V., Mevers, E., van der Hooft, J. J. J., & Hassoun, S. (2026). Fine-grained structural classification of biosynthetic gene cluster-encoded products. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag559
Vancouver
Porokhin V, Mevers E, van der Hooft JJJ, Hassoun S. Fine-grained structural classification of biosynthetic gene cluster-encoded products. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag559
BibTeX
@article{Porokhin2026,
author = {Porokhin, Vladimir and Mevers, Emily and van der Hooft, Justin J J and Hassoun, Soha},
title = {Fine-grained structural classification of biosynthetic gene cluster-encoded products},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag559}
}
EUVIMED