{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:24:18Z","timestamp":1781018658399,"version":"3.54.1"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T00:00:00Z","timestamp":1695081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001870","name":"Foundation for Polish Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001870","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["POIR.04.04.00-00-5CF1\/18-00"],"award-info":[{"award-number":["POIR.04.04.00-00-5CF1\/18-00"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004189","name":"Max Planck Society","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004189","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>The detection of homology through sequence comparison is a typical first step in the study of protein function and evolution. In this work, we explore the applicability of protein language models to this task.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We introduce pLM-BLAST, a tool inspired by BLAST, that detects distant homology by comparing single-sequence representations (embeddings) derived from a protein language model, ProtT5. Our benchmarks reveal that pLM-BLAST maintains a level of accuracy on par with HHsearch for both highly similar sequences (with &amp;gt;50% identity) and markedly divergent sequences (with &amp;lt;30% identity), while being significantly faster. Additionally, pLM-BLAST stands out among other embedding-based tools due to its ability to compute local alignments. We show that these local alignments, produced by pLM-BLAST, often connect highly divergent proteins, thereby highlighting its potential to uncover previously undiscovered homologous relationships and improve protein annotation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>pLM-BLAST is accessible via the MPI Bioinformatics Toolkit as a web server for searching precomputed databases (https:\/\/toolkit.tuebingen.mpg.de\/tools\/plmblast). It is also available as a standalone tool for building custom databases and performing batch searches (https:\/\/github.com\/labstructbioinf\/pLM-BLAST).<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad579","type":"journal-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T11:58:22Z","timestamp":1694779102000},"source":"Crossref","is-referenced-by-count":81,"title":["pLM-BLAST: distant homology detection based on direct comparison of sequence representations from protein language models"],"prefix":"10.1093","volume":"39","author":[{"given":"Kamil","family":"Kaminski","sequence":"first","affiliation":[{"name":"Institute of Evolutionary Biology, Faculty of Biology, Biological and Chemical Research Centre, University of Warsaw , Warsaw 02-089, Poland"},{"name":"Laboratory of Structural Bioinformatics, Centre of New Technologies, University of Warsaw , Warsaw 02-097, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3487-5433","authenticated-orcid":false,"given":"Jan","family":"Ludwiczak","sequence":"additional","affiliation":[{"name":"Institute of Evolutionary Biology, Faculty of Biology, Biological and Chemical Research Centre, University of Warsaw , Warsaw 02-089, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamil","family":"Pawlicki","sequence":"additional","affiliation":[{"name":"Institute of Evolutionary Biology, Faculty of Biology, Biological and Chemical Research Centre, University of Warsaw , Warsaw 02-089, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1188-473X","authenticated-orcid":false,"given":"Vikram","family":"Alva","sequence":"additional","affiliation":[{"name":"Department of Protein Evolution, Max Planck Institute for Biology T\u00fcbingen , T\u00fcbingen 72076, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4581-1558","authenticated-orcid":false,"given":"Stanislaw","family":"Dunin-Horkawicz","sequence":"additional","affiliation":[{"name":"Institute of Evolutionary Biology, Faculty of Biology, Biological and Chemical Research Centre, University of Warsaw , Warsaw 02-089, Poland"},{"name":"Department of Protein Evolution, Max Planck Institute for Biology T\u00fcbingen , T\u00fcbingen 72076, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,9,19]]},"reference":[{"key":"2023101423110219600_btad579-B1","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","article-title":"Gapped BLAST and PSI-BLAST: a new generation of protein database search programs","volume":"25","author":"Altschul","year":"1997","journal-title":"Nucleic Acids Res"},{"key":"2023101423110219600_btad579-B2","doi-asserted-by":"crossref","first-page":"e09410","DOI":"10.7554\/eLife.09410","article-title":"A