{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T11:08:16Z","timestamp":1769598496235,"version":"3.49.0"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2016,5,18]],"date-time":"2016-05-18T00:00:00Z","timestamp":1463529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/publicdomain\/zero\/1.0\/"}],"funder":[{"name":"the School of Medicine at the University of Maryland, Baltimore"},{"name":"the Intramural Research Program of the National Library of Medicine"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1004936","type":"journal-article","created":{"date-parts":[[2016,5,18]],"date-time":"2016-05-18T17:37:08Z","timestamp":1463593028000},"page":"e1004936","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":18,"title":["Bayesian Top-Down Protein Sequence Alignment with Inferred Position-Specific Gap Penalties"],"prefix":"10.1371","volume":"12","author":[{"given":"Andrew F.","family":"Neuwald","sequence":"first","affiliation":[]},{"given":"Stephen F.","family":"Altschul","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2016,5,18]]},"reference":[{"issue":"4","key":"ref1","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1007\/BF02603120","article-title":"Progressive sequence alignment as a prerequisite to correct phylogenetic trees","volume":"25","author":"DF Feng","year":"1987","journal-title":"J Mol Evol"},{"issue":"1","key":"ref2","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1186\/1471-2105-5-113","article-title":"MUSCLE: a multiple sequence alignment method with reduced time and space complexity","volume":"5","author":"RC Edgar","year":"2004","journal-title":"BMC Bioinformatics"},{"issue":"14","key":"ref3","doi-asserted-by":"crossref","first-page":"3059","DOI":"10.1093\/nar\/gkf436","article-title":"MAFFT: a novel method for rapid multiple sequence alignment based on fast Fourier transform","volume":"30","author":"K Katoh","year":"2002","journal-title":"Nucleic Acids Res"},{"issue":"4","key":"ref4","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":"K Katoh","year":"2013","journal-title":"Mol Biol Evol"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1007\/978-1-62703-646-7_8","article-title":"MAFFT: iterative refinement and additional methods","volume":"1079","author":"K Katoh","year":"2014","journal-title":"Methods Mol Biol"},{"issue":"3","key":"ref6","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1093\/bioinformatics\/btl592","article-title":"PartTree: an algorithm to build an approximate tree from a large number of unaligned sequences","volume":"23","author":"K Katoh","year":"2007","journal-title":"Bioinformatics"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1186\/1748-7188-5-21","article-title":"Sequence embedding for fast construction of guide trees for multiple sequence alignment","volume":"5","author":"G Blackshields","year":"2010","journal-title":"Algorithms Mol Biol"},{"issue":"29","key":"ref8","doi-asserted-by":"crossref","first-page":"10556","DOI":"10.1073\/pnas.1405628111","article-title":"Simple chained guide trees give high-quality protein multiple sequence alignments","volume":"111","author":"K Boyce","year":"2014","journal-title":"Proc Natl Acad Sci U S A"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/01621459.1999.10473814","article-title":"Markovian structures in biological sequence alignments","volume":"94","author":"JS Liu","year":"1999","journal-title":"J Am Stat Assoc"},{"issue":"1","key":"ref10","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1186\/1471-2105-5-157","article-title":"Gapped alignment of protein sequence motifs through Monte Carlo optimization of a hidden Markov model","volume":"5","author":"AF Neuwald","year":"2004","journal-title":"BMC Bioinformatics"},{"issue":"9","key":"ref11","doi-asserted-by":"crossref","first-page":"1665","DOI":"10.1093\/nar\/25.9.1665","article-title":"Extracting protein alignment models from the sequence database","volume":"25","author":"AF Neuwald","year":"1997","journal-title":"Nucleic Acids Research"},{"issue":"9","key":"ref12","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1093\/bioinformatics\/14.9.755","article-title":"Profile hidden Markov models","volume":"14","author":"SR Eddy","year":"1998","journal-title":"Bioinformatics"},{"issue":"432","key":"ref13","doi-asserted-by":"crossref","first-page":"1156","DOI":"10.1080\/01621459.1995.10476622","article-title":"Bayesian models for multiple local sequence alignment and Gibbs sampling strategies","volume":"90","author":"JS Liu","year":"1995","journal-title":"J Am Stat Assoc"},{"key":"ref14","author":"PD Grunwald","year":"2007"},{"key":"ref15","first-page":"47","article-title":"Using Dirichlet mixture priors to derive hidden Markov models for protein families","volume":"1","author":"M Brown","year":"1993","journal-title":"Ismb"},{"issue":"4","key":"ref16","first-page":"327","article-title":"Dirichlet mixtures: a method for improved detection of weak but significant protein sequence homology","volume":"12","author":"K Sjolander","year":"1996","journal-title":"Comput Appl Biosci"},{"issue":"1","key":"ref17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1089\/cmb.2012.0244","article-title":"Dirichlet mixtures, the Dirichlet process, and the structure of protein space","volume":"20","author":"VA Nguyen","year":"2013","journal-title":"Journal of