{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:23:34Z","timestamp":1773275014841,"version":"3.50.1"},"reference-count":118,"publisher":"Oxford University Press (OUP)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006,3,1]]},"DOI":"10.1093\/bib\/bbk001","type":"journal-article","created":{"date-parts":[[2006,2,3]],"date-time":"2006-02-03T20:32:56Z","timestamp":1138998776000},"page":"2-24","source":"Crossref","is-referenced-by-count":58,"title":["Statistical significance in biological sequence analysis"],"prefix":"10.1093","volume":"7","author":[{"given":"Alexander Yu.","family":"Mitrophanov","sequence":"first","affiliation":[{"name":"Alexander Yu. Mitrophanov is a postdoctoral fellow at the School of Biology, Georgia Institute of Technology. His research interests include applications of probabilistic methods in different areas of bioinformatics and computational biology."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Borodovsky","sequence":"additional","affiliation":[{"name":"Mark Borodovsky is a Regents\u2019 Professor at the School of Biology, Georgia Institute of Technology, and the Wallace H. Coulter Department of Biomedical Engineering at Georgia Institute of Technology and Emory University. His research interests include development of statistical methods for biological sequence analysis and identifying functionally important features of DNA and proteins in the conte"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","reference":[{"key":"key\n\t\t\t\t20180216214125_B1","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1016\/S0968-0004(98)01274-2","article-title":"Conservation of gene order: a fingerprint of proteins that physically interact","volume":"23","author":"Dandekar","year":"1998","journal-title":"Trends Biochem Sci"},{"key":"key\n\t\t\t\t20180216214125_B2","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/47056","article-title":"Protein interaction maps for complete genomes based on gene fusion events","volume":"402","author":"Enright","year":"1999","journal-title":"Nature"},{"key":"key\n\t\t\t\t20180216214125_B3","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1093\/bioinformatics\/15.10.776","article-title":"Genes regulated cooperatively by one or more transcription factors and their identification in whole eukaryotic genomes","volume":"15","author":"Wagner","year":"1999","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B4","first-page":"526","article-title":"Significance of nucleotide sequence alignments: a method for random sequence permutation that preserves dinucleotide and codon usage","volume":"2","author":"Altschul","year":"1985","journal-title":"Mol Biol Evol"},{"key":"key\n\t\t\t\t20180216214125_B5","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.1093\/nar\/20.6.1363","article-title":"Statistical analyses of counts and distributions of restriction sites in DNA sequences","volume":"20","author":"Karlin","year":"1992","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B6","doi-asserted-by":"crossref","first-page":"5800","DOI":"10.1073\/pnas.82.17.5800","article-title":"Comparative statistics for DNA and protein sequences: single-sequence analysis","volume":"82","author":"Karlin","year":"1985","journal-title":"Proc Natl Acad Sci USA"},{"key":"key\n\t\t\t\t20180216214125_B7","first-page":"133","article-title":"Patterns in DNA and amino acid sequences and their statistical significance","volume-title":"Mathematical Methods for DNA Sequences","author":"Karlin","year":"1989"},{"key":"key\n\t\t\t\t20180216214125_B8","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1093\/nar\/12.1Part1.215","article-title":"On the statistical significance of nucleic acid similarities","volume":"12","author":"Lipman","year":"1984","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B9","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1038\/ng0294-119","article-title":"Issues in searching molecular sequence databases","volume":"6","author":"Altschul","year":"1994","journal-title":"Nature Genet"},{"key":"key\n\t\t\t\t20180216214125_B10","first-page":"53","article-title":"Sequence alignments","volume-title":"Mathematical Methods for DNA Sequences","author":"Waterman","year":"1989"},{"key":"key\n\t\t\t\t20180216214125_B11","first-page":"93","article-title":"Consensus patterns in sequences","author":"Waterman","year":"1989","journal-title":"Mathematical Methods for DNA Sequences"},{"key":"key\n\t\t\t\t20180216214125_B12","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-1923-9","author":"Lehmann","year":"1986","journal-title":"Testing Statistical Hypotheses"},{"key":"key\n\t\t\t\t20180216214125_B13","first-page":"431","article-title":"The statistical significance of nucleotide position-weight matrix