{"id":"https://openalex.org/W4288421316","doi":"https://doi.org/10.1145/3535508.3545512","title":"MoDNA","display_name":"MoDNA","publication_year":2022,"publication_date":"2022-07-28","ids":{"openalex":"https://openalex.org/W4288421316","doi":"https://doi.org/10.1145/3535508.3545512"},"language":"en","primary_location":{"id":"doi:10.1145/3535508.3545512","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3535508.3545512","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3535508.3545512","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3535508.3545512","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071343551","display_name":"Weizhi An","orcid":"https://orcid.org/0000-0002-9530-0289"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weizhi An","raw_affiliation_strings":["University of Texas at Arlington"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008281887","display_name":"Yuzhi Guo","orcid":"https://orcid.org/0000-0002-8993-1818"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzhi Guo","raw_affiliation_strings":["University of Texas at Arlington"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045777220","display_name":"Yatao Bian","orcid":"https://orcid.org/0000-0002-2368-4084"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yatao Bian","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078917190","display_name":"Hehuan Ma","orcid":"https://orcid.org/0000-0002-5971-0053"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hehuan Ma","raw_affiliation_strings":["University of Texas at Arlington"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049718088","display_name":"Jinyu Yang","orcid":"https://orcid.org/0000-0002-7004-3570"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Yang","raw_affiliation_strings":["University of Texas at Arlington"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003075563","display_name":"Chunyuan Li","orcid":"https://orcid.org/0000-0002-3659-8089"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunyuan Li","raw_affiliation_strings":["University of Texas at Arlington"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068865316","display_name":"Junzhou Huang","orcid":"https://orcid.org/0000-0002-9548-1227"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junzhou Huang","raw_affiliation_strings":["University of Texas at Arlington"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5071343551"],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":2.4304,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.89893324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9990000128746033,"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":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.701991856098175},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5707134008407593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.558340847492218},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5529496669769287},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5258030295372009},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4694651663303375},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.44679781794548035},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.34504276514053345},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.325833261013031},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.16117137670516968},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.14250576496124268},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10004785656929016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.701991856098175},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5707134008407593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.558340847492218},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5529496669769287},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5258030295372009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4694651663303375},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.44679781794548035},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.34504276514053345},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.325833261013031},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16117137670516968},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.14250576496124268},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10004785656929016},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3535508.3545512","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3535508.3545512","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3535508.3545512","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3535508.3545512","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3535508.3545512","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3535508.3545512","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1171700966","display_name":null,"funder_award_id":"NSF CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3876414547","display_name":null,"funder_award_id":"IIS-1553687","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7363998610","display_name":null,"funder_award_id":"RP190107","funder_id":"https://openalex.org/F4320308129","funder_display_name":"Cancer Prevention and Research Institute of Texas"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320308129","display_name":"Cancer Prevention and Research Institute of Texas","ror":"https://ror.org/0003xa228"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4288421316.pdf","grobid_xml":"https://content.openalex.org/works/W4288421316.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2259938310","https://openalex.org/W2908351833","https://openalex.org/W2966164316","https://openalex.org/W2973114758","https://openalex.org/W3019905301","https://openalex.org/W3099179344","https://openalex.org/W3110341782","https://openalex.org/W3127238141"],"related_works":["https://openalex.org/W4214653257","https://openalex.org/W3040203686","https://openalex.org/W4249524554","https://openalex.org/W2521424917","https://openalex.org/W2349021146","https://openalex.org/W35583307","https://openalex.org/W1630076647","https://openalex.org/W2371138613","https://openalex.org/W1969895229","https://openalex.org/W2108497208"],"abstract_inverted_index":{"Obtaining":[0],"informative":[1],"representations":[2,55,109],"of":[3,36,61,152],"gene":[4],"expression":[5],"is":[6,91,116],"crucial":[7],"in":[8],"predicting":[9],"various":[10,57],"downstream":[11,58,100,134],"regulatory-related":[12],"tasks":[13,101],"such":[14],"as":[15],"promoter":[16,140],"prediction":[17,141,147],"and":[18,50,94,115,130,142],"transcription":[19,143],"factor":[20,144],"binding":[21,145],"sites":[22,146],"prediction.":[23],"Nevertheless,":[24],"current":[25],"supervised":[26],"learning":[27,67],"with":[28],"insufficient":[29],"labeled":[30],"genomes":[31],"limits":[32],"the":[33,52,64,105,149],"generalization":[34],"capability":[35],"training":[37,49],"a":[38,83],"robust":[39],"predictive":[40],"model.":[41],"Recently":[42],"researchers":[43],"model":[44],"DNA":[45,69,86],"sequences":[46],"by":[47],"self-supervised":[48,93],"transfer":[51],"pre-trained":[53],"genome":[54,77,108,113,128],"to":[56,68],"tasks.":[59,135],"Instead":[60],"directly":[62],"shifting":[63],"mask":[65],"language":[66,78],"sequence":[70],"learning,":[71],"we":[72],"incorporate":[73],"prior":[74],"knowledge":[75],"into":[76],"modeling":[79],"representations.":[80],"We":[81,123],"propose":[82],"novel":[84],"Motif-oriented":[85],"(MoDNA)":[87],"pre-training":[88],"framework,":[89],"which":[90],"designed":[92],"can":[95],"be":[96],"fine-tuned":[97],"for":[98],"different":[99],"MoDNA":[102,125],"effectively":[103],"learns":[104],"semantic":[106],"level":[107],"from":[110],"enormous":[111],"unlabelled":[112],"data,":[114],"more":[117],"computationally":[118],"efficient":[119],"than":[120],"previous":[121],"methods.":[122],"pre-train":[124],"on":[126,133,139],"human":[127],"data":[129],"fine-tune":[131],"it":[132],"Extensive":[136],"experimental":[137],"results":[138],"demonstrate":[148],"state-of-the-art":[150],"performance":[151],"MoDNA.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2022-07-29T00:00:00"}