OTalign: optimal transport alignment for remote protein homologs using protein language model embeddings
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag476 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Minsoo Kim und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics, Sungkyunkwan University, Suwon 16419, Korea. Hauptthemen laut MEDLINE: Proteins, Sequence Alignment, Computational Biology, Software. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation (IITP), Korea government (MSIT).
Abstract (Originalsprache)
Motivation Protein sequence alignment is a crucial task in bioinformatics, yet aligning remote homologs with low sequence identity remains a longstanding challenge, particularly due to the difficulty of handling gaps. We introduce a new method that applies Optimal Transport (OT) theory to sequence alignment, providing a mathematically principled framework for modeling residue matches and gaps. Results OTalign formulates sequence alignment as an entropy-regularized unbalanced optimal transport (UOT) problem over embeddings derived from protein language models (PLMs). Unlike traditional methods, it introduces position-specific gap penalties that adapt to each sequence pair. On challenging remote-homolog benchmarks (SABmark, MALIDUP, MALISAM), OTalign consistently outperforms baselines (Needleman-Wunsch, HHalign) and recent PLM-based methods (PLMAlign, DeepBLAST), achieving F1 scores of 0.594 on SABmark Superfamily and 0.358 on SABmark Twilight. Furthermore, OTalign provides a quantitative and interpretable metric of how effectively PLM embeddings represent sequence similarity relationships. Finally, its differentiable nature enables end-to-end fine-tuning of PLMs, establishing a framework for learning embeddings explicitly optimized for alignment tasks. Availability and implementation This code is available at https://github.com/DeepFoldProtein/OTalign.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Physics, Sungkyunkwan University, Suwon 16419, Korea.
- School of Computational Sciences, Korea Institute for Advanced Study, Seoul 02455, Korea.
- Center for Advanced Computation, Korea Institute for Advanced Study, Seoul 02455, Korea.
ORCID-Profile: Jejoong Yoo, Keehyoung Joo
Förderung
- Institute of Information & Communications Technology Planning & Evaluation (IITP)
- Korea government (MSIT)
Zitieren
APA
Kim, M., Bae, H., Jo, G., Kim, K., Yoo, J., & Joo, K. (2026). OTalign: optimal transport alignment for remote protein homologs using protein language model embeddings. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag476
Vancouver
Kim M, Bae H, Jo G, Kim K, Yoo J, Joo K. OTalign: optimal transport alignment for remote protein homologs using protein language model embeddings. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag476
BibTeX
@article{Kim2026,
author = {Kim, Minsoo and Bae, Hanjin and Jo, Gyeongpil and Kim, Kunwoo and Yoo, Jejoong and Joo, Keehyoung},
title = {OTalign: optimal transport alignment for remote protein homologs using protein language model embeddings},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag476}
}
EUVIMED