matches","volume":"12","author":"Claverie","year":"1996","journal-title":"CABIOS"},{"key":"key\n\t\t\t\t20180216214125_B14","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1006\/jmbi.2000.3875","article-title":"Accurate formula for p-values of gapped local sequence and profile alignments","volume":"300","author":"Mott","year":"2000","journal-title":"J Mol Biol"},{"key":"key\n\t\t\t\t20180216214125_B15","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1006\/jmbi.1997.1525","article-title":"Empirical statistical estimates for sequence similarity searches","volume":"276","author":"Pearson","year":"1998","journal-title":"J Mol Biol"},{"key":"key\n\t\t\t\t20180216214125_B16","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1214\/ss\/1177010382","article-title":"Sequence comparison significance and Poisson approximation","volume":"9","author":"Waterman","year":"1994","journal-title":"Statist Sci"},{"key":"key\n\t\t\t\t20180216214125_B17","doi-asserted-by":"crossref","first-page":"5529","DOI":"10.1093\/nar\/12.13.5529","article-title":"On the statistical assessment of similarities in DNA sequencies","volume":"12","author":"Reich","year":"1984","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B18","doi-asserted-by":"crossref","first-page":"4625","DOI":"10.1073\/pnas.91.11.4625","article-title":"Rapid and accurate estimates of statistical significance for sequence database searches","volume":"91","author":"Waterman","year":"1994","journal-title":"Proc Natl Acad Sci USA"},{"key":"key\n\t\t\t\t20180216214125_B19","author":"Liu","year":"2001","journal-title":"Monte Carlo Strategies in Scientific Computing"},{"key":"key\n\t\t\t\t20180216214125_B20","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1093\/bioinformatics\/bti041","article-title":"CIS: compound importance sampling method for protein-DNA binding site p-value estimation","volume":"21","author":"Barash","year":"2005","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B21","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-3675-0","author":"Coles","year":"2001","journal-title":"An Introduction to Statistical Modeling of Extreme Values"},{"key":"key\n\t\t\t\t20180216214125_B22","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/S0097-8485(99)00008-X","article-title":"Significance of Z-value statistics of Smith-Waterman scores for protein alignments","volume":"23","author":"Comet","year":"1999","journal-title":"Computers Chem"},{"key":"key\n\t\t\t\t20180216214125_B23","doi-asserted-by":"crossref","first-page":"534","DOI":"10.1093\/bioinformatics\/btg440","article-title":"Fundamentals of massive automatic pairwise alignments of protein sequences: theoretical significance of Z-value statistics","volume":"20","author":"Bastien","year":"2004","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B24","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1093\/nar\/13.2.645","article-title":"The statistical distribution of nucleic acid similarities","volume":"13","author":"Smith","year":"1985","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B25","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1093\/bioinformatics\/15.7.563","article-title":"Identifying DNA and protein patterns with statistically significant alignments of multiple sequences","volume":"15","author":"Hertz","year":"1999","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B26","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/BF02458620","article-title":"Maximum-likelihood estimation of the statistical distribution of Smith\u2013Waterman local sequence similarity scores","volume":"54","author":"Mott","year":"1992","journal-title":"Bull Math Biol"},{"key":"key\n\t\t\t\t20180216214125_B27","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":"Meth Enzymol"},{"key":"key\n\t\t\t\t20180216214125_B28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1089\/10665270050081360","article-title":"Probabilistic and statistical properties of words: an overview","volume":"7","author":"Reinert","year":"2000","journal-title":"J Comp Biol"},{"key":"key\n\t\t\t\t20180216214125_B29","first-page":"117","article-title":"Some statistical aspects of the primary structure of nucleotide sequences","volume-title":"Mathematical Methods for DNA Sequences","author":"Tavar\u00e9","year":"1989"},{"key":"key\n\t\t\t\t20180216214125_B30","first-page":"1144","article-title":"Statistical patterns in the primary structures of functional regions in the genome of E. coli. 3. Computer recognition of coding regions","volume":"20","author":"Borodovskii","year":"1986","journal-title":"Mol Biol"},{"key":"key\n\t\t\t\t20180216214125_B31","first-page":"826","article-title":"Statistical patterns in the primary structures of functional regions in the genome of E. coli. 1. Frequency characteristics","volume":"20","author":"Borodovskii","year":"1986","journal-title":"Mol