{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:45:39Z","timestamp":1792788339173,"version":"4.5.0"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":41,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100006108","name":"National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["BU-CTSI Grant Number 1UL1TR001430"],"award-info":[{"award-number":["BU-CTSI Grant Number 1UL1TR001430"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["U2C-CA233238"],"award-info":[{"award-number":["U2C-CA233238"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["R21-CA253498"],"award-info":[{"award-number":["R21-CA253498"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100027026","name":"Johnson and Johnson Innovation","doi-asserted-by":"publisher","award":["Sponsored Research Agreement"],"award-info":[{"award-number":["Sponsored Research Agreement"]}],"id":[{"id":"10.13039\/100027026","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000043","name":"American Association for Cancer Research","doi-asserted-by":"publisher","award":["SU2C-AACR-DT23-17"],"award-info":[{"award-number":["SU2C-AACR-DT23-17"]}],"id":[{"id":"10.13039\/100000043","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Heart, Lung, and Blood Institute,United States","award":["R01-HL159620"],"award-info":[{"award-number":["R01-HL159620"]}],"id":[{"id":"https:\/\/ror.org\/012pb6c26","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Institute on Aging,United States","award":["R01-AG083735"],"award-info":[{"award-number":["R01-AG083735"]}],"id":[{"id":"https:\/\/ror.org\/049v75w11","id-type":"ROR","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["R01- AG062109"],"award-info":[{"award-number":["R01- AG062109"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Institute of Neurological Disorders and Stroke,United States","award":["R01-NS142076"],"award-info":[{"award-number":["R01-NS142076"]}],"id":[{"id":"https:\/\/ror.org\/01s5ya894","id-type":"ROR","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000968","name":"American Heart Association","doi-asserted-by":"publisher","award":["20SFRN35460031"],"award-info":[{"award-number":["20SFRN35460031"]}],"id":[{"id":"10.13039\/100000968","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Genome Med"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Molecular and cellular alterations to the normal pseudostratified columnar bronchial epithelium results in the development of bronchial premalignant lesions representing a spectrum of histology from normal to hyperplasia, metaplasia, dysplasia (mild, moderate, and severe), carcinoma in situ and invasive carcinoma. Several studies have identified molecular alterations associated with lesion histology and progression. The broad and continuous spectrum of histologic and molecular changes makes reproducible stratification of lesions across multiple studies challenging.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a transformer-based framework that flexibly utilizes transcriptomic and histologic patterns to distinguish lesions with bronchial dysplasia or worse from normal, hyperplasia, and metaplasia. We leveraged H&amp;E whole slide images (WSIs) of endobronchial biopsies and bulk gene expression data (GE) derived from endobronchial biopsies and brushings from previously published studies and on-going lung precancer atlas efforts obtained from patients at high-risk for lung cancer.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On an external testing dataset of WSIs, the model trained on WSIs plus GE achieved an area under the ROC curve (AUROC) of 0.884\u2009\u00b1\u20090.040 compared to 0.829\u2009\u00b1\u20090.046 for the model trained on WSIs alone. On external testing datasets of GE, the model trained on WSIs plus GE achieved an AUROC of 0.857\u2009\u00b1\u20090.033 versus 0.713\u2009\u00b1\u20090.098 for a model trained on GE alone. Based on these results, we leveraged data across 4 studies to train a flexible fusion model that allows one or both data modalities (WSIs and GE) to be used in training. The model achieved an AUROC of 0.906\u2009\u00b1\u20090.034 on external testing WSIs data and 0.870\u2009\u00b1\u20090.023 on external testing GE data. Despite model training on a binary label, model probabilities were associated with histologic grade and the model identified gene expression alterations associated with bronchial dysplasia across multiple studies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our multimodal transformer outperformed models trained on a single data modality and enabled the inclusion of samples with one or both modalities during training and\/or testing. It increases the flexibility, scalability, and real-world applicability of disease severity assessment that better risk stratifies bronchial premalignant lesions even when only routine histology data is accessible.