computational biology: a journal of computational molecular cell biology"},{"issue":"4","key":"ref18","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1016\/0022-2836(94)90032-9","article-title":"Position-based sequence weights","volume":"243","author":"S Henikoff","year":"1994","journal-title":"J Mol Biol"},{"issue":"7","key":"ref19","doi-asserted-by":"crossref","first-page":"e1000852","DOI":"10.1371\/journal.pcbi.1000852","article-title":"The construction and use of log-odds substitution scores for multiple sequence alignment","volume":"6","author":"SF Altschul","year":"2010","journal-title":"PLoS Comput Biol"},{"issue":"5","key":"ref20","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1089\/cmb.2014.0156","article-title":"PASTA: Ultra-Large Multiple Sequence Alignment for Nucleotide and Amino-Acid Sequences","volume":"22","author":"S Mirarab","year":"2015","journal-title":"Journal of computational biology: a journal of computational molecular cell biology"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"D222","DOI":"10.1093\/nar\/gku1221","article-title":"CDD: NCBI's conserved domain database","volume":"43","author":"A Marchler-Bauer","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/978-1-62703-646-7_6","article-title":"Clustal Omega, accurate alignment of very large numbers of sequences","volume":"1079","author":"F Sievers","year":"2014","journal-title":"Methods Mol Biol"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1038\/msb.2011.75","article-title":"Fast, scalable generation of high-quality protein multiple sequence alignments using Clustal Omega","volume":"7","author":"F Sievers","year":"2011","journal-title":"Mol Syst Biol"},{"issue":"3","key":"ref24","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1093\/nar\/gkn1006","article-title":"Kalign2: high-performance multiple alignment of protein and nucleotide sequences allowing external features","volume":"37","author":"T Lassmann","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1186\/1471-2105-6-298","article-title":"Kalign\u2014an accurate and fast multiple sequence alignment algorithm","volume":"6","author":"T Lassmann","year":"2005","journal-title":"BMC Bioinformatics"},{"issue":"3","key":"ref26","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1093\/bioinformatics\/15.3.211","article-title":"DIALIGN 2: improvement of the segment-to-segment approach to multiple sequence alignment","volume":"15","author":"B Morgenstern","year":"1999","journal-title":"Bioinformatics"},{"issue":"3","key":"ref27","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1093\/bioinformatics\/14.3.290","article-title":"DIALIGN: finding local similarities by multiple sequence alignment","volume":"14","author":"B Morgenstern","year":"1998","journal-title":"Bioinformatics"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/978-1-62703-646-7_12","article-title":"Multiple sequence alignment with DIALIGN","volume":"1079","author":"B Morgenstern","year":"2014","journal-title":"Methods Mol Biol"},{"issue":"1","key":"ref29","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1002\/prot.20527","article-title":"BAliBASE 3.0: Latest developments of the multiple sequence alignment benchmark","volume":"61","author":"JD Thompson","year":"2005","journal-title":"Proteins"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual comparisons by ranking methods","volume":"1","author":"AF Wilcoxon","year":"1945","journal-title":"Biometrics"},{"issue":"5","key":"ref31","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":"RC Edgar","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"ref32","author":"JS Liu","year":"2008"},{"issue":"3","key":"ref33","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1089\/cmb.2013.0099","article-title":"A Bayesian sampler for optimization of protein domain hierarchies","volume":"21","author":"AF Neuwald","year":"2014","journal-title":"Journal of Computational Biology"},{"issue":"4","key":"ref34","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1515\/sagmb-2014-0008","article-title":"Protein domain hierarchy Gibbs sampling strategies","volume":"13","author":"AF Neuwald","year":"2014","journal-title":"Statistical applications in genetics and molecular biology"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1186\/1471-2105-13-144","article-title":"Automated hierarchical classification of protein domain subfamilies based on functionally-divergent residue signatures","volume":"13","author":"AF Neuwald","year":"2012","journal-title":"BMC Bioinformatics"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1126\/science.220.4598.671","article-title":"Optimization by simulated annealing","volume":"220","author":"S Kirkpatrick","year":"1983","journal-title":"Science"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1004936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,10,23]],"date-time":"2018-10-23T21:08:35Z","timestamp":1540328915000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1004936"}},"subtitle":[],"editor":[{"given":"Christine A.","family":"Orengo","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2016,5,18]]},"references-count":36,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2016,5,18]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1004936","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,5,18]]}}}