Protein language models uncover carbohydrate-active enzyme function in metagenomics
CAZyLingua is a powerful tool that effectively augments existing functional annotation pipelines for CAZymes. By leveraging the deep contextual information captured by pLMs, our method can uncover novel CAZyme diversity and reveal enzymatic functions relevant to health and disease, contributing to a further understanding of biological processes related to host health and nutrition.
Authors
- Kumar Thurimella (ORCID: https://orcid.org/0000-0002-0819-4378)
- Damian R. Plichta (ORCID: https://orcid.org/0000-0002-6555-2557)
- D. B. Graham (ORCID: https://orcid.org/0000-0002-1046-746X)
- Sabina Leanti La Rosa (ORCID: https://orcid.org/0000-0003-3527-8101)
- Tommi Vatanen (ORCID: https://orcid.org/0000-0003-0949-1291)
- Ahmed M. Mohamed (ORCID: https://orcid.org/0000-0003-2390-2210)
- Róisı́n M. Owens (ORCID: https://orcid.org/0000-0001-7856-2108)
- Sergio Bacallado (ORCID: https://orcid.org/0000-0002-7193-6450)
- Chenhao Li (ORCID: https://orcid.org/0000-0003-1182-6804)
- Ramnik J. Xavier
Institutions
- Broad Institute (US)
- University of Helsinki (FI)
- Harvard University (US)
- University of Auckland (NZ)
- University of Cambridge (GB)
- Massachusetts General Hospital (US)
- Center for Systems Biology (US)
- University of Colorado Anschutz Medical Campus (US)
- Norwegian University of Life Sciences (NO)
Publication Details
- Journal
- BMC Bioinformatics
- Published
- 2025-11-26
- DOI
- https://doi.org/10.1186/s12859-025-06286-y
- Citations
- 2
- Primary Topic
- Genomics and Rare Diseases
- Type
- article
- Field-Weighted Citation Impact
- 3.63