Biol"},{"key":"key\n\t\t\t\t20180216214125_B32","first-page":"833","article-title":"Statistical patterns in the primary structures of functional regions in the genome of E. coli. 2. Nonuniform Markov models","volume":"20","author":"Borodovskii","year":"1986","journal-title":"Mol Biol"},{"key":"key\n\t\t\t\t20180216214125_B33","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/BF02458838","article-title":"Codon preference and primary sequence structure in protein-coding regions","volume":"51","author":"Tavar\u00e9","year":"1989","journal-title":"Bull Math Biol"},{"key":"key\n\t\t\t\t20180216214125_B34","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1214\/ss\/1028905933","article-title":"Statistical methods for DNA sequence segmentation","volume":"13","author":"Braun","year":"1998","journal-title":"Statist Sci"},{"key":"key\n\t\t\t\t20180216214125_B35","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1006\/jmbi.1997.0951","article-title":"Prediction of complete gene structures in human genomic DNA","volume":"268","author":"Burge","year":"1997","journal-title":"J Mol Biol"},{"key":"key\n\t\t\t\t20180216214125_B36","doi-asserted-by":"crossref","first-page":"4768","DOI":"10.1093\/nar\/22.22.4768","article-title":"A hidden Markov model that finds genes in E. coli DNA","volume":"22","author":"Krogh","year":"1994","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B37","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.1093\/nar\/26.4.1107","article-title":"GeneMark.hmm: new solutions for gene finding","volume":"26","author":"Lukashin","year":"1998","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B38","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":"key\n\t\t\t\t20180216214125_B39","doi-asserted-by":"crossref","first-page":"8880","DOI":"10.1073\/pnas.88.20.8880","article-title":"Distribution of glutamine and asparagine residues and their near neighbors in peptides and proteins","volume":"88","author":"Robinson","year":"1991","journal-title":"Proc Natl Acad Sci USA"},{"key":"key\n\t\t\t\t20180216214125_B40","doi-asserted-by":"crossref","first-page":"2994","DOI":"10.1093\/nar\/29.14.2994","article-title":"Improving the accuracy of PSI-BLAST protein database searches with composition-based statistics and other refinements","volume":"29","author":"Sch\u00e4ffer","year":"2001","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B41","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1098\/rstb.1994.0077","article-title":"Estimating statistical significance of sequence alignments","volume":"344","author":"Waterman","year":"1994","journal-title":"Philosophical Transactions: Biological Sciences"},{"key":"key\n\t\t\t\t20180216214125_B42","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1007\/BF02459930","article-title":"Poisson, compound Poisson and process approximations for testing statistical significance in sequence comparisons","volume":"54","author":"Goldstein","year":"1992","journal-title":"Bull Math Biol"},{"key":"key\n\t\t\t\t20180216214125_B43","doi-asserted-by":"crossref","first-page":"2264","DOI":"10.1073\/pnas.87.6.2264","article-title":"Methods for assessing the statistical significance of molecular sequence features by using general scoring schemes","volume":"87","author":"Karlin","year":"1990","journal-title":"Proc Natl Acad Sci USA"},{"key":"key\n\t\t\t\t20180216214125_B44","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1214\/aos\/1176347615","article-title":"The Erd\u00f6s-R\u00e9nyi law in distribution, for coin tossing and sequence matching","volume":"18","author":"Arratia","year":"1990","journal-title":"Ann Statist"},{"key":"key\n\t\t\t\t20180216214125_B45","doi-asserted-by":"crossref","first-page":"3214","DOI":"10.1093\/nar\/gkf438","article-title":"Statistical significance of clusters of motifs represented by position specific scoring matrices in nucleotide sequences","volume":"30","author":"Frith","year":"2002","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B46","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1093\/bib\/5.3.217","article-title":"In silico representation and discovery of transcription factor binding sites","volume":"5","author":"Pavesi","year":"2004","journal-title":"Brief Bioinform"},{"key":"key\n\t\t\t\t20180216214125_B47","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1089\/cmb.1996.3.425","article-title":"Poisson process approximation for sequence repeats, and sequencing by hybridization","volume":"3","author":"Arratia","year":"1996","journal-title":"J Comp Biol"},{"key":"key\n\t\t\t\t20180216214125_B48","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1093\/nar\/gkh246","article-title":"Statistical analysis of over-represented words in human promoter