{"id":"https://openalex.org/W7222997720","doi":"https://doi.org/10.64898/2026.10.16.759399","title":"RDEmbed: A Sentence-Embedding Framework for Rare Disease Phenotype Representation and Phenotypic Similarity Analysis","display_name":"RDEmbed: A Sentence-Embedding Framework for Rare Disease Phenotype Representation and Phenotypic Similarity Analysis","publication_year":2026,"publication_date":"2026-10-19","ids":{"openalex":"https://openalex.org/W7222997720","doi":"https://doi.org/10.64898/2026.10.16.759399"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.16.759399","doi":"https://doi.org/10.64898/2026.10.16.759399","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.16.759399","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/19/2026.10.16.759399.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/19/2026.10.16.759399.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159145623","display_name":"Xinghua Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinghua Wang","raw_affiliation_strings":["Department of Health Data Science and Artificial Intelligence, D. Bradley McWilliams School of Biomedical Informatics, The University of Texas Health Science Center Houston, Houston, TX, 77030, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Health Data Science and Artificial Intelligence, D. Bradley McWilliams School of Biomedical Informatics, The University of Texas Health Science Center Houston, Houston, TX, 77030, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159148111","display_name":"Jianlian Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinlian Wang","raw_affiliation_strings":["Department of Quantitative and Systems Health Sciences, The University of Texas at Austin Dell Medical School, Austin, TX, 78712, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Quantitative and Systems Health Sciences, The University of Texas at Austin Dell Medical School, Austin, TX, 78712, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137029063","display_name":"Zijian Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I181547552","display_name":"Baylor College of Medicine","ror":"https://ror.org/02pttbw34","country_code":"US","type":"education","lineage":["https://openalex.org/I181547552","https://openalex.org/I2801539370"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zijian Zhang","raw_affiliation_strings":["Section of Epidemiology and Population Sciences, Department of Medicine, Baylor College of Medicine, Houston, TX, 77030, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Section of Epidemiology and Population Sciences, Department of Medicine, Baylor College of Medicine, Houston, TX, 77030, USA","institution_ids":["https://openalex.org/I181547552"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120873875","display_name":"Hongfang Liu","orcid":"https://orcid.org/0000-0003-2570-3741","observed_orcids":["https://orcid.org/0000-0003-2570-3741"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongfang Liu","raw_affiliation_strings":["Department of Quantitative and Systems Health Sciences, The University of Texas at Austin Dell Medical School, Austin, TX, 78712, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Quantitative and Systems Health Sciences, The University of Texas at Austin Dell Medical School, Austin, TX, 78712, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159107016","display_name":"Arif Harmanci","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arif Harmanci","raw_affiliation_strings":["Department of Health Data Science and Artificial Intelligence, D. Bradley McWilliams School of Biomedical Informatics, The University of Texas Health Science Center Houston, Houston, TX, 77030, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Health Data Science and Artificial Intelligence, D. Bradley McWilliams School of Biomedical Informatics, The University of Texas Health Science Center Houston, Houston, TX, 77030, USA","institution_ids":["https://openalex.org/I919571938"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5159107016"],"corresponding_institution_ids":["https://openalex.org/I919571938"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8003000020980835,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8003000020980835,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.18039999902248383,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.010099999606609344,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/rare-diseases","display_name":"rare diseases","score":0.9710000157356262},{"id":"https://openalex.org/keywords/phenotypic-similarity","display_name":"phenotypic similarity","score":0.8740000128746033},{"id":"https://openalex.org/keywords/sentence-embeddings","display_name":"sentence embeddings","score":0.9259999990463257},{"id":"https://openalex.org/keywords/human-phenotype-ontology","display_name":"Human Phenotype Ontology","score":0.824999988079071},{"id":"https://openalex.org/keywords/gene-discovery","display_name":"gene discovery","score":0.7369999885559082},{"id":"https://openalex.org/keywords/phenotypic-clustering","display_name":"phenotypic clustering","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.6251999735832214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.616100013256073},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6053000092506409},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5906999707221985},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.5637000203132629},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5539000034332275},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5220000147819519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4927999973297119},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.477400004863739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4562999904155731},{"id":"https://openalex.org/C137982476","wikidata":"https://www.wikidata.org/wiki/Q7072326","display_name":"Open Biomedical Ontologies","level":5,"score":0.4424999952316284},{"id":"https://openalex.org/C3020646490","wikidata":"https://www.wikidata.org/wiki/Q25203551","display_name":"Clinical phenotype","level":4,"score":0.4406999945640564},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C66782513","wikidata":"https://www.wikidata.org/wiki/Q864601","display_name":"Biomedicine","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3774999976158142},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C2779701055","wikidata":"https://www.wikidata.org/wiki/Q929833","display_name":"Rare disease","level":3,"score":0.3400999903678894},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C163763905","wikidata":"https://www.wikidata.org/wiki/Q17075943","display_name":"Precision medicine","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2987395477","wikidata":"https://www.wikidata.org/wiki/Q135085","display_name":"Gene ontology","level":4,"score":0.25949999690055847},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2549999952316284},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.16.759399","doi":"https://doi.org/10.64898/2026.10.16.759399","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.16.759399","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/19/2026.10.16.759399.