{"id":"https://openalex.org/W4417200325","doi":"https://doi.org/10.1145/3765612.3767304","title":"Rare Disease Phenotyping via Self-Supervised Multimodal Learning","display_name":"Rare Disease Phenotyping via Self-Supervised Multimodal Learning","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4417200325","doi":"https://doi.org/10.1145/3765612.3767304"},"language":null,"primary_location":{"id":"doi:10.1145/3765612.3767304","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765612.3767304","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3765612.3767304","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th 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/10.1145/3765612.3767304","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116156753","display_name":"Khartik Uppalapati","orcid":"https://orcid.org/0009-0006-1589-7334"},"institutions":[{"id":"https://openalex.org/I4210154915","display_name":"Youth & Family Services","ror":"https://ror.org/04htkzn50","country_code":"US","type":"other","lineage":["https://openalex.org/I4210154915"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khartik Uppalapati","raw_affiliation_strings":["RareGen Youth Network 501(c)(3), Oakton, VA, USA"],"raw_orcid":"https://orcid.org/0009-0006-1589-7334","affiliations":[{"raw_affiliation_string":"RareGen Youth Network 501(c)(3), Oakton, VA, USA","institution_ids":["https://openalex.org/I4210154915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119963916","display_name":"Bora Yimenicioglu","orcid":"https://orcid.org/0009-0000-6890-8486"},"institutions":[{"id":"https://openalex.org/I4210154915","display_name":"Youth & Family Services","ror":"https://ror.org/04htkzn50","country_code":"US","type":"other","lineage":["https://openalex.org/I4210154915"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bora Yimenicioglu","raw_affiliation_strings":["RareGen Youth Network 501(c)(3), Oakton, VA, USA"],"raw_orcid":"https://orcid.org/0009-0000-6890-8486","affiliations":[{"raw_affiliation_string":"RareGen Youth Network 501(c)(3), Oakton, VA, USA","institution_ids":["https://openalex.org/I4210154915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109516753","display_name":"Adan Eftekhari","orcid":"https://orcid.org/0009-0005-0713-5818"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adan Eftekhari","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0009-0005-0713-5818","affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5117596078","display_name":"Shakeel Abdulkareem","orcid":"https://orcid.org/0009-0000-8589-2981"},"institutions":[{"id":"https://openalex.org/I4210154915","display_name":"Youth & Family Services","ror":"https://ror.org/04htkzn50","country_code":"US","type":"other","lineage":["https://openalex.org/I4210154915"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shakeel Abdulkareem","raw_affiliation_strings":["RareGen Youth Network 501(c)(3), Oakton, VA, USA"],"raw_orcid":"https://orcid.org/0009-0000-8589-2981","affiliations":[{"raw_affiliation_string":"RareGen Youth Network 501(c)(3), Oakton, VA, USA","institution_ids":["https://openalex.org/I4210154915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3724345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.8407999873161316,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.8407999873161316,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T13702","display_name":"Machine Learning in Healthcare","score":0.053599998354911804,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.012600000016391277,"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/deep-learning","display_name":"Deep learning","score":0.4950999915599823},{"id":"https://openalex.org/keywords/exome-sequencing","display_name":"Exome sequencing","score":0.47940000891685486},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.43869999051094055},{"id":"https://openalex.org/keywords/exome","display_name":"Exome","score":0.4081999957561493},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3749000132083893},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.35100001096725464},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.34599998593330383},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.33709999918937683},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.32760000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6499000191688538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6233000159263611},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5138999819755554},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C16671776","wikidata":"https://www.wikidata.org/wiki/Q5420592","display_name":"Exome