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13073-026-01636-8","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T13:46:15Z","timestamp":1775655975000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesions"],"prefix":"10.1186","volume":"18","author":[{"given":"Lingyi","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yohana","family":"Kefella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Regan D.","family":"Conrad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kelley E.","family":"Anderson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kostyantyn","family":"Krysan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erin","family":"Kane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Pennycuick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel T.","family":"Merrick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sam M.","family":"Janes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mary E.","family":"Reid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric J.","family":"Burks","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ehab","family":"Billatos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah A.","family":"Mazzilli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vijaya B.","family":"Kolachalama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6699-2132","authenticated-orcid":false,"given":"Jennifer E.","family":"Beane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"issue":"12","key":"1636_CR1","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1164\/rccm.201504-0822OC","volume":"192","author":"RAA van Boerdonk","year":"2015","unstructured":"van Boerdonk RAA, Smesseim I, Heideman DAM, et al. Close surveillance with long-term follow-up of subjects with preinvasive endobronchial lesions. Am J Respir Crit Care Med. 2015;192(12):1483\u20139. https:\/\/doi.org\/10.1164\/rccm.201504-0822OC.","journal-title":"Am J Respir Crit Care Med"},{"issue":"1","key":"1636_CR2","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1158\/1940-6207.CAPR-15-0305","volume":"9","author":"DT Merrick","year":"2016","unstructured":"Merrick DT, Gao D, Miller YE, et al. persistence of bronchial dysplasia is associated with development of invasive squamous cell carcinoma. Cancer Prev Res. 2016;9(1):96\u2013104. https:\/\/doi.org\/10.1158\/1940-6207.CAPR-15-0305.","journal-title":"Cancer Prev Res"},{"issue":"7957","key":"1636_CR3","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1038\/d41586-023-00989-z","volume":"616","author":"H Ledford","year":"2023","unstructured":"Ledford H. How air pollution causes lung cancer \u2014 without harming DNA. Nature. 2023;616(7957):419\u201320. https:\/\/doi.org\/10.1038\/d41586-023-00989-z.","journal-title":"Nature"},{"issue":"3","key":"1636_CR4","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1183\/13993003.00359-2016","volume":"48","author":"J Malhotra","year":"2016","unstructured":"Malhotra J, Malvezzi M, Negri E, Vecchia CL, Boffetta P. Risk factors for lung cancer worldwide. Eur Respir J. 2016;48(3):889\u2013902. https:\/\/doi.org\/10.1183\/13993003.00359-2016.","journal-title":"Eur Respir J"},{"issue":"3","key":"1636_CR5","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1038\/s41591-018-0323-0","volume":"25","author":"VH Teixeira","year":"2019","unstructured":"Teixeira VH, Pipinikas CP, Pennycuick A, et al. Deciphering the genomic, epigenomic, and transcriptomic landscapes of pre-invasive lung cancer lesions. Nat Med. 2019;25(3):517\u201325. https:\/\/doi.org\/10.1038\/s41591-018-0323-0.","journal-title":"Nat Med"},{"issue":"1","key":"1636_CR6","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1038\/s41467-019-09834-2","volume":"10","author":"JE Beane","year":"2019","unstructured":"Beane JE, Mazzilli SA, Campbell JD, et al. Molecular subtyping reveals immune alterations associated with progression of bronchial premalignant lesions. Nat Commun. 2019;10(1):1856. https:\/\/doi.org\/10.1038\/s41467-019-09834-2.","journal-title":"Nat Commun"},{"issue":"7766","key":"1636_CR7","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1038\/s41586-019-1330-0","volume":"571","author":"C Mascaux","year":"2019","unstructured":"Mascaux C, Angelova M, Vasaturo A, et al. Immune evasion before tumour invasion in early lung squamous carcinogenesis. Nature. 