{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T03:37:39Z","timestamp":1783568259543,"version":"3.55.0"},"reference-count":23,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:00:00Z","timestamp":1731628800000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Recent breakthroughs in protein fold prediction from amino acid sequences have unleashed a deluge of new structures, presenting new opportunities and challenges to bioinformatics.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Reseek is a novel protein structure alignment algorithm based on sequence alignment where each residue in the protein backbone is represented by a letter in a \u201cmega-alphabet\u201d of 85\u00a0899\u00a0345\u00a0920 (\u223c1011) distinct states. Reseek achieves substantially improved sensitivity to remote homologs compared to state-of-the-art methods including DALI, TMalign, and Foldseek, with comparable speed to Foldseek, the fastest previous method. Scaling to large databases of AI-predicted folds is analyzed. Foldseek E-values are shown to be under-estimated by several orders of magnitude, while Reseek E-values are in good agreement with measured error rates.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>https:\/\/github.com\/rcedgar\/reseek.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae687","type":"journal-article","created":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T17:05:35Z","timestamp":1731690335000},"source":"Crossref","is-referenced-by-count":19,"title":["Protein structure alignment by Reseek improves sensitivity to remote homologs"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7355-2541","authenticated-orcid":false,"given":"Robert C","family":"Edgar","sequence":"first","affiliation":[{"name":"Independent Scientist , Corte Madera, CA 94925,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,11,15]]},"reference":[{"key":"2024112717340494800_btae687-B2","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1016\/S0076-6879(96)66029-7","article-title":"Local alignment statistics","volume":"266","author":"Altschul","year":"1996","journal-title":"Methods Enzymol"},{"key":"2024112717340494800_btae687-B3","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","article-title":"Basic local alignment search tool","volume":"215","author":"Altschul","year":"1990","journal-title":"J Mol Biol"},{"key":"2024112717340494800_btae687-B6","doi-asserted-by":"crossref","first-page":"6073","DOI":"10.1073\/pnas.95.11.6073","article-title":"Assessing sequence comparison methods with reliable structurally identified distant evolutionary relationships","volume":"95","author":"Brenner","year":"1998","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024112717340494800_btae687-B7","first-page":"233","author":"Davis","year":"2006"},{"key":"2024112717340494800_btae687-B9","doi-asserted-by":"publisher","author":"Edgar","year":"2024","DOI":"10.1101\/2024.10.26.620413"},{"key":"2024112717340494800_btae687-B10","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to roc analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recognit Lett"},{"key":"2024112717340494800_btae687-B11","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 USA"},{"key":"2024112717340494800_btae687-B12","doi-asserted-by":"crossref","first-page":"5326","DOI":"10.1093\/bioinformatics\/btz536","article-title":"Benchmarking fold detection by dalilite v. 5","volume":"35","author":"Holm","year":"2019","journal-title":"Bioinformatics"},{"key":"2024112717340494800_btae687-B13","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1006\/jmbi.1993.1489","article-title":"Protein structure comparison by alignment of distance matrices","volume":"233","author":"Holm","year":"1993","journal-title":"J Mol Biol"},{"key":"2024112717340494800_btae687-B14","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1107\/S0907444902003359","article-title":"Conformations of amino acids in proteins","volume":"58","author":"Hovmoller","year":"2002","journal-title":"Acta Crystallogr Sect D Biol Crystallogr"},{"key":"2024112717340494800_btae687-B15","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1107\/S0567739476001873","article-title":"A solution for the best rotation to relate two sets of vectors","volume":"32","author":"Kabsch","year":"1976","journal-title":"Acta Cryst A"},{"key":"2024112717340494800_btae687-B17","first-page":"281","author":"MacQueen","year":"1967"},{"key":"2024112717340494800_btae687-B19","doi-asserted-by":"crossref","first-page":"2722","DOI":"10.1093\/bioinformatics\/btt473","article-title":"lddt: a local superposition-free score for comparing protein structures and models using distance difference tests","volume":"29","author":"Mariani","year":"2013","journal-title":"Bioinformatics"},{"key":"2024112717340494800_btae687-B20","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1016\/S0022-2836(05)80134-2","article-title":"Scop: a structural classification of proteins database for the investigation of sequences and structures","volume":"247","author":"Murzin","year":"1995","journal-title":"J Mol Biol"},{"key":"2024112717340494800_btae687-B21","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1093\/protein\/11.9.739","article-title":"Protein structure alignment by incremental combinatorial extension (CE) of the optimal path","volume":"11","author":"Shindyalov","year":"1998","journal-title":"Protein Eng"},{"key":"2024112717340494800_btae687-B22","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/0022-2836(81)90087-5","article-title":"Identification of common molecular subsequences","volume":"147","author":"Smith","year":"1981","journal-title":"J Mol Biol"},{"key":"2024112717340494800_btae687-B23","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/S0006-3495(96)79210-X","article-title":"The shannon information entropy of protein sequences","volume":"71","author":"Strait","year":"1996","journal-title":"Biophys J"},{"key":"2024112717340494800_btae687-B24","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1109\/34.88573","article-title":"Least-squares estimation of transformation parameters between two point patterns","volume":"13","author":"Umeyama","year":"1991","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"2024112717340494800_btae687-B25","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1038\/s41587-023-01773-0","article-title":"Fast and accurate protein structure search with foldseek","volume":"42","author":"Van Kempen","year":"2024","journal-title":"Nat Biotechnol"},{"key":"2024112717340494800_btae687-B26","doi-asserted-by":"crossref","first-page":"D439","DOI":"10.1093\/nar\/gkab1061","article-title":"Alphafold protein structure database: massively expanding the structural coverage of protein-sequence space with high-accuracy models","volume":"50","author":"Varadi","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2024112717340494800_btae687-B27","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1142\/S0219720008003461","article-title":"Clepaps: fast pair alignment of protein structures based on conformational letters","volume":"6","author":"Wang","year":"2008","journal-title":"J Bioinform Comput Biol"},{"key":"2024112717340494800_btae687-B28","doi-asserted-by":"crossref","first-page":"3646","DOI":"10.1093\/nar\/gkl395","article-title":"Protein structure database search and evolutionary classification","volume":"34","author":"Yang","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"2024112717340494800_btae687-B29","doi-asserted-by":"crossref","first-page":"2302","DOI":"10.1093\/nar\/gki524","article-title":"TMalign: a protein structure alignment algorithm based on the TM-score","volume":"33","author":"Zhang","year":"2005","journal-title":"Nucleic Acids Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae687\/60686180\/btae687.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/11\/btae687\/60833232\/btae687.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/11\/btae687\/60833232\/btae687.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T17:34:22Z","timestamp":1732728862000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae687\/7901215"}},"subtitle":[],"editor":[{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"references-count":23,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae687","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,11]]},"published":{"date-parts":[[2024,11,1]]},"article-number":"btae687"}}