sequencing","level":4,"score":0.47940000891685486},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C10590036","wikidata":"https://www.wikidata.org/wiki/Q417664","display_name":"Exome","level":5,"score":0.4081999957561493},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C2779701055","wikidata":"https://www.wikidata.org/wiki/Q929833","display_name":"Rare disease","level":3,"score":0.3158999979496002},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C3020646490","wikidata":"https://www.wikidata.org/wiki/Q25203551","display_name":"Clinical phenotype","level":4,"score":0.3052000105381012},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.29809999465942383},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C163763905","wikidata":"https://www.wikidata.org/wiki/Q17075943","display_name":"Precision medicine","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2779620337","wikidata":"https://www.wikidata.org/wiki/Q14907256","display_name":"SDHA","level":4,"score":0.26809999346733093},{"id":"https://openalex.org/C58693492","wikidata":"https://www.wikidata.org/wiki/Q551875","display_name":"Neuroimaging","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.2667999863624573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3765612.3767304","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765612.3767304","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3765612.3767304","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3765612.3767304","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765612.3767304","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3765612.3767304","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417200325.pdf","grobid_xml":"https://content.openalex.org/works/W4417200325.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2082704080","https://openalex.org/W2122825543","https://openalex.org/W2159583324","https://openalex.org/W2165840723","https://openalex.org/W2194775991","https://openalex.org/W2270470215","https://openalex.org/W2619383789","https://openalex.org/W2911489562","https://openalex.org/W2921313412","https://openalex.org/W2973267506","https://openalex.org/W3012501605","https://openalex.org/W3035422918","https://openalex.org/W3035524453","https://openalex.org/W3037802599","https://openalex.org/W3046375318","https://openalex.org/W3106811464","https://openalex.org/W3127238141","https://openalex.org/W3203588026","https://openalex.org/W4312428231","https://openalex.org/W4319300504","https://openalex.org/W4385573131","https://openalex.org/W4404821554","https://openalex.org/W4411485357"],"related_works":[],"abstract_inverted_index":{"Rare":[0],"genetic":[1],"disorders":[2],"often":[3],"subject":[4],"patients":[5],"to":[6,43,49,73],"years-long":[7],"\"diagnostic":[8],"odysseys\"":[9],"involving":[10],"fragmented":[11],"analyses":[12],"of":[13],"genome":[14],"sequences,":[15],"neuroimaging":[16],"scans,":[17],"and":[18,39,91,129,147,159],"biosignal":[19],"recordings.":[20],"We":[21,67,100],"propose":[22],"a":[23,57,69,106,119],"multimodal":[24,76,121],"self-supervised":[25],"foundation":[26],"model":[27,95],"that":[28,123,137],"learns":[29],"unified":[30,120],"representations":[31,83],"from":[32],"whole":[33],"exome":[34],"sequencing":[35],"(WES),":[36],"volumetric":[37],"MRI,":[38],"wearable":[40],"sensor":[41],"data":[42,65,140],"phenotype":[44],"rare":[45,156],"diseases.":[46],"In":[47],"contrast":[48],"siloed":[50],"machine":[51],"learning":[52],"pipelines,":[53],"our":[54,94],"approach":[55],"uses":[56],"single":[58],"transformer-based":[59],"encoder-decoder":[60],"architecture":[61],"for":[62],"all":[63],"three":[64],"modalities.":[66],"optimize":[68],"cross-modal":[70],"contrastive":[71],"loss":[72,81],"align":[74],"patient-specific":[75],"features,":[77],"alongside":[78,141],"an":[79,133],"ontology-based":[80],"grounding":[82],"in":[84,154],"biomedical":[85],"knowledge":[86],"graphs.":[87],"Across":[88],"zero-shot":[89,102,155],"retrieval":[90,158],"classification":[92],"tasks,":[93],"outperforms":[96],"state-of-the-art":[97],"specialized":[98],"baselines.":[99],"demonstrate":[101],"rare-disease":[103],"identification":[104],"with":[105],"+5.6%":[107],"AUROC":[108],"gain":[109],"over":[110],"the":[111],"best":[112],"prior":[113],"method.":[114],"Key":[115],"contributions":[116],"include:":[117],"(i)":[118],"transformer":[122],"handles":[124],"genomic":[125],"variants,":[126],"3-D":[127],"images,":[128],"time-series":[130],"signals,":[131],"(ii)":[132],"ontology-aligned":[134],"latent":[135],"space":[136],"embeds":[138],"patient":[139],"Human":[142],"Phenotype":[143],"Ontology":[144],"(HPO)":[145],"terms,":[146],"(iii)":[148],"extensive":[149],"experiments":[150],"showing":[151],"improved":[152],"recall":[153],"disease":[157],"clinically":[160],"meaningful":[161],"attention-based":[162],"explanations.":[163]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-10T00:00:00"}