learnMSA2: deep protein multiple alignments with large language and hidden Markov models
Bioinformatics · 2024
DOI: 10.1093/bioinformatics/btae381 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2024. Verfasst von Felix Becker und 1 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Mathematics and Computer Science, University of Greifswald, 17489 Greifswald, Germany. Hauptthemen laut MEDLINE: Markov Chains, Sequence Alignment, Proteins, Sequence Analysis, Protein. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: ECCB2024.
Abstract (Originalsprache)
Motivation For the alignment of large numbers of protein sequences, tools are predominant that decide to align two residues using only simple prior knowledge, e.g. amino acid substitution matrices, and using only part of the available data. The accuracy of state-of-the-art programs declines with decreasing sequence identity and when increasingly large numbers of sequences are aligned. Recently, transformer-based deep-learning models started to harness the vast amount of protein sequence data, resulting in powerful pretrained language models with the main purpose of generating high-dimensional numerical representations, embeddings, for individual sites that agglomerate evolutionary, structural, and biophysical information. Results We extend the traditional profile hidden Markov model so that it takes as inputs unaligned protein sequences and the corresponding embeddings. We fit the model with gradient descent using our existing differentiable hidden Markov layer. All sequences and their embeddings are jointly aligned to a model of the protein family. We report that our upgraded HMM-based aligner, learnMSA2, combined with the ProtT5-XL protein language model aligns on average almost 6% points more columns correctly than the best amino acid-based competitor and scales well with sequence number. The relative advantage of learnMSA2 over other programs tends to be greater when the sequence identity is lower and when the number of sequences is larger. Our results strengthen the evidence on the rich information contained in protein language models’ embeddings and their potential downstream impact on the field of bioinformatics. Availability and implementation: https://github.com/Gaius-Augustus/learnMSA, PyPI and Bioconda, evaluation: https://github.com/felbecker/snakeMSA
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Institute of Mathematics and Computer Science, University of Greifswald, 17489 Greifswald, Germany.
ORCID-Profile: Felix Becker, Mario Stanke
Förderung
- ECCB2024
Zitieren
APA
Becker, F., & Stanke, M. (2024). learnMSA2: deep protein multiple alignments with large language and hidden Markov models. Bioinformatics. https://doi.org/10.1093/bioinformatics/btae381
Vancouver
Becker F, Stanke M. learnMSA2: deep protein multiple alignments with large language and hidden Markov models. Bioinformatics. 2024. doi:10.1093/bioinformatics/btae381
BibTeX
@article{Becker2024,
author = {Becker, Felix and Stanke, Mario},
title = {learnMSA2: deep protein multiple alignments with large language and hidden Markov models},
journal = {Bioinformatics},
year = {2024},
doi = {10.1093/bioinformatics/btae381}
}
EUVIMED