{"id":"https://openalex.org/W7213600985","doi":"https://doi.org/10.64898/2026.09.11.750957","title":"Mapping Gene Expression to an Interpretable Semantic Space","display_name":"Mapping Gene Expression to an Interpretable Semantic Space","publication_year":2026,"publication_date":"2026-09-18","ids":{"openalex":"https://openalex.org/W7213600985","doi":"https://doi.org/10.64898/2026.09.11.750957","pmid":"https://pubmed.ncbi.nlm.nih.gov/42779819","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13596221"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.11.750957","doi":"https://doi.org/10.64898/2026.09.11.750957","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.11.750957","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/18/2026.09.11.750957.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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/18/2026.09.11.750957.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiaoyu Duan","orcid":"https://orcid.org/0000-0002-0958-6189","observed_orcids":["https://orcid.org/0000-0002-0958-6189"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210090567","display_name":"National Institute of Diabetes and Digestive and Kidney Diseases","ror":"https://ror.org/00adh9b73","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210090567"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaoyu Duan","raw_affiliation_strings":["Laboratory of Biological Modeling, National Institute of Diabetes, Digestive and Kidney Diseases, National Institutes of Health, Bethesda, MD, United States"],"raw_orcid":"https://orcid.org/0000-0002-0958-6189","affiliations":[{"raw_affiliation_string":"Laboratory of Biological Modeling, National Institute of Diabetes, Digestive and Kidney Diseases, National Institutes of Health, Bethesda, MD, United States","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210090567"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060072564","display_name":"Manu Aggarwal","orcid":"https://orcid.org/0000-0002-8262-9341","observed_orcids":["https://orcid.org/0000-0002-8262-9341"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210090567","display_name":"National Institute of Diabetes and Digestive and Kidney Diseases","ror":"https://ror.org/00adh9b73","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210090567"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manu Aggarwal","raw_affiliation_strings":["Laboratory of Biological Modeling, National Institute of Diabetes, Digestive and Kidney Diseases, National Institutes of Health, Bethesda, MD, United States"],"raw_orcid":"https://orcid.org/0000-0002-8262-9341","affiliations":[{"raw_affiliation_string":"Laboratory of Biological Modeling, National Institute of Diabetes, Digestive and Kidney Diseases, National Institutes of Health, Bethesda, MD, United States","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210090567"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068770113","display_name":"Vipul Periwal","orcid":"https://orcid.org/0000-0002-8811-8884","observed_orcids":["https://orcid.org/0000-0002-8811-8884"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210090567","display_name":"National Institute of Diabetes and Digestive and Kidney Diseases","ror":"https://ror.org/00adh9b73","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210090567"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vipul Periwal","raw_affiliation_strings":["Laboratory of Biological Modeling, National Institute of Diabetes, Digestive and Kidney Diseases, National Institutes of Health, Bethesda, MD, United States"],"raw_orcid":"https://orcid.org/0000-0002-8811-8884","affiliations":[{"raw_affiliation_string":"Laboratory of Biological Modeling, National Institute of Diabetes, Digestive and Kidney Diseases, National Institutes of Health, Bethesda, MD, United States","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210090567"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210090567"],"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9994999766349792,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9994999766349792,"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":0.00019999999494757503,"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":9.999999747378752e-05,"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/single-cell-gene-expression","display_name":"single-cell gene expression","score":0.7409999966621399},{"id":"https://openalex.org/keywords/semantic-embeddings","display_name":"semantic embeddings","score":0.7310000061988831},{"id":"https://openalex.org/keywords/biomedical-language-models","display_name":"biomedical language models","score":0.8230000138282776},{"id":"https://openalex.org/keywords/interpretable-clustering","display_name":"interpretable clustering","score":0.6660000085830688},{"id":"https://openalex.org/keywords/cell-type-identification","display_name":"cell type annotation","score":0.5889999866485596},{"id":"https://openalex.org/keywords/cardiomyocytes","display_name":"cardiomyocytes","score":0.7390000224113464},{"id":"https://openalex.org/keywords/hypertrophic-cardiomyopathy","display_name":"hypertrophic cardiomyopathy","score":0.9959999918937683},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.5109999775886536}],"concepts":[{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.6360999941825867},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.6111000180244446},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5971999764442444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5605999827384949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5530999898910522},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.4950000047683716},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4846999943256378},{"id":"https://openalex.org/C2776673561","wikidata":"https://www.wikidata.org/wiki/Q655357","display_name":"Atlas (anatomy)","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4255000054836273},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.3456999957561493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C164953516","wikidata":"https://www.wikidata.org/wiki/Q320357","display_name":"Closed set","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.29249998927116394},{"id":"https://openalex.org/C18431079","wikidata":"https://www.wikidata.org/wiki/Q1502169","display_name":"Gene expression profiling","level":4,"score":0.2858000099658966},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.2718000113964081},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C2988382989","wikidata":"https://www.wikidata.org/wiki/Q370685","display_name":"Data space","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.64898/2026.09.11.750957","doi":"https://doi.org/10.64898/2026.09.11.750957","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.11.750957","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/18/2026.09.11.750957.