{"id":"https://openalex.org/W2953139847","doi":"https://doi.org/10.1093/bioinformatics/bty396","title":"YAMDA: thousandfold speedup of EM-based motif discovery using deep learning libraries and GPU","display_name":"YAMDA: thousandfold speedup of EM-based motif discovery using deep learning libraries and GPU","publication_year":2018,"publication_date":"2018-05-09","ids":{"openalex":"https://openalex.org/W2953139847","doi":"https://doi.org/10.1093/bioinformatics/bty396","mag":"2953139847","pmid":"https://pubmed.ncbi.nlm.nih.gov/29790915"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bty396","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty396","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/20/3578/26024388/bty396.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/34/20/3578/26024388/bty396.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033713368","display_name":"Daniel Quang","orcid":"https://orcid.org/0000-0002-7660-990X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Quang","raw_affiliation_strings":["Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA","Department of Human Genetics, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0000-0002-7660-990X","affiliations":[{"raw_affiliation_string":"Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Human Genetics, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011032655","display_name":"Yuanfang Guan","orcid":"https://orcid.org/0000-0001-8275-2852"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanfang Guan","raw_affiliation_strings":["Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054883884","display_name":"Stephen C.J. Parker","orcid":"https://orcid.org/0000-0001-8122-0117"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen C J Parker","raw_affiliation_strings":["Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA","Department of Human Genetics, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Human Genetics, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033713368"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.371,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.61980992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"34","issue":"20","first_page":"3578","last_page":"3580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.7476000189781189,"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":0.7476000189781189,"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":0.06549999862909317,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.01759999990463257,"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":0.8315200209617615},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7785600423812866},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6942819952964783},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.5618786215782166},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5409532189369202},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5227668285369873},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.5003726482391357},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47433653473854065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40433770418167114},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3842760920524597},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2057114839553833},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1574515998363495},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08782321214675903}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8315200209617615},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7785600423812866},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6942819952964783},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.5618786215782166},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5409532189369202},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5227668285369873},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.5003726482391357},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47433653473854065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40433770418167114},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3842760920524597},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2057114839553833},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1574515998363495},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08782321214675903},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/bty396","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty396","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/20/3578/26024388/bty396.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:29790915","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29790915","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},{"id":"pmh:oai:europepmc.org:5137010","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC6184538","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:6184538","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6184538","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bty396","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty396","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/20/3578/26024388/bty396.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3575671580","display_name":null,"funder_award_id":"U01HL137182","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953139847.pdf","grobid_xml":"https://content.openalex.org/works/W2953139847.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1592870802","https://openalex.org/W2071116416","https://openalex.org/W2103777723","https://openalex.org/W2121391914","https://openalex.org/W2336509392","https://openalex.org/W2770178180"],"related_works":["https://openalex.org/W2499279132","https://openalex.org/W271331623","https://openalex.org/W1974690493","https://openalex.org/W2073661767","https://openalex.org/W2380185347","https://openalex.org/W2370034659","https://openalex.org/W2117168988","https://openalex.org/W2103777723","https://openalex.org/W2610941444","https://openalex.org/W2159636084"],"abstract_inverted_index":{"Motivation:":[0],"Motif":[1],"discovery":[2,16,28,73],"in":[3,17,116],"large":[4,44],"biopolymer":[5],"sequence":[6],"datasets":[7],"can":[8,55],"be":[9],"computationally":[10],"demanding,":[11],"presenting":[12],"significant":[13],"challenges":[14],"for":[15,43,51,95,102],"omics":[18],"research.":[19],"MEME,":[20,114],"arguably":[21],"one":[22],"of":[23,58],"the":[24,59],"most":[25],"popular":[26],"motif":[27,72],"software,":[29],"takes":[30,105],"quadratic":[31],"time":[32,107],"with":[33,87],"respect":[34],"to":[35,39,108,122],"dataset":[36],"size,":[37],"leading":[38],"excessively":[40],"long":[41],"runtimes":[42],"datasets.":[45],"Therefore,":[46],"there":[47],"is":[48,77,92,131],"a":[49,69,81,125],"demand":[50],"fast":[52],"programs":[53],"that":[54,91,98],"generate":[56],"results":[57],"same":[60],"quality":[61],"as":[62,111,113],"MEME.":[63],"Results:":[64],"Here":[65],"we":[66],"describe":[67],"YAMDA,":[68],"highly":[70,93],"scalable":[71],"software":[74],"package.":[75],"It":[76],"built":[78],"on":[79,134],"Pytorch,":[80],"tensor":[82,96],"computation":[83],"deep":[84],"learning":[85],"library":[86],"strong":[88],"GPU":[89],"acceleration":[90],"optimized":[94],"operations":[97],"are":[99,141],"also":[100],"useful":[101],"motifs.":[103],"YAMDA":[104,130],"linear":[106],"find":[109],"motifs":[110],"accurately":[112],"completing":[115],"seconds":[117],"or":[118],"minutes,":[119],"which":[120],"translates":[121],"speedups":[123],"over":[124],"thousandfold.":[126],"Availability":[127],"and":[128],"implementation:":[129],"freely":[132],"available":[133,142],"Github":[135],"(https://github.com/daquang/YAMDA).":[136],"Supplementary":[137,139],"information:":[138],"data":[140],"at":[143],"Bioinformatics":[144],"online.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}