{"id":"https://openalex.org/W7162023343","doi":"https://doi.org/10.1186/s12859-026-06458-4","title":"Transcriptome graph transformer: a graph transformer-based unsupervised model for transcriptome data analysis","display_name":"Transcriptome graph transformer: a graph transformer-based unsupervised model for transcriptome data analysis","publication_year":2026,"publication_date":"2026-05-21","ids":{"openalex":"https://openalex.org/W7162023343","doi":"https://doi.org/10.1186/s12859-026-06458-4","pmid":"https://pubmed.ncbi.nlm.nih.gov/42168843"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-026-06458-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06458-4","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12859-026-06458-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018688345","display_name":"Teng Long","orcid":"https://orcid.org/0000-0001-9773-418X"},"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":"Teng Long","raw_affiliation_strings":["Computer Science and Engineering, The University of Texas at Arlington, 500 UTA Blvd, Arlington, TX, 76010, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The University of Texas at Arlington, 500 UTA Blvd, Arlington, TX, 76010, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134589404","display_name":"Sachit Satyal","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":"Sachit Satyal","raw_affiliation_strings":["Computer Science and Engineering, The University of Texas at Arlington, 500 UTA Blvd, Arlington, TX, 76010, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The University of Texas at Arlington, 500 UTA Blvd, Arlington, TX, 76010, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123547543","display_name":"Jean Gao","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":"Jean Gao","raw_affiliation_strings":["Computer Science and Engineering, The University of Texas at Arlington, 500 UTA Blvd, Arlington, TX, 76010, USA. gao@uta.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The University of Texas at Arlington, 500 UTA Blvd, Arlington, TX, 76010, USA. gao@uta.edu","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5123547543"],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44844299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","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":0.49239999055862427,"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":0.49239999055862427,"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":0.41260001063346863,"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/T11297","display_name":"Ferroptosis and cancer prognosis","score":0.02979999966919422,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transcriptome","display_name":"Transcriptome","score":0.6704000234603882},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5202999711036682},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5142999887466431},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.4115000069141388},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4106999933719635},{"id":"https://openalex.org/keywords/biological-network","display_name":"Biological network","score":0.38749998807907104},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.37229999899864197},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.36079999804496765}],"concepts":[{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.6704000234603882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6136000156402588},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5142999887466431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5026000142097473},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4334999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4302999973297119},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.4115000069141388},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4106999933719635},{"id":"https://openalex.org/C28225019","wikidata":"https://www.wikidata.org/wiki/Q4915005","display_name":"Biological network","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.3199000060558319},{"id":"https://openalex.org/C18431079","wikidata":"https://www.wikidata.org/wiki/Q1502169","display_name":"Gene expression profiling","level":4,"score":0.29330000281333923},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C124535831","wikidata":"https://www.wikidata.org/wiki/Q4915074","display_name":"Biomarker discovery","level":4,"score":0.27320000529289246},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.25270000100135803},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.25270000100135803}],"mesh":[{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098422","descriptor_name":"Graph Neural Networks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098422","descriptor_name":"Graph Neural Networks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098422","descriptor_name":"Graph Neural Networks","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000099285","descriptor_name":"Spatial Transcriptomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000099285","descriptor_name":"Spatial Transcriptomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000099285","descriptor_name":"Spatial Transcriptomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-026-06458-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06458-4","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:42168843","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42168843","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":"BMC bioinformatics","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13463954","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13463954/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13463954/pdf/12859_2026_Article_6458.pdf","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:fe8834c81e5649569e7182a604643dc4","is_oa":false,"landing_page_url":"https://doaj.org/article/fe8834c81e5649569e7182a604643dc4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-026-06458-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06458-4","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4321345054","display_name":"EAGER: Integrating Multi-Omics Biological Networks and Ontologies for lncRNA Function Annotation using Deep Learning","funder_award_id":"2400785","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1527927437","https://openalex.org/W1972649334","https://openalex.org/W2118258530","https://openalex.org/W2294798173","https://openalex.org/W2817817898","https://openalex.org/W2899224111","https://openalex.org/W2949084500","https://openalex.org/W2979947476","https://openalex.org/W2982437619","https://openalex.org/W3101709158","https://openalex.org/W3171623624","https://openalex.org/W3184100309","https://openalex.org/W3211269771","https://openalex.org/W4290154117","https://openalex.org/W4323545283","https://openalex.org/W4376171492","https://openalex.org/W4386387831","https://openalex.org/W4388539829","https://openalex.org/W4388845139","https://openalex.org/W4390700305","https://openalex.org/W4399388096","https://openalex.org/W4400430401","https://openalex.org/W4403479110","https://openalex.org/W4404126723","https://openalex.org/W4404511387","https://openalex.org/W4408129839","https://openalex.org/W4411870113","https://openalex.org/W4414410404","https://openalex.org/W4415620197"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"Rapidly":[1],"growing":[2],"transcriptomic":[3,133,153],"datasets":[4],"pose":[5],"challenges":[6],"for":[7,73,132,151],"traditional":[8],"analytical":[9],"methods,":[10],"which":[11],"struggle":[12],"with":[13,66,120,141],"high":[14],"dimensionality,":[15],"heterogeneity,":[16],"and":[17,29,59,71,78,83,98,110,115,129,155],"nonlinear":[18],"gene":[19,114],"relationships.":[20],"Existing":[21],"deep":[22],"learning":[23,135],"models":[24],"often":[25],"require":[26],"fixed-length":[27],"inputs":[28],"fail":[30],"to":[31],"integrate":[32],"biological":[33,138],"network":[34,139],"information.":[35],"METHODS:":[36],"We":[37],"introduce":[38],"Transcriptome":[39],"Graph":[40],"Transformer":[41,46,143],"(TGT),":[42],"an":[43,127],"unsupervised":[44],"graph":[45,53,142],"framework":[47],"that":[48],"constructs":[49],"a":[50,67],"heterogeneous":[51],"gene-pathway":[52],"using":[54],"expression":[55],"data,":[56],"STRING":[57],"interactions,":[58],"GO/KEGG/Reactome":[60],"pathway":[61,116],"annotations.":[62],"TGT":[63,87,125],"is":[64],"pretrained":[65],"masked-node":[68],"prediction":[69],"task":[70],"fine-tuned":[72],"disease":[74,122],"classification,":[75],"biomarker":[76],"discovery,":[77],"zero-shot":[79],"clustering":[80],"of":[81],"single-cell":[82],"spatial":[84],"transcriptomics.":[85],"RESULTS:":[86],"achieves":[88],"superior":[89],"performance":[90,147],"across":[91,108],"Alzheimer's":[92],"disease,":[93],"cancer,":[94],"acute":[95],"kidney":[96],"injury,":[97],"COVID-19":[99],"datasets,":[100],"outperforming":[101],"state-of-the-art":[102],"baselines.":[103],"The":[104],"model":[105],"generalizes":[106],"well":[107],"platforms":[109],"yields":[111],"biologically":[112],"meaningful":[113],"importance":[117],"scores":[118],"consistent":[119],"known":[121],"mechanisms.":[123],"CONCLUSIONS:":[124],"provides":[126],"effective":[128],"generalizable":[130],"approach":[131],"representation":[134],"by":[136],"integrating":[137],"knowledge":[140],"architectures.":[144],"Its":[145],"strong":[146],"highlights":[148],"its":[149],"utility":[150],"broad":[152],"applications":[154],"precision":[156],"medicine.":[157]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-05-22T00:00:00"}