{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T02:36:36Z","timestamp":1773282996348,"version":"3.50.1"},"reference-count":61,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2008,5,9]],"date-time":"2008-05-09T00:00:00Z","timestamp":1210291200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1000071","type":"journal-article","created":{"date-parts":[[2008,5,8]],"date-time":"2008-05-08T21:50:46Z","timestamp":1210283446000},"page":"e1000071","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":315,"title":["Discovering Sequence Motifs with Arbitrary Insertions and Deletions"],"prefix":"10.1371","volume":"4","author":[{"given":"Martin C.","family":"Frith","sequence":"first","affiliation":[]},{"given":"Neil F. W.","family":"Saunders","sequence":"additional","affiliation":[]},{"given":"Bostjan","family":"Kobe","sequence":"additional","affiliation":[]},{"given":"Timothy L.","family":"Bailey","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2008,5,9]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"2870","DOI":"10.1093\/bioinformatics\/btl528","article-title":"Adding sequence context to a Markov background model improves the identification of regulatory elements.","volume":"22","author":"NK Kim","year":"2006","journal-title":"Bioinformatics"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1038\/nbt1098-939","article-title":"Finding DNA regulatory motifs within unaligned noncoding sequences clustered by whole-genome mRNA quantitation.","volume":"16","author":"FP Roth","year":"1998","journal-title":"Nat Biotechnol"},{"key":"ref3","first-page":"127","article-title":"BioProspector: discovering conserved DNA motifs in upstream regulatory regions of co-expressed genes.","author":"X Liu","year":"2001","journal-title":"Pac Symp Biocomput"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1038\/nbt717","article-title":"An algorithm for finding protein-DNA binding sites with applications to chromatin-immunoprecipitation microarray experiments.","volume":"20","author":"XS Liu","year":"2002","journal-title":"Nat Biotechnol"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1006\/jmbi.1998.1947","article-title":"Extracting regulatory sites from the upstream region of yeast genes by computational analysis of oligonucleotide frequencies.","volume":"281","author":"J van Helden","year":"1998","journal-title":"J Mol Biol"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1002\/(SICI)1097-0061(20000130)16:2<177::AID-YEA516>3.0.CO;2-9","article-title":"A web site for the computational analysis of yeast regulatory sequences.","volume":"16","author":"J van Helden","year":"2000","journal-title":"Yeast"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"W199","DOI":"10.1093\/nar\/gkh465","article-title":"Weeder Web: discovery of transcription factor binding sites in a set of sequences from co-regulated genes.","volume":"32","author":"G Pavesi","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"3586","DOI":"10.1093\/nar\/gkg618","article-title":"YMF: A program for discovery of novel transcription factor binding sites by statistical overrepresentation.","volume":"31","author":"S Sinha","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"ref9","first-page":"28","article-title":"Fitting a mixture model by expectation maximization to discover motifs in biopolymers.","volume":"2","author":"TL Bailey","year":"1994","journal-title":"Proc Int Conf Intell Syst Mol Biol"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.1002\/pro.5560040820","article-title":"Gibbs motif sampling: detection of bacterial outer membrane protein repeats.","volume":"4","author":"AF Neuwald","year":"1995","journal-title":"Protein Sci"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"D108","DOI":"10.1093\/nar\/gkj143","article-title":"TRANSFAC and its module TRANSCompel: transcriptional gene regulation in eukaryotes.","volume":"34","author":"V Matys","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"D91","DOI":"10.1093\/nar\/gkh012","article-title":"JASPAR: an open-access database for eukaryotic transcription factor binding profiles.","volume":"32","author":"A Sandelin","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1093\/bioinformatics\/15.7.607","article-title":"SCPD: a promoter database of the yeast <italic>Saccharomyces cerevisiae<\/italic>.","volume":"15","author":"J Zhu","year":"1999","journal-title":"Bioinformatics"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"D75","DOI":"10.1093\/nar\/gkh074","article-title":"DBTBS: database of transcriptional regulation in <italic>Bacillus subtilis<\/italic> and its contribution to comparative genomics.","volume":"32","author":"Y Makita","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"3625","DOI":"10.1093\/nar\/gkg545","article-title":"ELM server: A new resource for investigating short functional sites in modular eukaryotic proteins.","volume":"31","author":"P Puntervoll","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"D227","DOI":"10.1093\/nar\/gkj063","article-title":"The PROSITE database.","volume":"34","author":"N Hulo","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1093\/nar\/28.1.228","article-title":"Increased coverage of protein families with the blocks database servers.","volume":"28","author":"JG Henikoff","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1093\/nar\/gkg030","article-title":"PRINTS and its automatic supplement, prePRINTS.","volume":"31","author":"TK