{"id":"https://openalex.org/W3127565598","doi":"https://doi.org/10.1109/bibm49941.2020.9313437","title":"Phylogenetic Manifold Regularization: A semi-supervised approach to predict transcription factor binding sites","display_name":"Phylogenetic Manifold Regularization: A semi-supervised approach to predict transcription factor binding sites","publication_year":2020,"publication_date":"2020-12-16","ids":{"openalex":"https://openalex.org/W3127565598","doi":"https://doi.org/10.1109/bibm49941.2020.9313437","mag":"3127565598"},"language":"en","primary_location":{"id":"doi:10.1109/bibm49941.2020.9313437","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm49941.2020.9313437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028239106","display_name":"Alexandre Drouin","orcid":"https://orcid.org/0000-0001-7718-0319"},"institutions":[{"id":"https://openalex.org/I43406934","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03","country_code":"CA","type":"education","lineage":["https://openalex.org/I43406934"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alexandre Drouin","raw_affiliation_strings":["Universit\u00e9 laval, Qu\u00e9bec, Canada"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 laval, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I43406934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054812796","display_name":"Fran\u00e7ois Laviolette","orcid":"https://orcid.org/0000-0002-1937-2512"},"institutions":[{"id":"https://openalex.org/I43406934","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03","country_code":"CA","type":"education","lineage":["https://openalex.org/I43406934"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Francois Laviolette","raw_affiliation_strings":["Universit\u00e9 laval, Qu\u00e9bec, Canada"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 laval, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I43406934"]}]},{"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, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, 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, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086261793"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.0829,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4634905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"62","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.6023736596107483},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5966470837593079},{"id":"https://openalex.org/keywords/dna-binding-site","display_name":"DNA binding site","score":0.590782642364502},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5877252221107483},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5494890213012695},{"id":"https://openalex.org/keywords/transcription-factor","display_name":"Transcription factor","score":0.5456994771957397},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.49084049463272095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46746399998664856},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4345772862434387},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3690558969974518},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.35922539234161377},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3561371862888336},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3285719156265259},{"id":"https://openalex.org/keywords/promoter","display_name":"Promoter","score":0.2397795021533966},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.22162070870399475},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.1806803047657013},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15047788619995117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6023736596107483},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5966470837593079},{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.590782642364502},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5877252221107483},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5494890213012695},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.5456994771957397},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.49084049463272095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46746399998664856},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4345772862434387},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3690558969974518},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.35922539234161377},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3561371862888336},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3285719156265259},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.2397795021533966},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.22162070870399475},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.1806803047657013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15047788619995117},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm49941.2020.9313437","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm49941.2020.9313437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W1594570392","https://openalex.org/W2022736304","https://openalex.org/W2098664089","https://openalex.org/W2101234009","https://openalex.org/W2104290444","https://openalex.org/W2109028614","https://openalex.org/W2110738405","https://openalex.org/W2112132489","https://openalex.org/W2119451273","https://openalex.org/W2127346557","https://openalex.org/W2128016314","https://openalex.org/W2136145671","https://openalex.org/W2145191876","https://openalex.org/W2259938310","https://openalex.org/W2414599762","https://openalex.org/W2433743436","https://openalex.org/W2951410692","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W4312203868","https://openalex.org/W2059637021","https://openalex.org/W2038264393","https://openalex.org/W2069013776","https://openalex.org/W2379997263","https://openalex.org/W2367493320","https://openalex.org/W2131580913","https://openalex.org/W3083097828","https://openalex.org/W1576021314","https://openalex.org/W2125854412"],"abstract_inverted_index":{"The":[0],"computational":[1,25],"prediction":[2,87,141],"of":[3,21,35,61,85,93,95,97,99,123,134,149],"transcription":[4,124,150],"factor":[5,125],"binding":[6],"sites":[7],"remains":[8],"a":[9,72,82,117,136,146],"challenging":[10],"problems":[11],"in":[12,140],"bioinformatics,":[13],"despite":[14],"significant":[15],"methodological":[16],"developments":[17],"from":[18],"the":[19,32,43,132,135],"field":[20],"machine":[22],"learning.":[23],"Such":[24],"models":[26],"are":[27,143],"essential":[28],"to":[29,39,101,114],"help":[30,130],"interpret":[31],"non-coding":[33],"portion":[34],"human":[36],"genomes,":[37],"and":[38,89,104,152],"learn":[40],"more":[41],"about":[42],"regulatory":[44],"mechanisms":[45],"controlling":[46],"gene":[47],"expression.":[48],"In":[49],"parallel,":[50],"massive":[51],"genome":[52],"sequencing":[53],"efforts":[54],"have":[55],"produced":[56],"assembled":[57],"genomes":[58],"for":[59,81],"hundred":[60],"vertebrate":[62],"species,":[63],"but":[64],"this":[65],"data":[66],"is":[67],"underused.":[68],"We":[69,107],"present":[70],"PhyloReg,":[71],"new":[73],"semi-supervised":[74],"learning":[75,121],"approach":[76],"that":[77,90,109],"can":[78,111],"be":[79,112],"used":[80,113],"wide":[83],"variety":[84],"sequence-to-function":[86],"problems,":[88],"takes":[91],"advantage":[92],"hundreds":[94],"millions":[96],"years":[98],"evolution":[100],"regularize":[102],"predictors":[103],"improve":[105],"accuracy.":[106],"demonstrate":[108],"PhyloReg":[110],"better":[115],"train":[116],"previously":[118],"proposed":[119],"deep":[120],"model":[122],"binding.":[126],"Simulation":[127],"studies":[128],"further":[129],"delineate":[131],"benefits":[133],"pproach.":[137],"G":[138],"ains":[139],"accuracy":[142],"obtained":[144],"over":[145],"broad":[147],"set":[148],"factors":[151],"cell":[153],"types.":[154]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