vocabulary of ancient peptides at the origin of folded proteins","volume":"4","author":"Alva","year":"2015","journal-title":"Elife"},{"key":"2023101423110219600_btad579-B3","author":"Barrera-Redondo","year":"2022"},{"key":"2023101423110219600_btad579-B4","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1016\/j.cels.2021.05.017","article-title":"Learning the protein language: evolution, structure, and function","volume":"12","author":"Bepler","year":"2021","journal-title":"Cell Syst"},{"key":"2023101423110219600_btad579-B5","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1186\/s12859-022-04873-x","article-title":"TMbed: transmembrane proteins predicted through language model embeddings","volume":"23","author":"Bernhofer","year":"2022","journal-title":"BMC Bioinform"},{"key":"2023101423110219600_btad579-B6","doi-asserted-by":"crossref","first-page":"3770","DOI":"10.1073\/pnas.0810767106","article-title":"Sequence context-specific profiles for homology searching","volume":"106","author":"Biegert","year":"2009","journal-title":"Proc Natl Acad Sci USA"},{"key":"2023101423110219600_btad579-B7","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1038\/s41592-021-01101-x","article-title":"Sensitive protein alignments at tree-of-life scale using DIAMOND","volume":"18","author":"Buchfink","year":"2021","journal-title":"Nat Methods"},{"key":"2023101423110219600_btad579-B8","doi-asserted-by":"crossref","first-page":"D211","DOI":"10.1093\/nar\/gkm698","article-title":"MALISAM: a database of structurally analogous motifs in proteins","volume":"36","author":"Cheng","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2023101423110219600_btad579-B9","doi-asserted-by":"crossref","first-page":"e1003926","DOI":"10.1371\/journal.pcbi.1003926","article-title":"ECOD: an Evolutionary Classification of Protein Domains","volume":"10","author":"Cheng","year":"2014","journal-title":"PLoS Comput Biol"},{"key":"2023101423110219600_btad579-B10","doi-asserted-by":"crossref","first-page":"e1002195","DOI":"10.1371\/journal.pcbi.1002195","article-title":"Accelerated profile HMM searches","volume":"7","author":"Eddy","year":"2011","journal-title":"PLoS Comput Biol"},{"key":"2023101423110219600_btad579-B11","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: towards cracking the language of lifes code through self-supervised deep learning and high performance computing","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2023101423110219600_btad579-B12","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1093\/bioinformatics\/btaa810","article-title":"A novel sequence alignment algorithm based on deep learning of the protein folding code","volume":"37","author":"Gao","year":"2021","journal-title":"Bioinformatics"},{"key":"2023101423110219600_btad579-B13","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1016\/j.str.2004.03.029","article-title":"The linked conservation of structure and function in a family of high diversity","volume":"12","author":"Gough","year":"2004","journal-title":"Structure"},{"key":"2023101423110219600_btad579-B14","author":"Hamamsy","year":"2022"},{"key":"2023101423110219600_btad579-B15","doi-asserted-by":"crossref","first-page":"10915","DOI":"10.1073\/pnas.89.22.10915","article-title":"Amino acid substitution matrices from protein blocks","volume":"89","author":"Henikoff","year":"1992","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2023101423110219600_btad579-B16","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2023101423110219600_btad579-B17","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.sbi.2020.11.006","article-title":"Searching protein space for ancient Sub-domain segments","volume":"68","author":"Kolodny","year":"2021","journal-title":"Curr Opin Struct Biol"},{"key":"2023101423110219600_btad579-B18","doi-asserted-by":"crossref","first-page":"2191","DOI":"10.1093\/molbev\/msab017","article-title":"Bridging themes: short protein segments found in different architectures","volume":"38","author":"Kolodny","year":"2021","journal-title":"Mol Biol Evol"},{"key":"2023101423110219600_btad579-B19","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1186\/s12859-017-1842-2","article-title":"Protein remote homology detection based on bidirectional long short-term memory","volume":"18","author":"Li","year":"2017","journal-title":"BMC Bioinform"},{"key":"2023101423110219600_btad579-B20","author":"Li","year":"2022"},{"key":"2023101423110219600_btad579-B21","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2023101423110219600_btad579-B22","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1038\/s41592-022-01700-2","article-title":"Deep