sequences","volume":"32","author":"Mari\u00f1o-Ram\u00edrez","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B49","doi-asserted-by":"crossref","first-page":"5549","DOI":"10.1093\/nar\/gkf669","article-title":"Discovery of novel transcription factor binding sites by statistical overrepresentation","volume":"30","author":"Sinha","year":"2002","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B50","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1093\/bioinformatics\/bth471","article-title":"DWE: discriminating word enumerator","volume":"21","author":"Sumazin","year":"2005","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B51","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1093\/bioinformatics\/btg005","article-title":"Alignment-free sequence-comparison\u2014a review","volume":"19","author":"Vinga","year":"2003","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B52","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1089\/10665270050081469","article-title":"An overview on the distribution of word counts in Markov chains","volume":"7","author":"Schbath","year":"2000","journal-title":"J Comp Biol"},{"key":"key\n\t\t\t\t20180216214125_B53","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1089\/106652701752236179","article-title":"Numerical comparison of several approximations of the word count distribution in random sequences","volume":"8","author":"Robin","year":"2001","journal-title":"J Comp Biol"},{"key":"key\n\t\t\t\t20180216214125_B54","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1126\/science.1621093","article-title":"Chance and statistical significance in protein and DNA sequence analysis","volume":"257","author":"Karlin","year":"1992","journal-title":"Science"},{"key":"key\n\t\t\t\t20180216214125_B55","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1214\/aos\/1176347616","article-title":"Statistical composition of high-scoring segments from molecular sequences","volume":"18","author":"Karlin","year":"1990","journal-title":"Ann Statist"},{"key":"key\n\t\t\t\t20180216214125_B56","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1214\/aoms\/1177692642","article-title":"Extreme values in the GI\/G\/1 queue","volume":"43","author":"Iglehart","year":"1972","journal-title":"Ann Math Statist"},{"key":"key\n\t\t\t\t20180216214125_B57","doi-asserted-by":"crossref","first-page":"113","DOI":"10.2307\/1427732","article-title":"Limit distributions of maximal segmental score among Markov-dependent partial sums","volume":"24","author":"Karlin","year":"1992","journal-title":"Adv Appl Probab"},{"key":"key\n\t\t\t\t20180216214125_B58","doi-asserted-by":"crossref","first-page":"5873","DOI":"10.1073\/pnas.90.12.5873","article-title":"Applications and statistics for multiple high-scoring segments in molecular sequences","volume":"90","author":"Karlin","year":"1993","journal-title":"Proc Natl Acad Sci USA"},{"key":"key\n\t\t\t\t20180216214125_B59","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1098\/rstb.1994.0078","article-title":"Statistical studies of biomolecular sequences: score-based methods","volume":"344","author":"Karlin","year":"1994","journal-title":"Philosophical Transactions: Biological Sciences"},{"key":"key\n\t\t\t\t20180216214125_B60","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":"key\n\t\t\t\t20180216214125_B61","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1016\/0022-2836(82)90398-9","article-title":"An improved algorithm for matching biological sequences","volume":"162","author":"Gotoh","year":"1982","journal-title":"J Mol Biol"},{"key":"key\n\t\t\t\t20180216214125_B62","doi-asserted-by":"crossref","first-page":"1158","DOI":"10.1093\/bioinformatics\/17.12.1158","article-title":"Estimation of P-values for global alignments of protein sequences","volume":"17","author":"Webber","year":"2001","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B63","first-page":"345","article-title":"A model of evolutionary change in proteins","volume-title":"Atlas of Protein Sequence and Structure","author":"Dayhoff","year":"1978"},{"key":"key\n\t\t\t\t20180216214125_B64","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":"key\n\t\t\t\t20180216214125_B65","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1126\/science.1604319","article-title":"Exhaustive matching of the entire protein sequence database","volume":"256","author":"Gonnet","year":"1992","journal-title":"Science"},{"key":"key\n\t\t\t\t20180216214125_B66","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":"key\n\t\t\t\t20180216214125_B67","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1016\/0022-2836(91)90193-A","article-title":"Amino acid substitution matrices from an information theoretic perspective","volume":"219","author":"Altschul","year":"1991","journal-title":"J Mol Biol"},{"key":"key\n\t\t\t\t20180216214125_B68","author":"Durbin","year":"1991","journal-title":"Biological