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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:42779819","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42779819","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13596221","doi":null,"is_oa":true,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42779819/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"bioRxiv","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.64898/2026.09.11.750957","doi":"https://doi.org/10.64898/2026.09.11.750957","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.11.750957","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/18/2026.09.11.750957.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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000859775","display_name":"Single Cell Data Analysis Algorithms","funder_award_id":"ZIADK075146","funder_id":"https://openalex.org/F4320337357","funder_display_name":"National Institute of Diabetes and Digestive and Kidney Diseases"}],"funders":[{"id":"https://openalex.org/F4320306085","display_name":"U.S. Department of Health and Human Services","ror":"https://ror.org/033jnv181"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337357","display_name":"National Institute of Diabetes and Digestive and Kidney Diseases","ror":"https://ror.org/00adh9b73"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213600985.pdf","grobid_xml":"https://content.openalex.org/works/W7213600985.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1999558567","https://openalex.org/W2025666521","https://openalex.org/W2035043164","https://openalex.org/W2052250375","https://openalex.org/W2069089843","https://openalex.org/W2070005254","https://openalex.org/W2084112564","https://openalex.org/W2088477804","https://openalex.org/W2103017472","https://openalex.org/W2110065044","https://openalex.org/W2120579640","https://openalex.org/W2295598076","https://openalex.org/W2416524868","https://openalex.org/W2557663987","https://openalex.org/W2800392236","https://openalex.org/W2949237386","https://openalex.org/W2949936626","https://openalex.org/W3040876684","https://openalex.org/W3046375318","https://openalex.org/W3095979265","https://openalex.org/W3206550133","https://openalex.org/W4224120598","https://openalex.org/W4235169531","https://openalex.org/W4280514175","https://openalex.org/W4283257569","https://openalex.org/W4309908782","https://openalex.org/W4319063426","https://openalex.org/W4378838672","https://openalex.org/W4379879135","https://openalex.org/W4388750790","https://openalex.org/W4392168151","https://openalex.org/W4399387478","https://openalex.org/W4405114593","https://openalex.org/W4416308796","https://openalex.org/W7126223607"],"related_works":["https://openalex.org/W4388898710","https://openalex.org/W4405636845","https://openalex.org/W3216943092","https://openalex.org/W4404032608","https://openalex.org/W2982521190","https://openalex.org/W7213592021","https://openalex.org/W7167841873","https://openalex.org/W3083756487","https://openalex.org/W7116743527","https://openalex.org/W4318981406"],"abstract_inverted_index":{"Cell":[0],"embeddings":[1,59],"organize":[2],"single-cell":[3,184],"expression":[4,89],"data,":[5],"but":[6],"their":[7,77,148],"dimensions":[8,42],"have":[9],"no":[10],"biological":[11],"meaning,":[12],"so":[13,87],"clusters":[14,126],"are":[15,81],"interpreted":[16],"afterward.":[17],"We":[18],"present":[19],"MESIC":[20,56],"(Mapping":[21],"Expression":[22],"to":[23,195],"Semantic":[24],"space":[25,115,129,166],"with":[26,173],"Interpretable":[27],"Components),":[28],"which":[29,190],"builds":[30],"the":[31,41,85,113,131,141,145,155,158,164],"written":[32,200],"knowledge":[33],"about":[34,152,201],"genes":[35,73,196],"held":[36],"in":[37,112,127,189],"curated":[38],"databases":[39],"into":[40,52,60],"themselves.":[43],"A":[44],"biomedical":[45],"language":[46],"model":[47],"converts":[48],"each":[49,66],"gene's":[50],"summary":[51],"a":[53,61,69,122,168,186],"semantic":[54],"embedding.":[55],"compresses":[57],"these":[58],"small":[62,70],"number":[63],"of":[64,72,154],"components,":[65],"concentrated":[67],"on":[68],"set":[71],"and":[74,96,172,197],"explained":[75],"by":[76,106],"annotations.":[78],"The":[79],"components":[80,142],"computed":[82],"once":[83],"from":[84],"summaries,":[86],"any":[88],"dataset":[90],"can":[91],"be":[92],"mapped":[93],"onto":[94],"them,":[95],"every":[97,191],"cluster,":[98],"outlier,":[99],"or":[100],"cell-type":[101],"assignment":[102],"is":[103,193,199],"then":[104],"characterized":[105],"named":[107],"genes.":[108,179],"In":[109,121,139],"cardiomyocytes,":[110],"outliers":[111],"component":[114],"were":[116],"enriched":[117],"for":[118],"hypertrophic":[119],"cardiomyopathy.":[120],"lung":[123],"atlas,":[124],"unsupervised":[125],"that":[128,135,143,157],"matched":[130,147],"broad":[132],"cell":[133],"types":[134],"experts":[136],"had":[137,161],"annotated.":[138],"both,":[140],"separated":[144],"cells":[146,156],"known":[149],"biology.":[150],"For":[151],"half":[153],"atlas":[159],"itself":[160],"left":[162],"unannotated,":[163],"same":[165],"gave":[167],"confident":[169],"cluster":[170],"assignment,":[171],"it":[174],"an":[175],"interpretation":[176],"through":[177],"component-associated":[178],"Gene":[180],"summaries":[181],"thus":[182],"give":[183],"analysis":[185],"coordinate":[187],"system":[188],"result":[192],"traced":[194],"what":[198],"them.":[202]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-19T00:00:00"}