{"id":"https://openalex.org/W2949720430","doi":"https://doi.org/10.1145/3107411.3107425","title":"Understanding Sequence Conservation With Deep Learning","display_name":"Understanding Sequence Conservation With Deep Learning","publication_year":2017,"publication_date":"2017-08-20","ids":{"openalex":"https://openalex.org/W2949720430","doi":"https://doi.org/10.1145/3107411.3107425","mag":"2949720430"},"language":"en","primary_location":{"id":"doi:10.1145/3107411.3107425","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3107411.3107425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th 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/A5100421284","display_name":"Yi Li","orcid":"https://orcid.org/0000-0001-6286-9340"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi Li","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033713368","display_name":"Daniel Quang","orcid":"https://orcid.org/0000-0002-7660-990X"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Quang","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084618257","display_name":"Xiaohui Xie","orcid":"https://orcid.org/0000-0002-5479-6345"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohui Xie","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100421284"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":0.638,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.68461395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"400","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","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"}},"topics":[{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9991000294685364,"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":0.9987999796867371,"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/conserved-sequence","display_name":"Conserved sequence","score":0.6773108243942261},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.579841673374176},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.555040717124939},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5346068143844604},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.496011346578598},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.49487656354904175},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.444894939661026},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.441951721906662},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4389284551143646},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4262066185474396},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4225269854068756},{"id":"https://openalex.org/keywords/functional-genomics","display_name":"Functional genomics","score":0.4107045829296112},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.3896050453186035},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3893207013607025},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.36241790652275085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32435452938079834},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.2795032560825348},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.21247944235801697},{"id":"https://openalex.org/keywords/base-sequence","display_name":"Base sequence","score":0.16041648387908936}],"concepts":[{"id":"https://openalex.org/C199216141","wikidata":"https://www.wikidata.org/wiki/Q4995178","display_name":"Conserved sequence","level":4,"score":0.6773108243942261},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.579841673374176},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.555040717124939},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5346068143844604},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.496011346578598},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.49487656354904175},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.444894939661026},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.441951721906662},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4389284551143646},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4262066185474396},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4225269854068756},{"id":"https://openalex.org/C161078062","wikidata":"https://www.wikidata.org/wiki/Q1068690","display_name":"Functional genomics","level":5,"score":0.4107045829296112},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3896050453186035},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3893207013607025},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.36241790652275085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32435452938079834},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.2795032560825348},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.21247944235801697},{"id":"https://openalex.org/C3017666073","wikidata":"https://www.wikidata.org/wiki/Q1764062","display_name":"Base