FAMUS: a few-shot learning framework for large-scale protein annotation

Abstract

Motivation: Gene function prediction is pivotal in genomic and metagenomic data analysis. Current annotation tools typically rely on the most similar sequence from the referencedatabase and struggle to robustly set meaningful hit thresholds, causing a major challenge for reliable annotation.

Results: Here, we present Functional Annotation Method Using Supervised contrastive learning (FAMUS). FAMUS compares query sequences to a full array of profile Hidden Markov Models, encoding each sequence’s complete similarity profile, rather than only its top-scoring hit, into a condensed vector space that minimizes the distance between proteins from the same family. Unannotated sequences are incorporated as negative examples during training, enabling robust detection of proteins that fall outside the reference database without requiring user-defined thresholds. FAMUS outperformed KEGG’s native KofamScan for KEGG Orthology annotation and InterPro’s InterProScan for PANTHER family annotation, especially on realistic, sparsely annotated data. We used this approach to build four protein annotation models spanning the KEGG Orthology, InterPro, OrthoDB, and EggNOG databases. FAMUS is a comprehensive, modular framework that supports both pre-defined and user-specific databases. It can be readily integrated into genomic and metagenomic analysis pipelines for accurate, large-scale functional annotation.

Availability and implementation: All four models are available as a conda package and via our web server at https://app.famus.bursteinlab.org/, and source code is freely available on GitHub at https://github.com/burstein-lab/famus/ as well as a source code snapshot at https://doi.org/10.5281/zenodo.23132542.

BILBO: a self-hosted platform for large-scale RNA-Seq analysis with a functional annotation clustering framework.
Vitor Luciano Costa da Silva, João Vitor Reis Alvarenga, Manoel Viana Linhares-Neto +2
Functional & integrative genomics29 Oct 2026Peer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMCPMC
A learning-to-rank framework for large-scale identification of unknown proteins from cryo-EM and cryo-ET maps
Qi Hu, Georges Mer
bioRxiv12 Oct 2026PreprintCC BYFull textBiophysicsbioRxivPMC
Large-scale discovery and annotation of substructure patterns in mass spectrometry profiles
Laura Rosina Torres Ortega, Jonas Dietrich, Joe Wandy +2
Nature Communications6 Jul 2026Peer-reviewedCC BYFull text10 citedMolecular biology & gene regulationOpenAlex
Large language model consensus substantially improves the cell type annotation accuracy for scRNA-seq data
Yang Chen, Xianyang Zhang, Jun Chen
Communications Biology8 Jun 2026Peer-reviewedCC BY-NC-NDFull text16 citedMolecular biology & gene regulationOpenAlex
AlloPool is a deep learning framework that infers protein allostery from molecular dynamics simulations
Matthieu Marfoglia, Miguel A. Pedraza-Joya, Lucas Guirardel +2
PLOS Biology21 Sep 2026Peer-reviewedCC BY 4.0Full textMolecular biology & gene regulationPLOS

Cite

BibTeX RIS

BibTeX

@article{shur2026famus,
  title = {{FAMUS: a few-shot learning framework for large-scale protein annotation}},
  author = {Guy Shur and David Burstein},
  journal = {Bioinformatics},
  year = {2026},
  month = oct,
  doi = {10.1093/bioinformatics/btag761},
  url = {https://academic.oup.com/bioinformatics/article/doi/10.1093/bioinformatics/btag761/8911833},
  note = {CC BY 4.0},
}

RIS

TY  - JOUR
TI  - FAMUS: a few-shot learning framework for large-scale protein annotation
AU  - Guy Shur
AU  - David Burstein
PY  - 2026
DA  - 2026/10/12
JO  - Bioinformatics
DO  - 10.1093/bioinformatics/btag761
UR  - https://academic.oup.com/bioinformatics/article/doi/10.1093/bioinformatics/btag761/8911833
AB  - Motivation: Gene function prediction is pivotal in genomic and metagenomic data analysis. Current annotation tools typically rely on the most similar sequence from the referencedatabase and struggle to robustly set meaningful hit thresholds, causing a major challenge for reliable annotation.  Results: Here, we present Functional Annotation Method Using Supervised contrastive learning (FAMUS). FAMUS compares query sequences to a full array of profile Hidden Markov Models, encoding each sequence’s complete similarity profile, rather than only its top-scoring hit, into a condensed vector space that minimizes the distance between proteins from the same family. Unannotated sequences are incorporated as negative examples during training, enabling robust detection of proteins that fall outside the reference database without requiring user-defined thresholds. FAMUS outperformed KEGG’s native KofamScan for KEGG Orthology annotation and InterPro’s InterProScan for PANTHER family annotation, especially on realistic, sparsely annotated data. We used this approach to build four protein annotation models spanning the KEGG Orthology, InterPro, OrthoDB, and EggNOG databases. FAMUS is a comprehensive, modular framework that supports both pre-defined and user-specific databases. It can be readily integrated into genomic and metagenomic analysis pipelines for accurate, large-scale functional annotation.  Availability and implementation: All four models are available as a conda package and via our web server at https://app.famus.bursteinlab.org/, and source code is freely available on GitHub at https://github.com/burstein-lab/famus/ as well as a source code snapshot at https://doi.org/10.5281/zenodo.23132542.
SN  - 1367-4803
SN  - 1367-4811
ER  -

Abstract

Related

Cite