{"id":"https://openalex.org/W7122570404","doi":"https://doi.org/10.3389/fbinf.2025.1713975","title":"SpaLLM: a general framework for spatial domain identification with large language models","display_name":"SpaLLM: a general framework for spatial domain identification with large language models","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7122570404","doi":"https://doi.org/10.3389/fbinf.2025.1713975","pmid":"https://pubmed.ncbi.nlm.nih.gov/41601479"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2025.1713975","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1713975","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1713975/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1713975/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122831939","display_name":"Zeyu Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zeyu Zou","raw_affiliation_strings":["Department of Computer Science, University of California, Irvine, Irvine, CA, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Irvine, Irvine, CA, United States","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122794938","display_name":"Ziheng Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziheng Duan","raw_affiliation_strings":["Department of Computer Science, University of California, Irvine, Irvine, CA, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Irvine, Irvine, CA, United States","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5122831939"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06741189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"1713975","last_page":"1713975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9902999997138977,"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":0.9902999997138977,"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":0.0012000000569969416,"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":0.0010000000474974513,"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/domain","display_name":"Domain (mathematical analysis)","score":0.6396999955177307},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.5450999736785889},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5375000238418579},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.534600019454956},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.41609999537467957},{"id":"https://openalex.org/keywords/gene-expression-profiling","display_name":"Gene expression profiling","score":0.39239999651908875},{"id":"https://openalex.org/keywords/gene-regulatory-network","display_name":"Gene regulatory network","score":0.3874000012874603},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.36160001158714294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6797000169754028},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6396999955177307},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.5450999736785889},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4131999909877777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39959999918937683},{"id":"https://openalex.org/C18431079","wikidata":"https://www.wikidata.org/wiki/Q1502169","display_name":"Gene expression profiling","level":4,"score":0.39239999651908875},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.3874000012874603},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.38029998540878296},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C161078062","wikidata":"https://www.wikidata.org/wiki/Q1068690","display_name":"Functional genomics","level":5,"score":0.33730000257492065},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.3003000020980835},{"id":"https://openalex.org/C158709400","wikidata":"https://www.wikidata.org/wiki/Q3578586","display_name":"Spatial ecology","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.27459999918937683},{"id":"https://openalex.org/C194226119","wikidata":"https://www.wikidata.org/wiki/Q161779","display_name":"Spatial reference system","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fbinf.2025.1713975","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1713975","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1713975/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41601479","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41601479","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,"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":"Frontiers in bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:186f7e23d1ce49c5aa4ccc2256f77100","is_oa":true,"landing_page_url":"https://doaj.org/article/186f7e23d1ce49c5aa4ccc2256f77100","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Bioinformatics, Vol 5 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12833451","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12833451/","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2025.1713975","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1713975","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1713975/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7122570404.pdf","grobid_xml":"https://content.openalex.org/works/W7122570404.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2915848182","https://openalex.org/W2952383043","https://openalex.org/W3108118546","https://openalex.org/W3126958162","https://openalex.org/W3165120573","https://openalex.org/W4226192560","https://openalex.org/W4229033508","https://openalex.org/W4285388882","https://openalex.org/W4322738920","https://openalex.org/W4387819650","https://openalex.org/W4398250214","https://openalex.org/W4398250269","https://openalex.org/W4399141090","https://openalex.org/W4400420052"],"related_works":[],"abstract_inverted_index":{"Spatial":[0],"transcriptomics":[1,66],"(ST)":[2],"technologies":[3],"enable":[4],"the":[5,37],"profiling":[6],"of":[7,60],"gene":[8,29,43,61,76,81,87],"expression":[9,30,91,103],"while":[10,35],"preserving":[11],"spatial":[12,22,33,65,117,122,143,155],"context,":[13],"offering":[14],"unprecedented":[15],"insights":[16],"into":[17],"tissue":[18],"organization.":[19],"However,":[20],"traditional":[21],"domain":[23,123,144],"identification":[24],"methods":[25,119],"primarily":[26],"rely":[27],"on":[28,127],"matrices":[31,92],"and":[32,105,132],"coordinates":[34],"overlooking":[36],"rich":[38],"biological":[39],"knowledge":[40],"encoded":[41],"in":[42],"functional":[44,106],"descriptions.":[45],"Here,":[46],"we":[47],"propose":[48],"SpaLLM,":[49],"a":[50],"general":[51],"framework":[52,148],"that":[53,100,139],"integrates":[54],"large":[55],"language":[56],"model":[57],"(LLM)":[58],"embeddings":[59,73],"descriptions":[62],"with":[63,89,114,153],"conventional":[64],"analysis.":[67],"Our":[68,146],"approach":[69],"leverages":[70],"pre-computed":[71],"GenePT":[72],"from":[74],"NCBI":[75],"summaries":[77],"to":[78,162],"create":[79],"biologically-informed":[80],"representations.":[82],"SpaLLM":[83,140],"combines":[84],"these":[85],"LLM-derived":[86],"features":[88,110],"cell-gene":[90],"through":[93],"matrix":[94],"multiplication,":[95],"generating":[96],"enriched":[97,109],"cell":[98],"representations":[99],"capture":[101],"both":[102],"patterns":[104],"knowledge.":[107],"These":[108],"are":[111],"then":[112],"integrated":[113,152],"existing":[115,154],"graph-based":[116],"analysis":[118,156],"for":[120],"improved":[121],"identification.":[124,145],"Extensive":[125],"validation":[126],"12":[128],"sequencing-based":[129],"Visium":[130],"sections":[131],"an":[133],"independent":[134],"imaging-based":[135],"osmFISH":[136],"dataset":[137],"demonstrate":[138],"consistently":[141],"enhances":[142],"modular":[147],"can":[149],"be":[150],"seamlessly":[151],"pipelines,":[157],"making":[158],"it":[159],"broadly":[160],"applicable":[161],"diverse":[163],"research":[164],"scenarios.":[165]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-01-13T00:00:00"}