Sequence Analysis: Probabilistic Models of Proteins and Nucleic Acids"},{"key":"key\n\t\t\t\t20180216214125_B69","doi-asserted-by":"crossref","first-page":"2022","DOI":"10.1214\/aop\/1176988493","article-title":"Limit distribution of maximal non-aligned two-sequence segmental score","volume":"22","author":"Dembo","year":"1994","journal-title":"Ann Probab"},{"key":"key\n\t\t\t\t20180216214125_B70","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1093\/nar\/29.2.351","article-title":"The estimation of statistical parameters for local alignment score distributions","volume":"29","author":"Altschul","year":"2001","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B71","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1089\/10665270252935449","article-title":"Rapid significance estimation in local sequence alignment with gaps","volume":"9","author":"Bundschuh","year":"2002","journal-title":"J Comp Biol"},{"key":"key\n\t\t\t\t20180216214125_B72","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1214\/aos\/1015951993","article-title":"Approximate p-values for local sequence alignments","volume":"28","author":"Siegmund","year":"2000","journal-title":"Ann Statist"},{"key":"key\n\t\t\t\t20180216214125_B73","doi-asserted-by":"crossref","first-page":"1027","DOI":"10.1214\/aos\/1056562473","article-title":"Correction: approximate p-values for local sequence alignments (vol 28, pg 657, 2000)","volume":"31","author":"Siegmund","year":"2003","journal-title":"Ann Statist"},{"key":"key\n\t\t\t\t20180216214125_B74","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1214\/aoap\/1177005208","article-title":"A phase transition for the score in matching random sequences allowing deletions","volume":"4","author":"Arratia","year":"1994","journal-title":"Ann Appl Probab"},{"key":"key\n\t\t\t\t20180216214125_B75","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1093\/bioinformatics\/18.9.1236","article-title":"The correlation error and finite-size correction in an ungapped sequence alignment","volume":"18","author":"Park","year":"2002","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B76","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1093\/bioinformatics\/14.3.279","article-title":"Statistics of large-scale sequence searching","volume":"14","author":"Spang","year":"1998","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B77","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1017\/S0021900200020039","article-title":"Finite-size corrections to Poisson approximations of rare events in renewal processes","volume":"38","author":"Spouge","year":"2001","journal-title":"J Appl Probab"},{"key":"key\n\t\t\t\t20180216214125_B78","doi-asserted-by":"crossref","first-page":"829","DOI":"10.3150\/bj\/1099579157","article-title":"Large deviations for global maxima of independent superadditive processes with negative drift and an application to optimal sequence alignments","volume":"10","author":"Grossmann","year":"2004","journal-title":"Bernoulli"},{"key":"key\n\t\t\t\t20180216214125_B79","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1089\/106652702760138637","article-title":"Estimating and evaluating the statistics of gapped local-alignment scores","volume":"9","author":"Bailey","year":"2002","journal-title":"J Comp Biol"},{"key":"key\n\t\t\t\t20180216214125_B80","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1089\/cmb.1999.6.91","article-title":"Approximate statistics of gapped alignments","volume":"6","author":"Mott","year":"1999","journal-title":"J Comp Biol"},{"key":"key\n\t\t\t\t20180216214125_B81","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1016\/S0097-8485(01)00074-2","article-title":"Sequence alignment: an approximation law for the Z-value with applications to databank scanning","volume":"25","author":"Bacro","year":"2001","journal-title":"Computers Chem"},{"key":"key\n\t\t\t\t20180216214125_B82","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":"key\n\t\t\t\t20180216214125_B83","doi-asserted-by":"crossref","first-page":"2444","DOI":"10.1073\/pnas.85.8.2444","article-title":"Improved tools for biological sequence comparison","volume":"85","author":"Pearson","year":"1988","journal-title":"Proc Natl Acad Sci USA"},{"key":"key\n\t\t\t\t20180216214125_B84","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.1093\/bioinformatics\/15.12.1000","article-title":"IMPALA: matching a protein sequence against a collection of PSI-BLAST-constructed position-specific score matrices","volume":"15","author":"Sch\u00e4ffer","year":"1999","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B85","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1016\/S0076-6879(96)66023-6","article-title":"Progressive alignment of amino acid sequences and construction of phylogenetic trees from