2019;571(7766):570\u20135. https:\/\/doi.org\/10.1038\/s41586-019-1330-0.","journal-title":"Nature"},{"issue":"10","key":"1636_CR8","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1158\/2159-8290.CD-19-1366","volume":"10","author":"A Pennycuick","year":"2020","unstructured":"Pennycuick A, Teixeira VH, AbdulJabbar K, et al. Immune surveillance in clinical regression of preinvasive squamous cell lung cancer. Cancer Discov. 2020;10(10):1489\u201399. https:\/\/doi.org\/10.1158\/2159-8290.CD-19-1366.","journal-title":"Cancer Discov"},{"issue":"17","key":"1636_CR9","doi-asserted-by":"publisher","first-page":"4971","DOI":"10.1158\/0008-5472.CAN-17-3822","volume":"78","author":"DT Merrick","year":"2018","unstructured":"Merrick DT, Edwards MG, Franklin WA, et al. Altered cell-cycle control, inflammation, and adhesion in high-risk persistent bronchial dysplasia. Cancer Res. 2018;78(17):4971\u201383. https:\/\/doi.org\/10.1158\/0008-5472.CAN-17-3822.","journal-title":"Cancer Res"},{"issue":"9","key":"1636_CR10","doi-asserted-by":"publisher","first-page":"e002647","DOI":"10.1136\/jitc-2021-002647","volume":"9","author":"A Maoz","year":"2021","unstructured":"Maoz A, Merenstein C, Koga Y, et al. Elevated T cell repertoire diversity is associated with progression of lung squamous cell premalignant lesions. J Immunother Cancer. 2021;9(9):e002647. https:\/\/doi.org\/10.1136\/jitc-2021-002647.","journal-title":"J Immunother Cancer"},{"issue":"1","key":"1636_CR11","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1186\/s13046-023-02674-5","volume":"42","author":"B Ning","year":"2023","unstructured":"Ning B, Tilston-Lunel AM, Simonetti J, et al. Convergence of YAP\/TAZ, TEAD and TP63 activity is associated with bronchial premalignant severity and progression. J Exp Clin Cancer Res. 2023;42(1):116. https:\/\/doi.org\/10.1186\/s13046-023-02674-5.","journal-title":"J Exp Clin Cancer Res"},{"issue":"3","key":"1636_CR12","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1046\/j.1365-2559.2001.01078.x","volume":"38","author":"AG Nicholson","year":"2001","unstructured":"Nicholson AG, Perry LJ, Cury PM, et al. Reproducibility of the WHO\/IASLC grading system for pre-invasive squamous lesions of the bronchus: a study of inter-observer and intra-observer variation. Histopathology. 2001;38(3):202\u20138. https:\/\/doi.org\/10.1046\/j.1365-2559.2001.01078.x.","journal-title":"Histopathology"},{"issue":"7","key":"1636_CR13","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1016\/j.ajpath.2024.03.009","volume":"194","author":"RH Gindra","year":"2024","unstructured":"Gindra RH, Zheng Y, Green EJ, et al. Graph Perceiver Network for Lung Tumor and Bronchial Premalignant Lesion Stratification from Histopathology. Am J Pathol. 2024;194(7):1285\u201393. https:\/\/doi.org\/10.1016\/j.ajpath.2024.03.009.","journal-title":"Am J Pathol"},{"key":"1636_CR14","doi-asserted-by":"crossref","unstructured":"Xu L, Kefella Y, Zhang Y, et al. Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesions. Human Tumor Atlas Network (HTAN) Data Portal. Published online 2026. https:\/\/data.humantumoratlas.org\/publications\/hta3_2026_genome-medicine_lingyi-xu.","DOI":"10.1186\/s13073-026-01636-8"},{"key":"1636_CR15","unstructured":"Beane J, Mazzilli S, Campbell J, et al. Bronchial premalignant lesions have distinct molecular subtypes associated with future histologic progression. Gene Expression Omnibus (GEO) database (Accession Number GSE109743). Published online 2019. https:\/\/www.ncbi.nlm.nih.gov\/geo\/query\/acc.cgi?acc=GSE109743."},{"key":"1636_CR16","doi-asserted-by":"crossref","unstructured":"Xu L, Kefella Y, Zhang Y, et al. Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesions. Gene Expression Omnibus (GEO) database (Accession Number GSE320381). Published online 2026. https:\/\/www.ncbi.nlm.nih.gov\/geo\/query\/acc.cgi?acc=GSE320381.","DOI":"10.1101\/2025.06.06.25328492"},{"key":"1636_CR17","unstructured":"Merrick DT, Edwards MG, Franklin WA, et al. Altered Cell-Cycle Control, Inflammation, and Adhesion in High-Risk Persistent Bronchial Dysplasia. Gene Expression Omnibus (GEO) database (Accession Number GSE114489). Published online 2018. Accessed January 9, 2025. https:\/\/www.ncbi.nlm.nih.gov\/geo\/query\/acc.cgi?acc=GSE114489."},{"key":"1636_CR18","unstructured":"Mascaux C, Angelova M, Vasaturo A, et al. Molecular characterisation of the multistep process of lung squamous carcinogenesis by gene expression profiling. Gene Expression Omnibus (GEO) database (Accession Number GSE33479). Published online 2019. https:\/\/www.ncbi.nlm.nih.gov\/geo\/query\/acc.cgi?acc=GSE33479."