Attwood","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1587","DOI":"10.1002\/pro.5560040817","article-title":"Finding flexible patterns in unaligned protein sequences.","volume":"4","author":"I Jonassen","year":"1995","journal-title":"Protein Sci"},{"key":"ref20","first-page":"95","article-title":"Hidden Markov models for sequence analysis: extension and analysis of the basic method.","volume":"12","author":"R Hughey","year":"1996","journal-title":"Comput Appl Biosci"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"846","DOI":"10.1093\/bioinformatics\/14.10.846","article-title":"Hidden Markov models for detecting remote protein homologies.","volume":"14","author":"K Karplus","year":"1998","journal-title":"Bioinformatics"},{"key":"ref22","first-page":"114","article-title":"Multiple alignment using hidden Markov models.","volume":"3","author":"SR Eddy","year":"1995","journal-title":"Proc Int Conf Intell Syst Mol Biol"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1093\/bioinformatics\/14.4.317","article-title":"Automatic extraction of motifs represented in the hidden Markov model from a number of DNA sequences.","volume":"14","author":"T Yada","year":"1998","journal-title":"Bioinformatics"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1126\/science.8211139","article-title":"Detecting subtle sequence signals: a Gibbs sampling strategy for multiple alignment.","volume":"262","author":"CE Lawrence","year":"1993","journal-title":"Science"},{"key":"ref25","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 Res"},{"key":"ref26","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"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1093\/nar\/gkh169","article-title":"Finding functional sequence elements by multiple local alignment.","volume":"32","author":"MC Frith","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"ref28","first-page":"21","article-title":"The value of prior knowledge in discovering motifs with MEME.","volume":"3","author":"TL Bailey","year":"1995"},{"key":"ref29","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":"ref30","first-page":"327","article-title":"Dirichlet mixtures: a method for improved detection of weak but significant protein sequence homology.","volume":"12","author":"K Sj\u00f6lander","year":"1996","journal-title":"Comput Appl Biosci"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1186\/1471-2105-7-486","article-title":"GibbsST: a Gibbs sampling method for motif discovery with enhanced resistance to local optima.","volume":"7","author":"K Shida","year":"2006","journal-title":"BMC Bioinformatics"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1016\/0022-2836(87)90478-5","article-title":"A new algorithm for best subsequence alignments with application to tRNA-rRNA comparisons.","volume":"197","author":"MS Waterman","year":"1987","journal-title":"J Mol Biol"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"W362","DOI":"10.1093\/nar\/gkl124","article-title":"ScanProsite: detection of PROSITE signature matches and ProRule-associated functional and structural residues in proteins.","volume":"34","author":"E de Castro","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"D154","DOI":"10.1093\/nar\/gki070","article-title":"The Universal Protein Resource (UniProt).","volume":"33","author":"A Bairoch","year":"2005","journal-title":"Nucleic Acids Res"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1093\/nar\/29.1.323","article-title":"BAliBASE (Benchmark Alignment dataBASE): enhancements for repeats, transmembrane sequences and circular permutations.","volume":"29","author":"A Bahr","year":"2001","journal-title":"Nucleic Acids Res"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1093\/bioinformatics\/17.8.713","article-title":"Evaluation of protein multiple alignments by SAM-T99 using the BAliBASE multiple alignment test set.","volume":"17","author":"K Karplus","year":"2001","journal-title":"Bioinformatics"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1186\/1471-2105-6-298","article-title":"Kalign\u2013an accurate and fast multiple sequence alignment algorithm.","volume":"6","author":"T Lassmann","year":"2005","journal-title":"BMC Bioinformatics"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1101\/gr.2821705","article-title":"ProbCons: Probabilistic consistency-based multiple sequence alignment.","volume":"15","author":"CB Do","year":"2005","journal-title":"Genome Res"},{"key":"ref39","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":"ref40","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1038\/nmeth731","article-title":"Kinomics: methods for deciphering the kinome.","volume":"2","author":"SA Johnson","year":"2005","journal-title":"Nat Methods"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/j.bbapap.2005.07.036","article-title":"Substrate specificity of protein kinases and computational prediction of substrates.","volume":"1754","author":"B Kobe","year":"2005","journal-title":"Biochim Biophys Acta"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"676","DOI":"10.1016\/j.sbi.2006.10.008","article-title":"Docking interactions in protein kinase and phosphatase networks.","volume":"16","author":"A Rem\u00e9nyi","year":"2006","journal-title":"Curr Opin Struct Biol"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1186\/1471-2105-5-79","article-title":"Phospho.ELM: a database of experimentally verified phosphorylation sites in eukaryotic proteins.","volume":"5","author":"F Diella","year":"2004","journal-title":"BMC