them","volume":"266","author":"Feng","year":"1996","journal-title":"Meth Enzymol"},{"key":"key\n\t\t\t\t20180216214125_B86","doi-asserted-by":"crossref","first-page":"4673","DOI":"10.1093\/nar\/22.22.4673","article-title":"CLUSTAL W: improving the sensitivity of progressive multiple sequence alignment through sequence weighting, position-specific gap penalties and weight matrix choice","volume":"22","author":"Thompson","year":"1994","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B87","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1006\/jmbi.2000.4042","article-title":"T-Coffee: a novel method for fast and accurate multiple sequence alignment","volume":"302","author":"Notredame","year":"2000","journal-title":"J Mol Biol"},{"key":"key\n\t\t\t\t20180216214125_B88","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2105-5-113","article-title":"MUSCLE: a multiple sequence alignment method with reduced time and space complexity","volume":"5","author":"Edgar","year":"2004","journal-title":"BMC Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B89","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1093\/nar\/gki198","article-title":"MAFFT version 5: improvement in accuracy of multiple sequence alignment","volume":"33","author":"Katoh","year":"2005","journal-title":"Nucleic Acids Res"},{"key":"key\n\t\t\t\t20180216214125_B90","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2105-6-66","article-title":"DIALIGN-T: an improved algorithm for segment-based multiple sequence alignment","volume":"6","author":"Subramanian","year":"2005","journal-title":"BMC Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B91","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1002\/prot.340090304","article-title":"A workbench for multiple alignment construction and analysis","volume":"9","author":"Schuler","year":"1991","journal-title":"PROTEINS"},{"key":"key\n\t\t\t\t20180216214125_B92","first-page":"28","volume-title":"Fitting a mixture model by expectation maximization to discover motifs in biopolymers","author":"Bailey","year":"1994"},{"key":"key\n\t\t\t\t20180216214125_B93","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":"Lawrence","year":"1993","journal-title":"Science"},{"key":"key\n\t\t\t\t20180216214125_B94","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1073\/pnas.0409240102","article-title":"An Eulerian path approach to local multiple alignment for DNA sequences","volume":"102","author":"Zhang","year":"2005","journal-title":"Proc Natl Acad Sci USA"},{"key":"key\n\t\t\t\t20180216214125_B95","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1006\/jmbi.2001.5187","article-title":"Towards a reliable objective function for multiple sequence alignments","volume":"314","author":"Thompson","year":"2001","journal-title":"J Mol Biol"},{"key":"key\n\t\t\t\t20180216214125_B96","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/978-3-540-30219-3_10","article-title":"A fast reliable algorithms to estimate the p-value of the multinomial llr statistic","volume":"3240","author":"Keich","year":"2004","journal-title":"Lect Notes Comp Sci"},{"key":"key\n\t\t\t\t20180216214125_B97","first-page":"89","article-title":"Methods for calculating the probabilities of finding patterns in sequences","volume":"5","author":"Staden","year":"1989","journal-title":"CABIOS"},{"key":"key\n\t\t\t\t20180216214125_B98","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/0097-8485(94)85024-0","article-title":"Some useful statistical properties of position weight matrices","volume":"18","author":"Claverie","year":"1994","journal-title":"Computers Chem"},{"key":"key\n\t\t\t\t20180216214125_B99","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/0076-6879(90)83011-W","article-title":"Profile analysis","volume":"183","author":"Gribskov","year":"1990","journal-title":"Meth Enzymol"},{"key":"key\n\t\t\t\t20180216214125_B100","doi-asserted-by":"crossref","first-page":"4355","DOI":"10.1073\/pnas.84.13.4355","article-title":"Profile analysis: detection of distantly related proteins","volume":"84","author":"Gribskov","year":"1987","journal-title":"Proc Natl Acad Sci USA"},{"key":"key\n\t\t\t\t20180216214125_B101","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/S0076-6879(96)66015-7","article-title":"Identification of sequence patterns with profile analysis","volume":"266","author":"Gribskov","year":"1996","journal-title":"Meth Enzymol"},{"key":"key\n\t\t\t\t20180216214125_B102","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1093\/bioinformatics\/16.1.16","article-title":"DNA binding sites: representation and discovery","volume":"16","author":"Stormo","year":"2000","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B103","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1089\/cmb.1998.5.211","article-title":"Methods and statistics