{"id":"https://openalex.org/W2103630240","doi":"https://doi.org/10.1093/bioinformatics/bti1044","title":"Computing the P-value of the information content from an alignment of multiple sequences","display_name":"Computing the P-value of the information content from an alignment of multiple sequences","publication_year":2005,"publication_date":"2005-06-01","ids":{"openalex":"https://openalex.org/W2103630240","doi":"https://doi.org/10.1093/bioinformatics/bti1044","mag":"2103630240","pmid":"https://pubmed.ncbi.nlm.nih.gov/15961473"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti1044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti1044","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/suppl_1/i311/526509/bti1044.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/21/suppl_1/i311/526509/bti1044.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062774997","display_name":"Niranjan Nagarajan","orcid":"https://orcid.org/0000-0003-0850-5604"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"N. Nagarajan","raw_affiliation_strings":["Computer Science Department 4130 Upson Hall Cornell University Ithaca, NY 14853, USA","Computer Science Department 4130 Upson Hall Cornell University Ithaca, NY 14853, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department 4130 Upson Hall Cornell University Ithaca, NY 14853, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Computer Science Department 4130 Upson Hall Cornell University Ithaca, NY 14853, USA#TAB#","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072255443","display_name":"Neil Jones","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Jones","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California-San Diego, 9500 Gilman Drive, La Jolla, CA 92093, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California-San Diego, 9500 Gilman Drive, La Jolla, CA 92093, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068879102","display_name":"Uri Keich","orcid":"https://orcid.org/0000-0002-3209-5011"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"U. Keich","raw_affiliation_strings":["Computer Science Department 4130 Upson Hall Cornell University Ithaca, NY 14853, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department 4130 Upson Hall Cornell University Ithaca, NY 14853, USA#TAB#","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062774997"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":2.0225,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.85922374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"21","issue":"Suppl 1","first_page":"i311","last_page":"i318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.2777000069618225,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.2777000069618225,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.14300000667572021,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.06319999694824219,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.6553823351860046},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5903353095054626},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5440856218338013},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.36359548568725586},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21581050753593445},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1944330930709839},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1359131634235382}],"concepts":[{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.6553823351860046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5903353095054626},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5440856218338013},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.36359548568725586},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21581050753593445},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1944330930709839},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1359131634235382},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/bti1044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti1044","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/suppl_1/i311/526509/bti1044.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:15961473","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15961473","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bti1044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti1044","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/suppl_1/i311/526509/bti1044.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1547412389","https://openalex.org/W1592870802","https://openalex.org/W1708197474","https://openalex.org/W2003967338","https://openalex.org/W2018353793","https://openalex.org/W2081715952","https://openalex.org/W2087338137","https://openalex.org/W2149769193","https://openalex.org/W2170120409"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,94],"efficient":[2],"and":[3,14,30,58,80],"accurate":[4],"computation":[5],"of":[6,49,52,55,65,68],"P-values":[7,51],"is":[8,84],"an":[9],"essential":[10],"requirement":[11],"for":[12,46,62],"motif-finding":[13,27],"alignment":[15],"tools.":[16],"We":[17,40],"show":[18],"that":[19],"the":[20,37,47,50,63,66,81,89],"approximation":[21],"algorithms":[22,95],"used":[23],"in":[24,86,97],"two":[25,42],"popular":[26],"programs,":[28],"MEME":[29],"Consensus,":[31],"can":[32],"fail":[33],"to":[34,88],"accurately":[35],"compute":[36],"P-value.":[38],"RESULTS:":[39],"present":[41],"new":[43],"algorithms:":[44],"one":[45,61],"evaluation":[48,64],"a":[53,59,69],"range":[54],"motif":[56,71],"scores,":[57],"faster":[60],"P-value":[67],"single":[70],"score.":[72],"Both":[73],"exhibit":[74],"more":[75],"reliability":[76],"than":[77],"existing":[78,91],"algorithms,":[79],"latter":[82],"algorithm":[83],"comparable":[85],"speed":[87],"fastest":[90],"method.":[92],"AVAILABILITY:":[93],"described":[96],"this":[98],"paper":[99],"are":[100],"available":[101],"from":[102],"http://www.cs.cornell.edu/~keich":[103]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}