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.16.759399","doi":"https://doi.org/10.64898/2026.10.16.759399","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.16.759399","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/19/2026.10.16.759399.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.504800021648407,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000866431","display_name":"Secure Outsourcing of Genotype Imputation for Privacy-aware Genomic Analysis (RO1HE21)","funder_award_id":"R01HG012604","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7222997720.pdf","grobid_xml":"https://content.openalex.org/works/W7222997720.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W105501628","https://openalex.org/W1617386893","https://openalex.org/W1980171391","https://openalex.org/W2048024098","https://openalex.org/W2084168100","https://openalex.org/W2119818111","https://openalex.org/W2128049108","https://openalex.org/W2136410628","https://openalex.org/W2157079123","https://openalex.org/W2246559112","https://openalex.org/W2754903026","https://openalex.org/W2778088240","https://openalex.org/W2807640626","https://openalex.org/W2911489562","https://openalex.org/W2928818852","https://openalex.org/W2963716420","https://openalex.org/W2970641574","https://openalex.org/W3087028093","https://openalex.org/W3106811464","https://openalex.org/W4224997359","https://openalex.org/W4368616878","https://openalex.org/W4377091864","https://openalex.org/W4385848332","https://openalex.org/W4392866086","https://openalex.org/W4399280731","https://openalex.org/W4399941107","https://openalex.org/W4400128031","https://openalex.org/W4401726216","https://openalex.org/W4401821647","https://openalex.org/W4402358523","https://openalex.org/W4413274997","https://openalex.org/W4414037010","https://openalex.org/W7152600598"],"related_works":["https://openalex.org/W7149632617","https://openalex.org/W4408146338","https://openalex.org/W3164362281","https://openalex.org/W3081625604","https://openalex.org/W4378746344","https://openalex.org/W7202385979","https://openalex.org/W7171956269","https://openalex.org/W4292633571","https://openalex.org/W4322627064","https://openalex.org/W7131446572"],"abstract_inverted_index":{"Abstract":[0],"Accurate":[1],"phenotypic":[2,84,108,253],"characterization":[3],"of":[4],"patients":[5],"with":[6,225],"rare":[7,67,148,164,206,270],"diseases":[8],"is":[9,279],"essential":[10],"for":[11,71,269],"improving":[12,180],"diagnosis,":[13,272],"patient":[14,62,160,273],"matchmaking,":[15,274],"and":[16,40,152,172,182,199,264,275],"gene":[17,276],"discovery.":[18,277],"Conventional":[19],"ontology-driven":[20],"approaches":[21,88],"based":[22],"on":[23,91,259],"the":[24,37,45,168],"Human":[25],"Phenotype":[26],"Ontology":[27],"(HPO)":[28],"enable":[29],"structured":[30],"phenotype":[31,63,240],"comparison":[32],"but":[33],"often":[34],"limited":[35],"by":[36,124,184,242],"incomplete":[38],"annotations":[39,263],"reduced":[41],"ability":[42],"to":[43,82,238],"capture":[44,106],"contextual":[46],"information":[47],"contained":[48],"in":[49,196],"free-text":[50,246],"clinical":[51,247],"narratives.":[52,248],"We":[53,113],"present":[54],"RDEmbed,":[55],"a":[56,153,266],"sentence":[57,232],"embedding":[58,117,122],"framework":[59,268],"that":[60,89,105,231],"learns":[61],"representations":[64,123,189,241],"directly":[65,244],"from":[66,110,245],"disease":[68,149,165,207,271],"case":[69,77,99,150,155],"reports":[70,78,100,151],"similarity":[72,140,254],"analysis.":[73],"RDEmbed":[74,96,135,175,249,278],"encodes":[75,97],"narrative":[76,98],"into":[79,101],"high-dimensional":[80],"vectors":[81],"quantify":[83],"similarity.":[85],"Unlike":[86],"ontology-based":[87,178,210,239],"rely":[90],"manually":[92,260],"curated":[93,154,173,261],"HPO":[94,262],"annotations,":[95],"dense":[102],"semantic":[103],"embeddings":[104,233],"complex":[107],"relationships":[109],"unstructured":[111],"text.":[112],"further":[114,217],"introduced":[115],"retrieval-augmented":[116],"refinement":[118],"(RAER),":[119],"which":[120],"enhances":[121],"incorporating":[125],"external":[126],"domain":[127],"knowledge":[128],"at":[129,282],"inference":[130],"time":[131],"without":[132],"task-specific":[133],"fine-tuning.":[134],"was":[136],"evaluated":[137],"against":[138],"HPO-based":[139],"methods":[141,211],"(OWLSim,":[142],"simGIC)":[143],"using":[144],"simulated":[145],"datasets,":[146],"published":[147],"study":[156],"dataset":[157],"comprising":[158],"156":[159],"abstracts":[161],"presenting":[162],"six":[163],"groups.":[166],"Across":[167],"real":[169],"world":[170],"datasets":[171],"cohort.":[174],"consistently":[176],"outperformed":[177],"approaches,":[179],"AUROC":[181],"AUPRC":[183],"more":[185,192,251],"than":[186],"5%.":[187],"Embedding-based":[188],"also":[190],"produced":[191],"distinct":[193],"disease-specific":[194],"clustering":[195],"t-SNE":[197],"visualizations":[198],"identified":[200],"twice":[201],"as":[202,209],"many":[203],"true":[204],"positive":[205],"pairs":[208],"(8":[212],"versus":[213],"4).":[214],"Incorporating":[215],"RAER":[216],"improved":[218],"precision":[219],"while":[220,256],"maintaining":[221],"high":[222],"sensitivity":[223],"compared":[224],"zero-shot":[226],"embeddings.":[227],"These":[228],"results":[229],"demonstrate":[230],"provide":[234],"an":[235],"effective":[236],"alternative":[237],"learning":[243],"enables":[250],"accurate":[252],"analysis":[255],"reducing":[257],"dependence":[258],"offers":[265],"scalable":[267],"publicly":[280],"available":[281],"https://github.com/xhwang2017/RDEmbed":[283],".":[284]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-21T00:00:00"}