},{"key":"1636_CR19","unstructured":"Pennycuick A, Teixeira VH, AbdulJabbar K, et al. Immune surveillance in clinical regression of pre-invasive squamous cell lung cancer. Image Data Resource (IDR) (Accession number idr0082). Published online 2020. https:\/\/idr.openmicroscopy.org\/webclient\/?show=project-1251."},{"issue":"1","key":"1636_CR20","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1186\/s12890-019-0825-7","volume":"19","author":"E Billatos","year":"2019","unstructured":"Billatos E, Duan F, Moses E, et al. Detection of early lung cancer among military personnel (DECAMP) consortium: study protocols. BMC Pulm Med. 2019;19(1):59. https:\/\/doi.org\/10.1186\/s12890-019-0825-7.","journal-title":"BMC Pulm Med"},{"key":"1636_CR21","doi-asserted-by":"publisher","unstructured":"Beane-Ebel J. H&E stained endobronchial biopsies from patients at high-risk of developing lung cancer. In Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesions. Zenodo. Published online 2025. https:\/\/doi.org\/10.5281\/zenodo.17362964.","DOI":"10.5281\/zenodo.17362964"},{"key":"1636_CR22","doi-asserted-by":"crossref","unstructured":"Xu L, Kefella Y, Zhang Y, et al. Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesions. Gene Expression Omnibus (GEO) database (Accession Number GSE300258). Published online 2026. https:\/\/www.ncbi.nlm.nih.gov\/geo\/query\/acc.cgi?acc=GSE300258.","DOI":"10.1101\/2025.06.06.25328492"},{"issue":"6","key":"1636_CR23","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu MY, Williamson DFK, Chen TY, Chen RJ, Barbieri M, Mahmood F. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat Biomed Eng. 2021;5(6):555\u201370. https:\/\/doi.org\/10.1038\/s41551-020-00682-w.","journal-title":"Nat Biomed Eng"},{"issue":"3","key":"1636_CR24","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","volume":"30","author":"RJ Chen","year":"2024","unstructured":"Chen RJ, Ding T, Lu MY, et al. Towards a general-purpose foundation model for computational pathology. Nat Med. 2024;30(3):850\u201362. https:\/\/doi.org\/10.1038\/s41591-024-02857-3.","journal-title":"Nat Med"},{"issue":"D1","key":"1636_CR25","doi-asserted-by":"publisher","first-page":"D991","DOI":"10.1093\/nar\/gks1193","volume":"41","author":"T Barrett","year":"2013","unstructured":"Barrett T, Wilhite SE, Ledoux P, et al. NCBI GEO: archive for functional genomics data sets\u2014update. Nucleic Acids Res. 2013;41(D1):D991\u20135. https:\/\/doi.org\/10.1093\/nar\/gks1193.","journal-title":"Nucleic Acids Res"},{"issue":"8","key":"1636_CR26","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1038\/nprot.2009.97","volume":"4","author":"S Durinck","year":"2009","unstructured":"Durinck S, Spellman PT, Birney E, Huber W. Mapping identifiers for the integration of genomic datasets with the R\/Bioconductor package biomaRt. Nat Protoc. 2009;4(8):1184\u201391. https:\/\/doi.org\/10.1038\/nprot.2009.97.","journal-title":"Nat Protoc"},{"issue":"16","key":"1636_CR27","doi-asserted-by":"publisher","first-page":"3439","DOI":"10.1093\/bioinformatics\/bti525","volume":"21","author":"S Durinck","year":"2005","unstructured":"Durinck S, Moreau Y, Kasprzyk A, et al. BioMart and Bioconductor: a powerful link between biological databases and microarray data analysis. Bioinforma Oxf Engl. 2005;21(16):3439\u201340. https:\/\/doi.org\/10.1093\/bioinformatics\/bti525.","journal-title":"Bioinforma Oxf Engl"},{"issue":"17","key":"1636_CR28","doi-asserted-by":"publisher","first-page":"3151","DOI":"10.1093\/bioinformatics\/btz031","volume":"35","author":"J Rainer","year":"2019","unstructured":"Rainer J, Gatto L, Weichenberger CX. Ensembldb: an R package to create and use Ensembl-based annotation resources. Bioinformatics. 2019;35(17):3151\u20133. https:\/\/doi.org\/10.1093\/bioinformatics\/btz031.","journal-title":"Bioinformatics"},{"issue":"2","key":"1636_CR29","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1093\/biostatistics\/4.2.249","volume":"4","author":"RA Irizarry","year":"2003","unstructured":"Irizarry RA, Hobbs B, Collin F. Exploration, normalization, and summaries of high density oligonucleotide array probe level data. Biostatistics. 