Bioinformatics"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1038\/nbt0307-285","article-title":"A curated compendium of phosphorylation motifs.","volume":"25","author":"R Amanchy","year":"2007","journal-title":"Nat Biotechnol"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1046\/j.1471-4159.2003.01647.x","article-title":"CIP98, a novel PDZ domain protein, is expressed in the central nervous system and interacts with calmodulin-dependent serine kinase.","volume":"85","author":"CC Yap","year":"2003","journal-title":"J Neurochem"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"3145","DOI":"10.1093\/emboj\/16.11.3145","article-title":"The LIM-only protein Lmo2 is a bridging molecule assembling an erythroid, DNA-binding complex which includes the TAL1, E47, GATA-1 and Ldb1\/NLI proteins.","volume":"16","author":"IA Wadman","year":"1997","journal-title":"EMBO J"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"3136","DOI":"10.1182\/blood-2004-04-1603","article-title":"Global regulation of erythroid gene expression by transcription factor GATA-1.","volume":"104","author":"JJ Welch","year":"2004","journal-title":"Blood"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"2687","DOI":"10.1128\/MCB.00493-06","article-title":"TAL-1\/SCL and its partners E47 and LMO2 up-regulate VE-cadherin expression in endothelial cells.","volume":"27","author":"V Deleuze","year":"2007","journal-title":"Mol Cell Biol"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"5330","DOI":"10.1128\/MCB.20.14.5330-5342.2000","article-title":"A pentamer transcriptional complex including tal-1 and retinoblastoma protein downmodulates c-kit expression in normal erythroblasts.","volume":"20","author":"L Vitelli","year":"2000","journal-title":"Mol Cell Biol"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"1439","DOI":"10.1128\/MCB.24.4.1439-1452.2004","article-title":"SCL assembles a multifactorial complex that determines glycophorin A expression.","volume":"24","author":"R Lahlil","year":"2004","journal-title":"Mol Cell Biol"},{"key":"ref51","doi-asserted-by":"crossref","first-page":"2799","DOI":"10.1242\/dev.126.12.2799","article-title":"Different sequence requirements for expression in erythroid and megakaryocytic cells within a regulatory element upstream of the GATA-1 gene.","volume":"126","author":"P Vyas","year":"1999","journal-title":"Development"},{"key":"ref52","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1634\/stemcells.22-2-216","article-title":"IL-3-dependent early erythropoiesis is stimulated by autocrine transforming growth factor beta.","volume":"22","author":"RM B\u00f6hmer","year":"2004","journal-title":"Stem Cells"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1093\/bioinformatics\/bth088","article-title":"GOstat: find statistically overrepresented Gene Ontologies within a group of genes.","volume":"20","author":"T Beissbarth","year":"2004","journal-title":"Bioinformatics"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1038\/75556","article-title":"Gene ontology: tool for the unification of biology.","volume":"25","author":"M Ashburner","year":"2000","journal-title":"Nat Genet"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1016\/j.bbrc.2007.10.071","article-title":"The Lim-only protein LMO2 acts as a positive regulator of erythroid differentiation.","volume":"364","author":"A Hansson","year":"2007","journal-title":"Biochem Biophys Res Commun"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1038\/nrg1315","article-title":"Applied bioinformatics for the identification of regulatory elements.","volume":"5","author":"WW Wasserman","year":"2004","journal-title":"Nat Rev Genet"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"R17","DOI":"10.1093\/hmg\/ddl046","article-title":"Non-coding RNA.","volume":"1","author":"JS Mattick","year":"2006","journal-title":"Hum Mol Genet 15 Spec No"},{"key":"ref58","article-title":"Biological sequence analysis: Probabilistic models of proteins and nucleic acids","author":"R Durbin","year":"2000"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"1546","DOI":"10.1093\/bioinformatics\/bth126","article-title":"Combining partial order alignment and progressive multiple sequence alignment increases alignment speed and scalability to very large alignment problems.","volume":"20","author":"C Grasso","year":"2004","journal-title":"Bioinformatics"},{"key":"ref60","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1186\/1471-2105-8-381","article-title":"PFAAT version 2.0 : A tool for editing, annotating, and analyzing multiple sequence alignments.","volume":"8","author":"D Caffrey","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"ref61","doi-asserted-by":"crossref","first-page":"6097","DOI":"10.1093\/nar\/18.20.6097","article-title":"Sequence logos: a new way to display consensus sequences.","volume":"18","author":"TD Schneider","year":"1990","journal-title":"Nucleic Acids Res"}],"container-title":["PLoS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1000071","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T04:01:57Z","timestamp":1631246517000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1000071"}},"subtitle":[],"editor":[{"given":"Gary","family":"Stormo","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2008,5,9]]},"references-count":61,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2008,5,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1000071","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,5,9]]}}}