sequence","level":3,"score":0.16041648387908936},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3107411.3107425","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3107411.3107425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W1423339008","https://openalex.org/W1498436455","https://openalex.org/W1533861849","https://openalex.org/W1900337607","https://openalex.org/W2011457803","https://openalex.org/W2011582941","https://openalex.org/W2038473742","https://openalex.org/W2064675550","https://openalex.org/W2077327925","https://openalex.org/W2085442947","https://openalex.org/W2095705004","https://openalex.org/W2101234009","https://openalex.org/W2102619694","https://openalex.org/W2103777723","https://openalex.org/W2108871359","https://openalex.org/W2113207845","https://openalex.org/W2118646732","https://openalex.org/W2124080033","https://openalex.org/W2136101247","https://openalex.org/W2145191876","https://openalex.org/W2146502635","https://openalex.org/W2152175008","https://openalex.org/W2157009395","https://openalex.org/W2160815625","https://openalex.org/W2169393322","https://openalex.org/W2198606573","https://openalex.org/W2264017649","https://openalex.org/W2271840356","https://openalex.org/W2336509392","https://openalex.org/W2345512687","https://openalex.org/W2346578521","https://openalex.org/W2618530766","https://openalex.org/W2949888546","https://openalex.org/W4299828299","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W2360935227","https://openalex.org/W2364993072","https://openalex.org/W2115576822","https://openalex.org/W2356429006","https://openalex.org/W2155595079","https://openalex.org/W2380568150","https://openalex.org/W2385787406","https://openalex.org/W2411510900","https://openalex.org/W2263355832","https://openalex.org/W284518807"],"abstract_inverted_index":{"Comparative":[0],"genomics":[1],"has":[2],"been":[3,20],"a":[4,32,63,79,86,141],"powerful":[5],"tool":[6],"for":[7],"identifying":[8],"functional":[9,25,54,72,174,214,224],"elements":[10,18,29,46,55,73,139,146],"in":[11,35,147],"the":[12,24,96,99,126,133,148,159,163,173,206,239,243],"human":[13,149],"genome.":[14,150],"Millions":[15],"of":[16,27,53,89,98,101,110,144,166,176,205,223,242,250,261],"conserved":[17,49,75,138,177,251],"have":[19],"discovered.":[21],"However,":[22],"understanding":[23],"roles":[26,175],"these":[28,45,59],"still":[30,42],"remain":[31],"challenge,":[33],"especially":[34],"noncoding":[36],"regions.":[37],"In":[38],"particular,":[39],"it":[40],"is":[41,78,263],"unclear":[43],"why":[44],"are":[47,56,114],"evolutionarily":[48],"and":[50,94],"what":[51],"kind":[52],"encoded":[57],"within":[58,74],"sequences.":[60,76],"We":[61,226],"present":[62],"deep":[64],"learning":[65],"framework,":[66],"DeepCons,":[67],"to":[68,116,119,135,156,172,187,196,211,231],"further":[69],"understand":[70],"potential":[71],"DeepCons":[77,262],"convolutional":[80],"neural":[81],"net":[82],"(CNN)":[83],"that":[84,217],"receives":[85],"short":[87],"segment":[88],"DNA":[90,123],"sequence":[91,100,117],"as":[92],"input":[93],"outputs":[95],"probability":[97],"being":[102],"evolutionary":[103],"conserved.":[104],"The":[105,258],"CNN":[106],"model":[107,134,160],"utilizes":[108],"hundreds":[109],"convolution":[111],"kernels,":[112],"which":[113,168],"analogous":[115],"motifs,":[118],"extract":[120],"features":[121],"from":[122,140],"sequences":[124,252],"during":[125],"training":[127],"pro-":[128],"cess.":[129],"First,":[130],"we":[131,152],"train":[132],"discriminate":[136],"887,577":[137],"matched":[142],"number":[143],"nonconserved":[145],"Then,":[151],"use":[153],"visualization":[154],"techniques":[155],"interpret":[157],"how":[158,233],"discriminates":[161],"between":[162],"two":[164],"classes":[165],"sequences,":[167,245],"provides":[169],"indirect":[170],"clues":[171],"elements.":[178,225],"Some":[179],"kernels":[180,191,207],"significantly":[181],"match":[182],"well-known":[183],"regulatory":[184],"motifs":[185],"corresponding":[186],"transcription":[188,197,201],"factors.":[189],"Many":[190],"show":[192],"positional":[193],"biases":[194],"relative":[195],"start":[198],"sites":[199],"or":[200],"end":[202],"sites.":[203],"Most":[204],"do":[208],"not":[209],"correspond":[210],"any":[212],"known":[213],"element,":[215],"suggesting":[216],"they":[218],"might":[219],"represent":[220],"unknown":[221],"categories":[222],"also":[227],"utilize":[228],"Deep-":[229],"Cons":[230],"annotate":[232],"changes":[234],"at":[235,253,266],"individual":[236,255],"nucleotides":[237],"impact":[238],"conservation":[240],"properties":[241],"surrounding":[244],"thereby":[246],"providing":[247],"an":[248,254],"annotation":[249],"nucleotide":[256],"level.":[257],"source":[259],"code":[260],"publicly":[264],"available":[265],"https://github.com/uci-cbcl/DeepCons.":[267]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}