2003;4(2):249\u201364. https:\/\/doi.org\/10.1093\/biostatistics\/4.2.249.","journal-title":"Biostatistics"},{"issue":"20","key":"1636_CR30","doi-asserted-by":"publisher","first-page":"e175","DOI":"10.1093\/nar\/gni179","volume":"33","author":"M Dai","year":"2005","unstructured":"Dai M, Wang P, Boyd AD, et al. Evolving gene\/transcript definitions significantly alter the interpretation of GeneChip data. Nucleic Acids Res. 2005;33(20):e175. https:\/\/doi.org\/10.1093\/nar\/gni179.","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"1636_CR31","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1093\/bioinformatics\/bts635","volume":"29","author":"A Dobin","year":"2013","unstructured":"Dobin A, Davis CA, Schlesinger F, et al. STAR: ultrafast universal RNA-seq aligner. Bioinformatics. 2013;29(1):15\u201321. https:\/\/doi.org\/10.1093\/bioinformatics\/bts635.","journal-title":"Bioinformatics"},{"issue":"1","key":"1636_CR32","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1186\/1471-2105-12-323","volume":"12","author":"B Li","year":"2011","unstructured":"Li B, Dewey CN. RSEM: accurate transcript quantification from RNA-Seq data with or without a reference genome. BMC Bioinformatics. 2011;12(1):323. https:\/\/doi.org\/10.1186\/1471-2105-12-323.","journal-title":"BMC Bioinformatics"},{"issue":"16","key":"1636_CR33","doi-asserted-by":"publisher","first-page":"2184","DOI":"10.1093\/bioinformatics\/bts356","volume":"28","author":"L Wang","year":"2012","unstructured":"Wang L, Wang S, Li W. RSeQC: quality control of RNA-seq experiments. Bioinformatics. 2012;28(16):2184\u20135. https:\/\/doi.org\/10.1093\/bioinformatics\/bts356.","journal-title":"Bioinformatics"},{"key":"1636_CR34","unstructured":"Kefella Y., Husted C., Mischler W., Venkatraman D., Campbell JD., Beane JE. htan-pipelines\/bulk-rna-seq-pipeline. Published online 2024. https:\/\/github.com\/htan-pipelines\/bulk-rna-seq-pipeline."},{"issue":"1","key":"1636_CR35","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1186\/s13073-020-00761-2","volume":"12","author":"BS Pedersen","year":"2020","unstructured":"Pedersen BS, Bhetariya PJ, Brown J, et al. Somalier: rapid relatedness estimation for cancer and germline studies using efficient genome sketches. Genome Med. 2020;12(1):62. https:\/\/doi.org\/10.1186\/s13073-020-00761-2.","journal-title":"Genome Med"},{"issue":"1","key":"1636_CR36","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1093\/bioinformatics\/btz474","volume":"36","author":"R Orenbuch","year":"2020","unstructured":"Orenbuch R, Filip I, Comito D, Shaman J, Pe\u2019er I, Rabadan R. arcasHLA: high-resolution HLA typing from RNAseq. Bioinformatics. 2020;36(1):33\u201340. https:\/\/doi.org\/10.1093\/bioinformatics\/btz474.","journal-title":"Bioinformatics"},{"issue":"3","key":"1636_CR37","doi-asserted-by":"publisher","first-page":"R25","DOI":"10.1186\/gb-2010-11-3-r25","volume":"11","author":"MD Robinson","year":"2010","unstructured":"Robinson MD, Oshlack A. A scaling normalization method for differential expression analysis of RNA-seq data. Genome Biol. 2010;11(3):R25. https:\/\/doi.org\/10.1186\/gb-2010-11-3-r25.","journal-title":"Genome Biol"},{"key":"1636_CR38","doi-asserted-by":"publisher","unstructured":"Chen Y, Chen L, Lun ATL, Baldoni PL, Smyth GK. edgeR v4: powerful differential analysis of sequencing data with expanded functionality and improved support for small counts and larger datasets. bioRxiv. Preprint posted online November 24, 2024:2024.01.21.576131https:\/\/doi.org\/10.1101\/2024.01.21.576131","DOI":"10.1101\/2024.01.21.576131"},{"issue":"1","key":"1636_CR39","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1186\/s12859-018-2263-6","volume":"19","author":"Y Zhang","year":"2018","unstructured":"Zhang Y, Jenkins DF, Manimaran S, Johnson WE. Alternative empirical Bayes models for adjusting for batch effects in genomic studies. BMC Bioinformatics. 2018;19(1):262. https:\/\/doi.org\/10.1186\/s12859-018-2263-6.","journal-title":"BMC Bioinformatics"},{"key":"1636_CR40","doi-asserted-by":"publisher","unstructured":"Newville M, Stensitzki T, Allen DB, Ingargiola A. LMFIT: Non-Linear Least-Square Minimization and Curve-Fitting for Python. Published online September 21, 2014. https:\/\/doi.org\/10.5281\/zenodo.11813","DOI":"10.5281\/zenodo.11813"},{"issue":"7","key":"1636_CR41","doi-asserted-by":"publisher","first-page":"e47","DOI":"10.1093\/nar\/gkv007","volume":"43","author":"ME Ritchie","year":"2015","unstructured":"Ritchie ME, Phipson B, Wu D, et al. limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Res. 2015;43(7):e47. https:\/\/doi.org\/10.1093\/nar\/gkv007.","journal-title":"Nucleic Acids Res"},{"issue":"9","key":"1636_CR42","doi-asserted-by":"publisher","first-page":"2067","DOI":"10.1093\/bioinformatics\/bti270","volume":"21","author":"GK Smyth","year":"2005","unstructured":"Smyth GK, Michaud J, Scott HS. Use of within-array replicate spots for assessing differential expression in microarray experiments. Bioinformatics. 