{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T03:22:25Z","timestamp":1782703345658,"version":"3.54.5"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T00:00:00Z","timestamp":1736294400000},"content-version":"vor","delay-in-days":13,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["448\/20"],"award-info":[{"award-number":["448\/20"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["2818\/21"],"award-info":[{"award-number":["2818\/21"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Azrieli Foundation Early Career Faculty"},{"name":"Edmond J. Safra Center for Bioinformatics at Tel Aviv University"},{"name":"Edouard Seroussi Chair for Protein Nanobiotechnology"},{"DOI":"10.13039\/501100004375","name":"Tel Aviv University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004375","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>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\u201345. 2020) at: https:\/\/huggingface.co\/dotan1111. Source code is available at: https:\/\/github.com\/idotan286\/SimulateAlignments.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf009","type":"journal-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T07:17:58Z","timestamp":1736234278000},"source":"Crossref","is-referenced-by-count":9,"title":["BetaAlign: a deep learning approach for multiple sequence alignment"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5403-6016","authenticated-orcid":false,"given":"Edo","family":"Dotan","sequence":"first","affiliation":[{"name":"The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University , Tel Aviv 69978,","place":["Israel"]},{"name":"The Henry and Marilyn Taub Faculty of Computer Science, Technion\u2014Israel Institute of Technology , Haifa 3200003,","place":["Israel"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elya","family":"Wygoda","sequence":"additional","affiliation":[{"name":"The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University , Tel Aviv 69978,","place":["Israel"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noa","family":"Ecker","sequence":"additional","affiliation":[{"name":"The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University , Tel Aviv 69978,","place":["Israel"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Alburquerque","sequence":"additional","affiliation":[{"name":"The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University , Tel Aviv 69978,","place":["Israel"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1984-2139","authenticated-orcid":false,"given":"Oren","family":"Avram","sequence":"additional","affiliation":[{"name":"The Department of Computer Science, University of California Los Angeles , Los Angeles, CA 90095,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonatan","family":"Belinkov","sequence":"additional","affiliation":[{"name":"The Henry and Marilyn Taub Faculty of Computer Science, Technion\u2014Israel Institute of Technology , Haifa 3200003,","place":["Israel"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9463-2575","authenticated-orcid":false,"given":"Tal","family":"Pupko","sequence":"additional","affiliation":[{"name":"The Shmunis School of Biomedicine and Cancer Research, George S. Wise Faculty of Life Sciences, Tel Aviv University , Tel Aviv 69978,","place":["Israel"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,1,8]]},"reference":[{"key":"2025040718362418500_btaf009-B1","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1186\/1471-2148-13-140","article-title":"Evolution of protein indels in plants, animals and fungi","volume":"13","author":"Ajawatanawong","year":"2013","journal-title":"BMC Evol Biol"},{"key":"2025040718362418500_btaf009-B2","first-page":"1614","article-title":"SLIViT: a general AI framework for accurate clinical-feature diagnosis from limited 3D medical-imaging data","volume":"65","author":"Avram","year":"2024","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"2025040718362418500_btaf009-B3","author":"Bahdanau"},{"key":"2025040718362418500_btaf009-B4","doi-asserted-by":"crossref","first-page":"1625","DOI":"10.1093\/molbev\/msu117","article-title":"TCS: a new multiple sequence alignment reliability measure to estimate alignment accuracy and improve phylogenetic tree reconstruction","volume":"31","author":"Chang","year":"2014","journal-title":"Mol Biol Evol"},{"key":"2025040718362418500_btaf009-B5","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1186\/1471-2105-13-117","article-title":"MergeAlign: improving multiple sequence alignment performance by dynamic reconstruction of consensus multiple sequence alignments","volume":"13","author":"Collingridge","year":"2012","journal-title":"BMC Bioinformatics"},{"key":"2025040718362418500_btaf009-B6","author":"Dotan"},{"key":"2025040718362418500_btaf009-B7","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1093\/bioinformatics\/btae196","article-title":"Effect of tokenization on transformers for biological sequences","volume":"40","author":"Dotan","year":"2024","journal-title":"Bioinformatics"},{"key":"2025040718362418500_btaf009-B8","doi-asserted-by":"crossref","first-page":"1792","DOI":"10.1093\/nar\/gkh340","article-title":"MUSCLE: multiple sequence alignment with high accuracy and high throughput","volume":"32","author":"Edgar","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2025040718362418500_btaf009-B9","doi-asserted-by":"crossref","first-page":"6968","DOI":"10.1038\/s41467-022-34630-w","article-title":"Muscle5: high-accuracy alignment ensembles enable unbiased assessments of sequence homology and phylogeny","volume":"13","author":"Edgar","year":"2022","journal-title":"Nat Commun"},{"key":"2025040718362418500_btaf009-B10","author":"Gu","year":"2022"},{"key":"2025040718362418500_btaf009-B11","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.1093\/molbev\/msw046","article-title":"ETE 3: reconstruction, analysis, and visualization of phylogenomic data","volume":"33","author":"Huerta-Cepas","year":"2016","journal-title":"Mol Biol Evol"},{"key":"2025040718362418500_btaf009-B12","first-page":"59","volume-title":"Methods Mol Biol","author":"Iantorno","year":"2014"},{"key":"2025040718362418500_btaf009-B13","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1093\/molbev\/mst010","article-title":"MAFFT