{"id":"https://openalex.org/W7214910731","doi":"https://doi.org/10.64898/2026.09.24.754149","title":"RNA-guided contrastive learning enhances patient-level prediction from histology","display_name":"RNA-guided contrastive learning enhances patient-level prediction from histology","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7214910731","doi":"https://doi.org/10.64898/2026.09.24.754149"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.24.754149","doi":"https://doi.org/10.64898/2026.09.24.754149","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754149","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/30/2026.09.24.754149.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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/2026/09/30/2026.09.24.754149.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092183506","display_name":"Anqi Zou","orcid":"https://orcid.org/0009-0008-1663-1962","observed_orcids":["https://orcid.org/0009-0008-1663-1962"]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anqi Zou","raw_affiliation_strings":["Section of Computational Biomedicine Section, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0009-0008-1663-1962","affiliations":[{"raw_affiliation_string":"Section of Computational Biomedicine Section, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153665551","display_name":"Elaine Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elain Huang","raw_affiliation_strings":["Section of Computational Biomedicine Section, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Section of Computational Biomedicine Section, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153670128","display_name":"Qiyou Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiyou Wu","raw_affiliation_strings":["Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064382326","display_name":"Mollie E. Barnard","orcid":"https://orcid.org/0000-0002-4843-4655","observed_orcids":["https://orcid.org/0000-0002-4843-4655"]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I1286490081","display_name":"Boston Medical Center","ror":"https://ror.org/010b9wj87","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1286490081"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mollie E. Barnard","raw_affiliation_strings":["Section of Hematology/Oncology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA","Slone Epidemiology Center, Boston University Chobanian & Avedisian School of Medicine, Boston Medical Center, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Section of Hematology/Oncology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Slone Epidemiology Center, Boston University Chobanian & Avedisian School of Medicine, Boston Medical Center, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046","https://openalex.org/I1286490081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060215226","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0001-8019-7998","observed_orcids":["https://orcid.org/0000-0001-8019-7998"]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Section of Computational Biomedicine Section, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8019-7998","affiliations":[{"raw_affiliation_string":"Section of Computational Biomedicine Section, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060215226"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"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/T10862","display_name":"AI in cancer detection","score":0.9955999851226807,"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"}},"topics":[{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9955999851226807,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.0020000000949949026,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/T10183","display_name":"Breast Cancer Treatment Studies","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/contrastive-learning","display_name":"contrastive learning","score":0.7390000224113464},{"id":"https://openalex.org/keywords/whole-slide-images","display_name":"whole slide images","score":0.7070000171661377},{"id":"https://openalex.org/keywords/breast-cancer","display_name":"breast cancer","score":0.7419999837875366},{"id":"https://openalex.org/keywords/estrogen-receptor","display_name":"estrogen receptor","score":0.9829999804496765},{"id":"https://openalex.org/keywords/progesterone-receptor","display_name":"progesterone receptor","score":1.0},{"id":"https://openalex.org/keywords/her2","display_name":"HER2","score":0.9929999709129333},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.7720000147819519},{"id":"https://openalex.org/keywords/biobert","display_name":"BioBERT","score":0.6690000295639038},{"id":"https://openalex.org/keywords/molecular-subtyping","display_name":"molecular subtyping","score":0.7129999995231628},{"id":"https://openalex.org/keywords/erbb2-amplification","display_name":"ERBB2 amplification","score":0.8009999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.536899983882904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112000107765198},{"id":"https://openalex.org/C84606932","wikidata":"https://www.wikidata.org/wiki/Q416496","display_name":"Estrogen receptor","level":4,"score":0.48910000920295715},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C530470458","wikidata":"https://www.wikidata.org/wiki/Q128581","display_name":"Breast cancer","level":3,"score":0.3693000078201294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.362199991941452},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C98717036","wikidata":"https://www.wikidata.org/wiki/Q14872994","display_name":"Progesterone