2005;21(9):2067\u201375. https:\/\/doi.org\/10.1093\/bioinformatics\/bti270.","journal-title":"Bioinformatics"},{"issue":"301","key":"1636_CR43","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1080\/01621459.1963.10500845","volume":"58","author":"JJH Ward","year":"1963","unstructured":"Ward JJH. Hierarchical grouping to optimize an objective function. J Am Stat Assoc. 1963;58(301):236\u201344. https:\/\/doi.org\/10.1080\/01621459.1963.10500845.","journal-title":"J Am Stat Assoc"},{"issue":"W1","key":"1636_CR44","doi-asserted-by":"publisher","first-page":"W90","DOI":"10.1093\/nar\/gkw377","volume":"44","author":"MV Kuleshov","year":"2016","unstructured":"Kuleshov MV, Jones MR, Rouillard AD, et al. Enrichr: a comprehensive gene set enrichment analysis web server 2016 update. Nucleic Acids Res. 2016;44(W1):W90\u20137. https:\/\/doi.org\/10.1093\/nar\/gkw377.","journal-title":"Nucleic Acids Res"},{"issue":"43","key":"1636_CR45","doi-asserted-by":"publisher","first-page":"15545","DOI":"10.1073\/pnas.0506580102","volume":"102","author":"A Subramanian","year":"2005","unstructured":"Subramanian A, Tamayo P, Mootha VK, et al. Gene set enrichment analysis: A knowledge-based approach for interpreting genome-wide expression profiles. Proc Natl Acad Sci. 2005;102(43):15545\u201350. https:\/\/doi.org\/10.1073\/pnas.0506580102.","journal-title":"Proc Natl Acad Sci"},{"issue":"6","key":"1636_CR46","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1016\/j.cels.2015.12.004","volume":"1","author":"A Liberzon","year":"2015","unstructured":"Liberzon A, Birger C, Thorvaldsd\u00f3ttir H, Ghandi M, Mesirov JP, Tamayo P. The Molecular Signatures Database (MSigDB) hallmark gene set collection. Cell Syst. 2015;1(6):417\u201325. https:\/\/doi.org\/10.1016\/j.cels.2015.12.004.","journal-title":"Cell Syst"},{"issue":"1","key":"1636_CR47","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1093\/nar\/28.1.27","volume":"28","author":"M Kanehisa","year":"2000","unstructured":"Kanehisa M, Goto S. KEGG: Kyoto Encyclopedia of Genes and Genomes. Nucleic Acids Res. 2000;28(1):27\u201330. https:\/\/doi.org\/10.1093\/nar\/28.1.27.","journal-title":"Nucleic Acids Res"},{"issue":"D1","key":"1636_CR48","doi-asserted-by":"publisher","first-page":"D587","DOI":"10.1093\/nar\/gkac963","volume":"51","author":"M Kanehisa","year":"2023","unstructured":"Kanehisa M, Furumichi M, Sato Y, Kawashima M, Ishiguro-Watanabe M. KEGG for taxonomy-based analysis of pathways and genomes. Nucleic Acids Res. 2023;51(D1):D587\u201392. https:\/\/doi.org\/10.1093\/nar\/gkac963.","journal-title":"Nucleic Acids Res"},{"key":"1636_CR49","unstructured":"Shen L. GeneOverlap: Test and visualize gene overlaps. Published online 2013. https:\/\/bioconductor.org\/packages\/GeneOverlap\/"},{"key":"1636_CR50","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention Is All You Need. arXiv. Preprint posted online August 2, 2023:arXiv:1706.03762. https:\/\/doi.org\/10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"1636_CR51","doi-asserted-by":"publisher","unstructured":"Bianchi FM, Grattarola D, Alippi C. Spectral Clustering with Graph Neural Networks for Graph Pooling. arXiv. Preprint posted online December 29, 2020:arXiv:1907.00481https:\/\/doi.org\/10.48550\/arXiv.1907.00481","DOI":"10.48550\/arXiv.1907.00481"},{"key":"1636_CR52","doi-asserted-by":"publisher","unstructured":"Ba JL, Kiros JR, Hinton GE. Layer Normalization. arXiv. Preprint posted online July 21, 2016:arXiv:1607.06450https:\/\/doi.org\/10.48550\/arXiv.1607.06450","DOI":"10.48550\/arXiv.1607.06450"},{"key":"1636_CR53","doi-asserted-by":"publisher","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et al. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv. Preprint posted online June 3, 2021:arXiv:2010.11929. https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"issue":"3","key":"1636_CR54","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44(3):837\u201345. https:\/\/doi.org\/10.2307\/2531595.","journal-title":"Biometrics"},{"key":"1636_CR55","unstructured":"Bertail P, Cl\u00e9men\u00e7con S, Vayatis N. On Bootstrapping the ROC Curve. In: Advances in Neural Information Processing Systems. Vol 21. Curran Associates, Inc.; 2008. Accessed November 8, 2025. