{"id":"https://openalex.org/W7138217792","doi":"https://doi.org/10.1609/aaai.v40i2.37114","title":"GenePheno: Interpretable Gene Knockout-Induced Phenotype Abnormality Prediction from Gene Sequences","display_name":"GenePheno: Interpretable Gene Knockout-Induced Phenotype Abnormality Prediction from Gene Sequences","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138217792","doi":"https://doi.org/10.1609/aaai.v40i2.37114"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i2.37114","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37114","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37114/41076","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37114/41076","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129669492","display_name":"Jingquan Yan","orcid":null},"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":"Jingquan Yan","raw_affiliation_strings":["University of Texas at Arlington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006042185","display_name":"Yuwei Miao","orcid":null},"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":"Yuwei Miao","raw_affiliation_strings":["University of Texas at Arlington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129697270","display_name":"Lei YU","orcid":null},"institutions":[{"id":"https://openalex.org/I4388891891","display_name":"Southwestern Medical Center","ror":"https://ror.org/05d80e146","country_code":null,"type":"healthcare","lineage":["https://openalex.org/I4388891891"]},{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Yu","raw_affiliation_strings":["University of Texas Southwestern Medical Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas Southwestern Medical Center","institution_ids":["https://openalex.org/I867280407","https://openalex.org/I4388891891"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722669","display_name":"Xue Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4388891891","display_name":"Southwestern Medical Center","ror":"https://ror.org/05d80e146","country_code":null,"type":"healthcare","lineage":["https://openalex.org/I4388891891"]},{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xue Xiao","raw_affiliation_strings":["University of Texas Southwestern Medical Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas Southwestern Medical Center","institution_ids":["https://openalex.org/I867280407","https://openalex.org/I4388891891"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129711640","display_name":"Lin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4388891891","display_name":"Southwestern Medical Center","ror":"https://ror.org/05d80e146","country_code":null,"type":"healthcare","lineage":["https://openalex.org/I4388891891"]},{"id":"https://openalex.org/I867280407","display_name":"The University of Texas Southwestern Medical Center","ror":"https://ror.org/05byvp690","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I867280407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin Xu","raw_affiliation_strings":["University of Texas Southwestern Medical Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas Southwestern Medical Center","institution_ids":["https://openalex.org/I867280407","https://openalex.org/I4388891891"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129725915","display_name":"Junzhou Huang","orcid":null},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5129669492"],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46236559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"2","first_page":"1400","last_page":"1408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.2750999927520752,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.2750999927520752,"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":0.26249998807907104,"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/T10885","display_name":"Gene expression and cancer classification","score":0.15000000596046448,"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/phenotype","display_name":"Phenotype","score":0.730400025844574},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.6728000044822693},{"id":"https://openalex.org/keywords/gene-knockout","display_name":"Gene knockout","score":0.6086999773979187},{"id":"https://openalex.org/keywords/gene-prediction","display_name":"Gene prediction","score":0.5242999792098999},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44209998846054077},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43709999322891235},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.3752000033855438},{"id":"https://openalex.org/keywords/abnormality","display_name":"Abnormality","score":0.3434999883174896}],"concepts":[{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.730400025844574},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6851999759674072},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.6728000044822693},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6510999798774719},{"id":"https://openalex.org/C77957584","wikidata":"https://www.wikidata.org/wiki/Q1133550","display_name":"Gene