embedding and alignment of protein sequences","volume":"20","author":"Llinares-L\u00f3pez","year":"2023","journal-title":"Nat Methods"},{"key":"2023101423110219600_btad579-B23","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.64415","article-title":"On the emergence of P-Loop NTPase and Rossmann enzymes from a Beta-Alpha-Beta ancestral fragment","volume":"9","author":"Longo","year":"2020","journal-title":"Elife"},{"key":"2023101423110219600_btad579-B24","first-page":"2633","article-title":"Localpdb\u2014a python package to manage protein structures and their annotations","volume":"38","author":"Ludwiczak","year":"2022","journal-title":"Bioinformatics (Oxford, England)"},{"key":"2023101423110219600_btad579-B25","author":"Morton","year":"2023"},{"key":"2023101423110219600_btad579-B26","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":"2023101423110219600_btad579-B27","author":"Pantolini","year":"2022"},{"key":"2023101423110219600_btad579-B28","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1038\/nmeth.1818","article-title":"HHblits: lightning-fast iterative protein sequence searching by HMM-HMM alignment","volume":"9","author":"Remmert","year":"2011","journal-title":"Nat Methods"},{"key":"2023101423110219600_btad579-B29","doi-asserted-by":"crossref","first-page":"1033775","DOI":"10.3389\/fbinf.2022.1033775","article-title":"Nearest neighbor search on embeddings rapidly identifies distant protein relations","volume":"2","author":"Sch\u00fctze","year":"2022","journal-title":"Front Bioinform"},{"key":"2023101423110219600_btad579-B30","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1038\/nbt.3988","article-title":"MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets","volume":"35","author":"Steinegger","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2023101423110219600_btad579-B31","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1186\/s12859-019-3019-7","article-title":"HH-suite3 for fast remote homology detection and deep protein annotation","volume":"20","author":"Steinegger","year":"2019","journal-title":"BMC Bioinform"},{"key":"2023101423110219600_btad579-B32","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1002\/jmr.861","article-title":"Homology versus analogy: possible evolutionary relationship of immunoglobulins, cupredoxins, and Cu,Zn-superoxide dismutase","volume":"21","author":"Stevens","year":"2008","journal-title":"J Mol Recognit"},{"key":"2023101423110219600_btad579-B33","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1038\/s41587-021-01156-3","article-title":"SignalP 6.0 predicts all five types of signal peptides using protein language models","volume":"40","author":"Teufel","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2023101423110219600_btad579-B34","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1038\/s41592-022-01585-1","article-title":"US-align: universal structure alignments of proteins, nucleic acids, and macromolecular complexes","volume":"19","author":"Zhang","year":"2022","journal-title":"Nat Methods"},{"key":"2023101423110219600_btad579-B35","doi-asserted-by":"crossref","first-page":"e1007411","DOI":"10.1371\/journal.pcbi.1007411","article-title":"Detecting distant-homology protein structures by aligning deep neural-network based contact maps","volume":"15","author":"Zheng","year":"2019","journal-title":"PLoS Comput Biol"},{"key":"2023101423110219600_btad579-B36","doi-asserted-by":"crossref","first-page":"2237","DOI":"10.1016\/j.jmb.2017.12.007","article-title":"A completely reimplemented MPI bioinformatics toolkit with a new HHpred server at its core","volume":"430","author":"Zimmermann","year":"2018","journal-title":"J Mol Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad579\/51684423\/btad579.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/10\/btad579\/52147181\/btad579.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/10\/btad579\/52147181\/btad579.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,14]],"date-time":"2023-10-14T19:11:26Z","timestamp":1697310686000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad579\/7277200"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,9,19]]},"references-count":36,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad579","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.11.24.517862","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,10,1]]},"published":{"date-parts":[[2023,9,19]]},"article-number":"btad579"}}