for combining motif match scores","volume":"5","author":"Bailey","year":"1998","journal-title":"J Comp Biol"},{"key":"key\n\t\t\t\t20180216214125_B104","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1093\/bioinformatics\/14.1.48","article-title":"Combining evidence using p-values: application to sequence homology searches","volume":"14","author":"Bailey","year":"1998","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B105","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1089\/cmb.1994.1.93","article-title":"Approximations to profile score distribution","volume":"1","author":"Goldstein","year":"1994","journal-title":"J Comp Biol"},{"key":"key\n\t\t\t\t20180216214125_B106","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1089\/cmb.1997.4.45","article-title":"Score distributions for simultaneous matching to multiple motifs","volume":"4","author":"Bailey","year":"1997","journal-title":"J Comp Biol"},{"key":"key\n\t\t\t\t20180216214125_B107","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/0076-6879(90)83014-Z","article-title":"Searching for patterns in protein and nucleic acid sequences","volume":"183","author":"Staden","year":"1990","journal-title":"Meth Enzymol"},{"key":"key\n\t\t\t\t20180216214125_B108","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1089\/106652704773416858","article-title":"Determination of local statistical significance of patterns in Markov sequences with application to promoter element identification","volume":"11","author":"Huang","year":"2004","journal-title":"J Comp Biol"},{"key":"key\n\t\t\t\t20180216214125_B109","doi-asserted-by":"crossref","first-page":"i169","DOI":"10.1093\/bioinformatics\/btg1021","article-title":"Identification of functional clusters of transcription factor binding motifs in genome sequences: the MSCAN algorithm","volume":"19","author":"Johansson","year":"2003","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B110","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1093\/bib\/5.2.118","article-title":"Probabilistic methods of identifying genes in prokaryotic genomes: connections to the HMM theory","volume":"5","author":"Azad","year":"2004","journal-title":"Brief Bioinform"},{"key":"key\n\t\t\t\t20180216214125_B111","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2105-4-21","article-title":"EasyGene\u2014a prokaryotic gene finder that ranks ORFs by statistical significance","volume":"4","author":"Larsen","year":"2003","journal-title":"BMC Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B112","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1073\/pnas.91.3.1059","article-title":"Hidden Markov models of biological primary sequence information","volume":"91","author":"Baldi","year":"1994","journal-title":"Proc Natl Acad Sci USA"},{"key":"key\n\t\t\t\t20180216214125_B113","doi-asserted-by":"crossref","first-page":"1501","DOI":"10.1006\/jmbi.1994.1104","article-title":"Hidden Markov models in computational biology. Applications to protein modeling","volume":"235","author":"Krogh","year":"1994","journal-title":"J Mol Biol"},{"key":"key\n\t\t\t\t20180216214125_B114","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1093\/bioinformatics\/14.9.755","article-title":"Profile hidden Markov models","volume":"14","author":"Eddy","year":"1998","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180216214125_B115","first-page":"95","article-title":"Hidden Markov models for sequence analysis: extension and analysis of the basic method","volume":"12","author":"Hughey","year":"1996","journal-title":"CABIOS"},{"key":"key\n\t\t\t\t20180216214125_B116","unstructured":"ftp:\/\/ftp.genetics.wustl.edu\/pub\/eddy\/hmmer\/CURRENT\/ Userguide.pdf. Last accessed 13 January 2006"},{"key":"key\n\t\t\t\t20180216214125_B117","first-page":"191","article-title":"Scoring hidden Markov models","volume":"13","author":"Barrett","year":"1997","journal-title":"CABIOS"},{"key":"key\n\t\t\t\t20180216214125_B118","first-page":"407","article-title":"Discovering simple DNA sequences by the algorithmic significance method","volume":"9","author":"Milosavljevi\u0107","year":"1993","journal-title":"CABIOS"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bib\/article-pdf\/7\/1\/2\/23992288\/bbk001.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,2,16]],"date-time":"2018-02-16T21:42:33Z","timestamp":1518817353000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/7\/1\/2\/262762"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,3,1]]},"references-count":118,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2006,3,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbk001","relation":{},"ISSN":["1467-5463"],"issn-type":[{"value":"1467-5463","type":"print"}],"subject":[],"published-other":{"date-parts":[[2006,3]]},"published":{"date-parts":[[2006,3,1]]}}}