receptor","level":5,"score":0.34549999237060547},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3343000113964081},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3325999975204468},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3061999976634979},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C57742111","wikidata":"https://www.wikidata.org/wiki/Q7168","display_name":"Histology","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2908728163","wikidata":"https://www.wikidata.org/wiki/Q415271","display_name":"Human Epidermal Growth Factor Receptor 2","level":4,"score":0.2921000123023987},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2915000021457672},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C125473707","wikidata":"https://www.wikidata.org/wiki/Q9914","display_name":"H&E stain","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2777164284","wikidata":"https://www.wikidata.org/wiki/Q277954","display_name":"Estrogen","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.24.754149","doi":"https://doi.org/10.64898/2026.09.24.754149","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754149","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/30/2026.09.24.754149.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.24.754149","doi":"https://doi.org/10.64898/2026.09.24.754149","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.24.754149","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/30/2026.09.24.754149.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":0.428600013256073,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214910731.pdf","grobid_xml":"https://content.openalex.org/works/W7214910731.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1908864745","https://openalex.org/W2010871781","https://openalex.org/W2132619562","https://openalex.org/W2216554257","https://openalex.org/W2911489562","https://openalex.org/W2999400187","https://openalex.org/W4301159569","https://openalex.org/W4366208220","https://openalex.org/W4379600909","https://openalex.org/W4383473945","https://openalex.org/W4386791134","https://openalex.org/W4393935425","https://openalex.org/W4398201291","https://openalex.org/W4399929574","https://openalex.org/W4405114593","https://openalex.org/W4408829385","https://openalex.org/W4410866390","https://openalex.org/W7125496881"],"related_works":["https://openalex.org/W7162494084","https://openalex.org/W7166695857","https://openalex.org/W7117758351","https://openalex.org/W4353065773","https://openalex.org/W7220692024","https://openalex.org/W7128444976","https://openalex.org/W7133538723","https://openalex.org/W4400679772","https://openalex.org/W3046305306","https://openalex.org/W7167041315"],"abstract_inverted_index":{"Abstract":[0],"Predicting":[1],"molecular":[2,214,228],"receptor":[3,7,10,17],"status,":[4],"including":[5],"estrogen":[6],"(ER),":[8],"progesterone":[9],"(PR),":[11],"and":[12,24,94,101,129,136,160,221],"human":[13],"epidermal":[14],"growth":[15],"factor":[16],"2":[18],"(HER2),":[19],"directly":[20],"from":[21,72,98,108],"routine":[22],"hematoxylin":[23],"eosin":[25],"(H&E)-stained":[26],"whole-slide":[27,56],"images":[28],"(WSIs)":[29],"could":[30],"reduce":[31],"reliance":[32],"on":[33,148],"costly":[34],"immunohistochemistry,":[35],"but":[36],"image-only":[37],"models":[38],"have":[39],"no":[40],"access":[41],"to":[42,104,132,211,237],"the":[43,91,142,173,198],"transcriptomic":[44,205],"programs":[45],"that":[46,53,218],"define":[47],"these":[48],"subtypes.":[49],"Here":[50],"we":[51,89],"show":[52],"coupling":[54],"a":[55,65,85,133,153,186,191,208,234],"vision":[57,235],"transformer":[58],"(GigaPath)":[59],"with":[60],"bulk":[61,105],"RNA-sequencing":[62],"profiles":[63,107],"through":[64],"training-time-only":[66],"contrastive":[67],"objective":[68],"improves":[69],"receptor-status":[70],"classification":[71,195],"WSIs":[73],"alone,":[74,225],"without":[75],"requiring":[76],"any":[77],"RNA-seq":[78,106],"data":[79],"at":[80,197],"inference.":[81],"Rather":[82],"than":[83,185],"training":[84],"dedicated":[86],"bulk-transcriptomics":[87],"encoder,":[88],"purpose":[90],"gene-sentence":[92],"encoding":[93],"pretrained":[95],"text":[96],"encoder":[97],"BioBERT":[99],"1":[100],"apply":[102],"them":[103],"The":[109],"Cancer":[110],"Genome":[111],"Atlas":[112],"breast":[113],"cancer":[114],"cohort":[115],"(TCGA-BRCA).":[116],"Under":[117],"five-fold":[118],"cross-validation,":[119],"this":[120],"RNA-guided":[121],"pre-training":[122],"consistently":[123],"improved":[124],"AUROC":[125,175],"for":[126,158,177],"ER,":[127],"PR,":[128,161],"HER2":[130],"relative":[131],"contrastive-pre-training-free":[134],"baseline":[135],"reproducibly":[137],"introduced":[138],"receptor-relevant":[139],"structure":[140],"into":[141],"learned":[143],"slide":[144],"representation.":[145],"However,":[146],"evaluation":[147],"independent":[149],"external":[150],"cohorts":[151],"revealed":[152],"striking,":[154],"receptor-dependent":[155],"divergence:":[156],"gains":[157],"ER":[159],"both":[162],"governed":[163],"by":[164,180],"broad,":[165],"multi-gene":[166],"luminal":[167],"transcriptional":[168,188],"programs,":[169],"generalized":[170],"robustly,":[171],"whereas":[172],"apparent":[174],"improvement":[176],"HER2,":[178],"driven":[179],"focal":[181],"ERBB2":[182],"amplification":[183],"rather":[184],"coordinated":[187],"signature,":[189],"masked":[190],"severe":[192],"loss":[193],"of":[194],"sensitivity":[196],"operating":[199],"threshold.":[200],"These":[201],"findings":[202],"establish":[203],"training-time":[204],"supervision":[206,231],"as":[207],"practical":[209],"route":[210],"enhancing":[212],"histology-only":[213],"subtyping,":[215],"while":[216],"showing":[217],"gene-selection":[219],"strategy,":[220],"not":[222],"model":[223,236],"architecture":[224],"determines":[226],"which":[227],"alterations":[229],"such":[230],"can":[232],"teach":[233],"recognize.":[238]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-01T00:00:00"}