knockout","level":3,"score":0.6086999773979187},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5622000098228455},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.5242999792098999},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C50965678","wikidata":"https://www.wikidata.org/wiki/Q2724302","display_name":"Abnormality","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C122735190","wikidata":"https://www.wikidata.org/wiki/Q715789","display_name":"Gene mapping","level":4,"score":0.3003999888896942},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C19843653","wikidata":"https://www.wikidata.org/wiki/Q213907","display_name":"Model organism","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.28760001063346863},{"id":"https://openalex.org/C84799019","wikidata":"https://www.wikidata.org/wiki/Q426365","display_name":"Polygene","level":4,"score":0.2802000045776367},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C161078062","wikidata":"https://www.wikidata.org/wiki/Q1068690","display_name":"Functional genomics","level":5,"score":0.2524000108242035},{"id":"https://openalex.org/C165864922","wikidata":"https://www.wikidata.org/wiki/Q411391","display_name":"Regulation of gene expression","level":3,"score":0.25130000710487366},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i2.37114","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37114","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37114/41076","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i2.37114","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37114","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37114/41076","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138217792.pdf","grobid_xml":"https://content.openalex.org/works/W7138217792.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Exploring":[0],"how":[1],"genetic":[2,73],"sequences":[3,30,102,173],"shape":[4],"phenotypes":[5],"is":[6,22],"a":[7,13,56,83,124,145],"fundamental":[8],"challenge":[9],"in":[10,163],"biology":[11],"and":[12,31,80,176,194,197],"key":[14],"step":[15],"toward":[16],"scalable,":[17],"hypothesis-driven":[18],"experimentation.":[19],"The":[20],"task":[21,86],"complicated":[23],"by":[24,134,181],"the":[25,36,47,85,90,108],"large":[26],"modality":[27],"gap":[28],"between":[29],"phenotypes,":[32,60],"as":[33,35,75,174,184],"well":[34],"pleiotropic":[37],"nature":[38],"of":[39,52,59,87,92],"gene\u2013phenotype":[40],"relationships.":[41],"Existing":[42],"sequence-based":[43],"efforts":[44],"focus":[45],"on":[46,71],"degree":[48],"to":[49,203],"which":[50,77],"variants":[51],"specific":[53],"genes":[54],"alter":[55],"limited":[57],"set":[58],"while":[61],"general":[62],"gene":[63,97,101,120,146,172,182,205],"knockout-induced":[64,116],"phenotype":[65,94,158],"abnormality":[66],"prediction":[67,112],"methods":[68],"heavily":[69],"rely":[70],"curated":[72],"information":[74],"inputs,":[76],"limits":[78],"scalability":[79],"generalizability.":[81],"As":[82],"result,":[84],"broadly":[88],"predicting":[89],"presence":[91],"multiple":[93],"abnormalities":[95,118,179],"under":[96],"knockout":[98],"directly":[99],"from":[100,119],"remains":[103],"underexplored.":[104],"We":[105],"introduce":[106],"GenePheno,":[107],"first":[109],"interpretable":[110],"multi-label":[111,126,177],"framework":[113],"that":[114,129,138,153],"predicts":[115],"phenotypic":[117,178],"sequences.":[121],"GenePheno":[122,189],"employs":[123],"contrastive":[125],"learning":[127],"objective":[128],"captures":[130],"inter-phenotype":[131],"correlations,":[132],"complemented":[133],"an":[135],"exclusive":[136],"regularization":[137],"enforces":[139],"biological":[140],"consistency.":[141],"It":[142],"further":[143],"incorporates":[144],"function":[147],"bottleneck":[148],"layer,":[149],"offering":[150],"human-interpretable":[151],"concepts":[152],"reflect":[154],"functional":[155,206],"mechanisms":[156],"behind":[157],"formation.":[159],"To":[160],"support":[161],"progress":[162],"this":[164],"area,":[165],"we":[166],"curate":[167],"four":[168],"datasets":[169],"with":[170],"canonical":[171],"input":[175],"induced":[180],"knockouts":[183],"targets.":[185],"Across":[186],"these":[187],"datasets,":[188],"achieves":[190],"state-of-the-art":[191],"gene-centric":[192],"Fmax":[193],"phenotype-centric":[195],"AUC,":[196],"case":[198],"studies":[199],"demonstrate":[200],"its":[201],"ability":[202],"reveal":[204],"mechanisms.":[207]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}