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2008\/hash\/30bb3825e8f631cc6075c0f87bb4978c-Abstract.html"},{"issue":"1","key":"1636_CR56","doi-asserted-by":"publisher","first-page":"14490","DOI":"10.1038\/s41598-021-93651-5","volume":"11","author":"V Singh","year":"2021","unstructured":"Singh V, Pencina M, Einstein AJ, Liang JX, Berman DS, Slomka P. Impact of train\/test sample regimen on performance estimate stability of machine learning in cardiovascular imaging. Sci Rep. 2021;11(1):14490. https:\/\/doi.org\/10.1038\/s41598-021-93651-5.","journal-title":"Sci Rep"},{"issue":"1","key":"1636_CR57","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1214\/aoms\/1177730491","volume":"18","author":"HB Mann","year":"1947","unstructured":"Mann HB, Whitney DR. On a test of whether one of two random variables is stochastically larger than the other. Ann Math Stat. 1947;18(1):50\u201360. https:\/\/doi.org\/10.1214\/aoms\/1177730491.","journal-title":"Ann Math Stat"},{"issue":"11","key":"1636_CR58","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1080\/14786440109462720","volume":"2","author":"K Pearson","year":"1901","unstructured":"Pearson K. On lines and planes of closest fit to systems of points in space. Lond Edinb Dublin Philos Mag J Sci. 1901;2(11):559\u201372. https:\/\/doi.org\/10.1080\/14786440109462720.","journal-title":"Lond Edinb Dublin Philos Mag J Sci"},{"issue":"6","key":"1636_CR59","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1037\/h0071325","volume":"24","author":"H Hotelling","year":"1933","unstructured":"Hotelling H. Analysis of a complex of statistical variables into principal components. J Educ Psychol. 1933;24(6):417\u201341. https:\/\/doi.org\/10.1037\/h0071325.","journal-title":"J Educ Psychol"},{"key":"1636_CR60","doi-asserted-by":"publisher","unstructured":"Loshchilov I, Hutter F. Decoupled Weight Decay Regularization. arXiv. Preprint posted online January 4, 2019:arXiv:1711.05101https:\/\/doi.org\/10.48550\/arXiv.1711.05101","DOI":"10.48550\/arXiv.1711.05101"},{"issue":"4","key":"1636_CR61","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1109\/TMI.2020.3021387","volume":"41","author":"RJ Chen","year":"2022","unstructured":"Chen RJ, Lu MY, Wang J, et al. Pathomic fusion: an integrated framework for fusing histopathology and genomic features for cancer diagnosis and prognosis. IEEE Trans Med Imaging. 2022;41(4):757\u201370. https:\/\/doi.org\/10.1109\/TMI.2020.3021387.","journal-title":"IEEE Trans Med Imaging"},{"issue":"8","key":"1636_CR62","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1016\/j.ccell.2022.07.004","volume":"40","author":"RJ Chen","year":"2022","unstructured":"Chen RJ, Lu MY, Williamson DFK, et al. Pan-cancer integrative histology-genomic analysis via multimodal deep learning. Cancer Cell. 2022;40(8):865-878.e6. https:\/\/doi.org\/10.1016\/j.ccell.2022.07.004.","journal-title":"Cancer Cell"},{"issue":"17","key":"1636_CR63","doi-asserted-by":"publisher","first-page":"5091","DOI":"10.1158\/1078-0432.CCR-16-2540","volume":"23","author":"J Beane","year":"2017","unstructured":"Beane J, Mazzilli SA, Tassinari AM, et al. Detecting the presence and progression of premalignant lung lesions via airway gene expression. Clin Cancer Res. 2017;23(17):5091\u2013100. https:\/\/doi.org\/10.1158\/1078-0432.CCR-16-2540.","journal-title":"Clin Cancer Res"},{"issue":"3","key":"1636_CR64","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1038\/nm1556","volume":"13","author":"A Spira","year":"2007","unstructured":"Spira A, Beane JE, Shah V, et al. Airway epithelial gene expression in the diagnostic evaluation of smokers with suspect lung cancer. Nat Med. 2007;13(3):361\u20136. https:\/\/doi.org\/10.1038\/nm1556.","journal-title":"Nat Med"},{"issue":"1","key":"1636_CR65","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1158\/1940-6207.CAPR-08-0011","volume":"1","author":"J Beane","year":"2008","unstructured":"Beane J, Sebastiani P, Whitfield TH, et al. A prediction model for lung cancer diagnosis that integrates genomic and clinical features. Cancer Prev Res (Phila Pa). 2008;1(1):56\u201364. https:\/\/doi.org\/10.1158\/1940-6207.CAPR-08-0011.","journal-title":"Cancer Prev Res (Phila Pa)"},{"issue":"1","key":"1636_CR66","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s12920-015-0091-3","volume":"8","author":"DH Whitney","year":"2015","unstructured":"Whitney DH, Elashoff MR, Porta-Smith K, et al. Derivation of a bronchial genomic classifier for lung cancer in a prospective study of patients undergoing diagnostic bronchoscopy. BMC Med Genomics. 