{"id":"https://openalex.org/W2557972923","doi":"https://doi.org/10.1145/2975167.2985652","title":"Prediction of Cell Type Specific Transcription Factor Binding Site Occupancy","display_name":"Prediction of Cell Type Specific Transcription Factor Binding Site Occupancy","publication_year":2016,"publication_date":"2016-10-02","ids":{"openalex":"https://openalex.org/W2557972923","doi":"https://doi.org/10.1145/2975167.2985652","mag":"2557972923"},"language":"en","primary_location":{"id":"doi:10.1145/2975167.2985652","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2975167.2985652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086261793","display_name":"Faizy Ahsan","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Faizy Ahsan","raw_affiliation_strings":["McGill University, Sherbrooke Street West, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Sherbrooke Street West, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065836447","display_name":"Doina Precup","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Doina Precup","raw_affiliation_strings":["McGill University, Sherbrooke Street West, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Sherbrooke Street West, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065720651","display_name":"Mathieu Blanchette","orcid":"https://orcid.org/0000-0002-9555-860X"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mathieu Blanchette","raw_affiliation_strings":["McGill University, Sherbrooke Street West, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Sherbrooke Street West, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086261793"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09645576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"497","last_page":"498"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9980999827384949,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9980999827384949,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9977999925613403,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.995199978351593,"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/transcription-factor","display_name":"Transcription factor","score":0.7062220573425293},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6177592277526855},{"id":"https://openalex.org/keywords/dna-binding-site","display_name":"DNA binding site","score":0.6028790473937988},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.5517006516456604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5002727508544922},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.49530544877052307},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4809345602989197},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.45885542035102844},{"id":"https://openalex.org/keywords/occupancy","display_name":"Occupancy","score":0.4584609270095825},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.4460085332393646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3841080069541931},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.36149001121520996},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.3330882787704468},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29230284690856934},{"id":"https://openalex.org/keywords/promoter","display_name":"Promoter","score":0.2464548945426941},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.21973687410354614},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1532270312309265},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.08094221353530884}],"concepts":[{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.7062220573425293},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6177592277526855},{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.6028790473937988},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.5517006516456604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5002727508544922},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.49530544877052307},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4809345602989197},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.45885542035102844},{"id":"https://openalex.org/C160331591","wikidata":"https://www.wikidata.org/wiki/Q7075743","display_name":"Occupancy","level":2,"score":0.4584609270095825},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.4460085332393646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3841080069541931},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.36149001121520996},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.3330882787704468},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29230284690856934},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.2464548945426941},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.21973687410354614},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1532270312309265},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.08094221353530884},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2975167.2985652","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2975167.2985652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1554944419","https://openalex.org/W1614298861","https://openalex.org/W1989338936","https://openalex.org/W2099351601","https://openalex.org/W2118608526","https://openalex.org/W2135963245","https://openalex.org/W2163485494","https://openalex.org/W2259938310","https://openalex.org/W2950577311","https://openalex.org/W2997591727","https://openalex.org/W3215186461"],"related_works":["https://openalex.org/W2073661767","https://openalex.org/W2143211236","https://openalex.org/W2380185347","https://openalex.org/W2370034659","https://openalex.org/W2103777723","https://openalex.org/W2159636084","https://openalex.org/W2610941444","https://openalex.org/W2117168988","https://openalex.org/W2154430121","https://openalex.org/W2162836426"],"abstract_inverted_index":{"We":[0,102],"propose":[1],"a.":[2],"machine":[3],"learning":[4,23],"approach":[5],"to":[6,131,175],"predict":[7,178],"the":[8,28,33,39,47,76,86,99,140,164,185],"particular":[9],"cell":[10,54],"type":[11],"where":[12],"a":[13,19,72,117],"given":[14],"transcription":[15,44,137,154],"factor":[16,155],"can":[17,128,145],"bind":[18],"DNA":[20,29],"sequence.":[21],"The":[22,90],"models":[24],"are":[25,61],"trained":[26],"on":[27,64,107],"sequences":[30],"provided":[31],"from":[32],"publicly":[34],"available":[35],"ChIPseq":[36],"experiments":[37],"of":[38,68,88,125,136,149,170],"ENCODE":[40],"project":[41],"for":[42,98],"52":[43],"factors":[45],"across":[46],"GM12878,":[48],"K562,":[49],"HeLa,":[50],"H1-hESC":[51],"and":[52,71,127,183],"HepG2":[53],"lines.":[55],"Three":[56],"different":[57],"feature":[58],"extraction":[59],"methods":[60],"used":[62,97,130,147],"based":[63,106],"k-mer":[65],"representations,":[66],"counts":[67,110],"known":[69,108],"motifs,":[70],"new":[73],"model":[74],"called":[75],"skip":[77,141],"gram":[78,142],"model,":[79],"which":[80,144],"has":[81],"become":[82],"very":[83],"popular":[84],"in":[85],"analysis":[87],"text.":[89],"logistic":[91],"regression":[92],"with":[93,121],"\u21131":[94],"penalty":[95],"is":[96],"classification":[100],"task.":[101],"find":[103],"that":[104],"predictors":[105,171],"motifs":[109],"detect":[111],"cell-type":[112,179],"specific":[113,180],"signatures":[114],"better":[115,177],"than":[116],"previously":[118],"published":[119],"method,":[120],"mean":[122],"AUC":[123],"improvement":[124],"0.18":[126],"be":[129,146,173],"identify":[132],"t":[133],"he":[134],"interaction":[135],"factors.":[138],"Remarkably,":[139],"approach,":[143],"without":[148],"any":[150],"prior":[151],"knowledge":[152],"about":[153],"binding":[156],"sit":[157],"es,":[158],"performs":[159],"almost":[160],"as":[161,163],"well":[162],"motif-based":[165],"method.":[166],"Overall,":[167],"our":[168],"family":[169],"will":[172],"useful":[174],"both":[176],"TF":[181],"occupancy":[182],"understand":[184],"mechanisms":[186],"underlying":[187],"this":[188],"phenomenon.":[189]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}