EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BetaAlign: a deep learning approach for multiple sequence alignment

Edo Dotan iD, Elya Wygoda, Noa Ecker, Michael Alburquerque, Oren Avram iD, Yonatan Belinkov, Tal Pupko iD

Bioinformatics · 2024

DOI: 10.1093/bioinformatics/btaf009 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2024. Verfasst von Edo Dotan und 6 weiteren Autor:innen. Beteiligte Einrichtung: The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University, Tel Aviv 69978, Israel. Hauptthemen laut MEDLINE: Deep Learning, Sequence Alignment, Software. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Israel Science Foundation, Azrieli Foundation Early Career Faculty, Edmond J. Safra Center for Bioinformatics at Tel Aviv University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Multiple sequence alignments (MSAs) are extensively used in biology, from phylogenetic reconstruction to structure and function prediction. Here, we suggest an out-of-the-box approach for the inference of MSAs, which relies on algorithms developed for processing natural languages. We show that our artificial intelligence (AI)-based methodology can be trained to align sequences by processing alignments that are generated via simulations, and thus different aligners can be easily generated for datasets with specific evolutionary dynamics attributes. We expect that natural language processing (NLP) solutions will replace or augment classic solutions for computing alignments, and more generally, challenging inference tasks in phylogenomics. Results The MSA problem is a fundamental pillar in bioinformatics, comparative genomics, and phylogenetics. Here, we characterize and improve BetaAlign, the first deep learning aligner, which substantially deviates from conventional algorithms of alignment computation. BetaAlign draws on NLP techniques and trains transformers to map a set of unaligned biological sequences to an MSA. We show that our approach is highly accurate, comparable and sometimes better than state-of-the-art alignment tools. We characterize the performance of BetaAlign and the effect of various aspects on accuracy; for example, the size of the training data, the effect of different transformer architectures, and the effect of learning on a subspace of indel-model parameters (subspace learning). We also introduce a new technique that leads to improved performance compared to our previous approach. Our findings further uncover the potential of NLP-based methods for sequence alignment, highlighting that AI-based algorithms can substantially challenge classic approaches in phylogenomics and bioinformatics. Availability and implementation Datasets used in this work are available on HuggingFace (Wolf et al. Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. p.38–45. 2020) at: https://huggingface.co/dotan1111. Source code is available at: https://github.com/idotan286/SimulateAlignments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSequence AlignmentSoftwareAlgorithmsNatural Language ProcessingComputational BiologyPhylogeny

Autor:innen und Institutionen

  • The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University, Tel Aviv 69978, Israel.
  • The Henry and Marilyn Taub Faculty of Computer Science, Technion-Israel Institute of Technology, Haifa 3200003, Israel.
  • The Department of Computer Science, University of California Los Angeles, Los Angeles, CA 90095, United States.

ORCID-Profile: Edo Dotan, Oren Avram, Tal Pupko

Förderung

  • Israel Science Foundation
  • Azrieli Foundation Early Career Faculty
  • Edmond J. Safra Center for Bioinformatics at Tel Aviv University
  • Edouard Seroussi Chair for Protein Nanobiotechnology
  • Tel Aviv University

Zitieren

APA

Dotan, E., Wygoda, E., Ecker, N., Alburquerque, M., Avram, O., Belinkov, Y., & Pupko, T. (2024). BetaAlign: a deep learning approach for multiple sequence alignment. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf009

Vancouver

Dotan E, Wygoda E, Ecker N, Alburquerque M, Avram O, Belinkov Y, et al. BetaAlign: a deep learning approach for multiple sequence alignment. Bioinformatics. 2024. doi:10.1093/bioinformatics/btaf009

BibTeX
@article{Dotan2024,
  author = {Dotan, Edo and Wygoda, Elya and Ecker, Noa and Alburquerque, Michael and Avram, Oren and Belinkov, Yonatan and Pupko, Tal},
  title = {BetaAlign: a deep learning approach for multiple sequence alignment},
  journal = {Bioinformatics},
  year = {2024},
  doi = {10.1093/bioinformatics/btaf009}
}
Kostenlos starten →