2015;8(1):18. https:\/\/doi.org\/10.1186\/s12920-015-0091-3.","journal-title":"BMC Med Genomics"},{"issue":"3","key":"1636_CR67","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1056\/NEJMoa1504601","volume":"373","author":"GA Silvestri","year":"2015","unstructured":"Silvestri GA, Vachani A, Whitney D, et al. A bronchial genomic classifier for the diagnostic evaluation of lung cancer. N Engl J Med. 2015;373(3):243\u201351. https:\/\/doi.org\/10.1056\/NEJMoa1504601.","journal-title":"N Engl J Med"},{"issue":"9","key":"1636_CR68","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1164\/rccm.201208-1449OC","volume":"187","author":"K Steiling","year":"2013","unstructured":"Steiling K, van den Berge M, Hijazi K, et al. A dynamic bronchial airway gene expression signature of chronic obstructive pulmonary disease and lung function impairment. Am J Respir Crit Care Med. 2013;187(9):933\u201342. https:\/\/doi.org\/10.1164\/rccm.201208-1449OC.","journal-title":"Am J Respir Crit Care Med"},{"issue":"9","key":"1636_CR69","doi-asserted-by":"publisher","first-page":"3085","DOI":"10.1109\/TMI.2024.3386108","volume":"43","author":"Y Zheng","year":"2024","unstructured":"Zheng Y, Conrad RD, Green EJ, et al. Graph attention-based fusion of pathology images and gene expression for prediction of cancer survival. IEEE Trans Med Imaging. 2024;43(9):3085\u201397. https:\/\/doi.org\/10.1109\/TMI.2024.3386108.","journal-title":"IEEE Trans Med Imaging"},{"key":"1636_CR70","doi-asserted-by":"publisher","unstructured":"Chen LC, Papandreou G, Schroff F, Adam H. Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv. Preprint posted online December 5, 2017:arXiv:1706.05587https:\/\/doi.org\/10.48550\/arXiv.1706.05587","DOI":"10.48550\/arXiv.1706.05587"},{"key":"1636_CR71","doi-asserted-by":"publisher","unstructured":"Chen Y, Zou J. GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT. bioRxiv. Preprint posted online March 5, 2024:2023.10.16.562533https:\/\/doi.org\/10.1101\/2023.10.16.562533","DOI":"10.1101\/2023.10.16.562533"},{"key":"1636_CR72","doi-asserted-by":"crossref","unstructured":"Xu L, Kefella Y, Zhang Y, et al. Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesions. GitHub. Published online 2026. https:\/\/github.com\/vkola-lab\/gm2026.","DOI":"10.1101\/2025.06.06.25328492"}],"container-title":["Genome Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13073-026-01636-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13073-026-01636-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13073-026-01636-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T07:03:43Z","timestamp":1791270223000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13073-026-01636-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,8]]},"references-count":72,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1636"],"URL":"https:\/\/doi.org\/10.1186\/s13073-026-01636-8","relation":{},"ISSN":["1756-994X"],"issn-type":[{"value":"1756-994X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,8]]},"assertion":[{"value":"19 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2026","order":6,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":7,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Please note that following original publication, the URL to the Humor Tumor Atlas and the Funding declaration have been updated.","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The Lung PCA Consortium study was approved by the individual site Institutional Review Boards (IRBs) for every participating site, which were centrally and annually reviewed for compliance by a multi-site\u202foffice of research subject protection. All subjects were approached for and provided written informed consent to participate in the study in accordance with IRB regulations. Accrual, safety information, and adverse events are monitored by individual sites. The Detection of Early Lung Cancer Among Military Personnel (DECAMP) Consortium study was approved by the Human Research Protection Office of the Department of Defense and the individual site IRBs for every participating site. All subjects were approached for and provided written informed consent to participate in the study in accordance with IRB regulations. The Lung PCA and DECAMP individual site IRBs adhere to the ethical principles and guidelines delineated in the Belmont Report and the Helsinki Declaration.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Y.K., R.D.C., K.E.A., K.K., G.L., E.K., A.P., S.M.J., M.E.R., S.A.M., and J.E.B. have received support from sponsored research agreements from Johnson & Johnson Enterprise Innovation, Inc. The remaining authors declare that they have no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"69"}}