multiple sequence alignment software version 7: improvements in performance and usability","volume":"30","author":"Katoh","year":"2013","journal-title":"Mol Biol Evol"},{"key":"2025040718362418500_btaf009-B14","doi-asserted-by":"crossref","first-page":"2947","DOI":"10.1093\/bioinformatics\/btm404","article-title":"Clustal W and clustal X version 2.0","volume":"23","author":"Larkin","year":"2007","journal-title":"Bioinformatics"},{"key":"2025040718362418500_btaf009-B16","doi-asserted-by":"crossref","first-page":"5769","DOI":"10.1093\/molbev\/msab266","article-title":"A probabilistic model for indel evolution: differentiating insertions from deletions","volume":"38","author":"Loewenthal","year":"2021","journal-title":"Mol Biol Evol"},{"key":"2025040718362418500_btaf009-B17","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1093\/nar\/28.1.85","article-title":"YIDB: the yeast intron DataBase","volume":"28","author":"Lopez","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2025040718362418500_btaf009-B18","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1007\/978-1-62703-646-7_10","article-title":"Phylogeny-aware alignment with PRANK","volume":"1079","author":"L\u00f6ytynoja","year":"2014","journal-title":"Methods Mol Biol"},{"key":"2025040718362418500_btaf009-B19","doi-asserted-by":"crossref","first-page":"1632","DOI":"10.1126\/science.1158395","article-title":"Phylogeny-aware gap placement prevents errors in sequence alignment and evolutionary analysis","volume":"320","author":"L\u00f6ytynoja","year":"2008","journal-title":"Science"},{"key":"2025040718362418500_btaf009-B20","first-page":"6297","article-title":"Learned in translation: contextualized word vectors","volume":"30","author":"McCann","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025040718362418500_btaf009-B21","doi-asserted-by":"crossref","first-page":"W33","DOI":"10.1093\/nar\/gkh373","article-title":"DIALIGN: multiple DNA and protein sequence alignment at BiBiServ","volume":"32","author":"Morgenstern","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2025040718362418500_btaf009-B22","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/0022-2836(70)90057-4","article-title":"A general method applicable to the search for similarities in the amino acid sequence of two proteins","volume":"48","author":"Needleman","year":"1970","journal-title":"J Mol Biol"},{"key":"2025040718362418500_btaf009-B23","first-page":"48","author":"Ott","year":"2019"},{"key":"2025040718362418500_btaf009-B24","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1007\/PL00006487","article-title":"Nucleotide substitution rate of mammalian mitochondrial genomes","volume":"48","author":"Pesole","year":"1999","journal-title":"J Mol Evol"},{"key":"2025040718362418500_btaf009-B25","doi-asserted-by":"crossref","first-page":"3032","DOI":"10.1093\/bioinformatics\/btab129","article-title":"BAli-Phy version 3: model-based co-estimation of alignment and phylogeny","volume":"37","author":"Redelings","year":"2021","journal-title":"Bioinformatics"},{"key":"2025040718362418500_btaf009-B26","doi-asserted-by":"crossref","first-page":"W7","DOI":"10.1093\/nar\/gkv318","article-title":"GUIDANCE2: accurate detection of unreliable alignment regions accounting for the uncertainty of multiple parameters","volume":"43","author":"Sela","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2025040718362418500_btaf009-B27","author":"Shalumov","year":"2023"},{"key":"2025040718362418500_btaf009-B28","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025040718362418500_btaf009-B29","author":"Szegedy","year":"2016"},{"key":"2025040718362418500_btaf009-B30","author":"Tan","year":"2018"},{"key":"2025040718362418500_btaf009-B31","author":"Vaswani","year":"2017"},{"key":"2025040718362418500_btaf009-B32","doi-asserted-by":"crossref","first-page":"e1009221","DOI":"10.1371\/journal.pgen.1009221","article-title":"Short-range template switching in great ape genomes explored using pair hidden markov models","volume":"17","author":"Walker","year":"2021","journal-title":"PLoS Genet"},{"key":"2025040718362418500_btaf009-B33","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1186\/1471-2148-8-331","article-title":"A class frequency mixture model that adjusts for site-specific amino acid frequencies and improves inference of protein phylogeny","volume":"8","author":"Wang","year":"2008","journal-title":"BMC Evol Biol"},{"key":"2025040718362418500_btaf009-B34","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1089\/cmb.1994.1.337","article-title":"On the complexity of multiple sequence alignment","volume":"1","author":"Wang","year":"1994","journal-title":"J Comput Biol"},{"key":"2025040718362418500_btaf009-B35","first-page":"38","author":"Wolf","year":"2020"},{"key":"2025040718362418500_btaf009-B36","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1186\/1471-2148-7-19","article-title":"Long-term trends in evolution of indels in protein sequences","volume":"7","author":"Wolf","year":"2007","journal-title":"BMC Evol Biol"},{"key":"2025040718362418500_btaf009-B37","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/BF00178256","article-title":"Estimating the pattern of nucleotide substitution","volume":"39","author":"Yang","year":"1994","journal-title":"J Mol Evol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf009\/61381591\/btaf009.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/1\/btaf009\/61381591\/btaf009.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/1\/btaf009\/61381591\/btaf009.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T22:50:42Z","timestamp":1744066242000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf009\/7945664"}},"subtitle":[],"editor":[{"given":"Russell","family":"Schwartz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,12,26]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,12,26]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf009","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.03.24.586462","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,1]]},"published":{"date-parts":[[2024,12,26]]},"article-number":"btaf009"}}