{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:06:09Z","timestamp":1783901169952,"version":"3.55.0"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:00:00Z","timestamp":1778544000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"vor","delay-in-days":62,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Accurate prediction of Homologous Recombination Deficiency (HRD) is vital for personalized cancer therapy, yet genomic assays are often costly and complex. Predicting HRD from Hematoxylin and Eosin (H&amp;E) stained whole-slide images (WSIs) via deep learning offers an alternative, but model generalization across diverse cancer types remains challenging.  We developed a three-stage transfer learning framework to improve HRD prediction across cancer types. After establishing baseline models on data from eight cancer types, the TCGA-BRCA model was selected as a pretrained model for transfer learning applied to eligible cohorts.  Transfer learning enhanced HRD prediction performance specifically in cancers with histological similarity to the TCGA-BRCA source model. The AUC increased by +\u20094% (TCGA-LUAD), +\u20095% (CPTAC-LUAD), and +\u20091% (SARC) compared to baseline models. Interpretability analysis confirmed that the model\u2019s predictions were driven by histologically relevant tumor regions, which was further supported by quantitative cellular analysis showing that HRD-high status was characterized by a significantly higher density of neoplastic cells (HRD-high: median 16.0, IQR 1.0\u201327.0 vs. HRD-low: median 1.0, IQR:0.0\u20135.0;\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.001), whereas HRD-low cases featured a stromal-rich microenvironment.\n                    <jats:bold>Conclusions<\/jats:bold>\n                    This study demonstrates that transfer learning can enhance HRD prediction from H&amp;E images for cancer types sharing histopathological features with the TCGA-BRCA source model, offering a more efficient and accessible approach for clinical HRD assessment.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-52094-6","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T11:05:31Z","timestamp":1778583931000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-cancer homologous recombination deficiency prediction from whole slide images using transfer learning"],"prefix":"10.1038","volume":"16","author":[{"given":"Zhengxiao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruijian","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoming","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,12]]},"reference":[{"key":"52094_CR1","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1016\/j.celrep.2018.03.076","volume":"23","author":"TA Knijnenburg","year":"2018","unstructured":"Knijnenburg, T. A. et al. Genomic and molecular landscape of DNA damage repair deficiency across the cancer genome atlas. Cell Rep. 23, 239\u2013254. https:\/\/doi.org\/10.1016\/j.celrep.2018.03.076 (2018).","journal-title":"Cell Rep."},{"key":"52094_CR2","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1016\/j.cell.2011.02.013","volume":"144","author":"D Hanahan","year":"2011","unstructured":"Hanahan, D. & Weinberg, R. A. Hallmarks of cancer: The next generation. Cell 144, 646\u2013674. https:\/\/doi.org\/10.1016\/j.cell.2011.02.013 (2011).","journal-title":"Cell"},{"key":"52094_CR3","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1038\/cr.2008.1","volume":"18","author":"X Li","year":"2008","unstructured":"Li, X. & Heyer, W. D. Homologous recombination in DNA repair and DNA damage tolerance. Cell. Res. 18, 99\u2013113. https:\/\/doi.org\/10.1038\/cr.2008.1 (2008).","journal-title":"Cell. Res."},{"key":"52094_CR4","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1038\/nrc3342","volume":"12","author":"P Bouwman","year":"2012","unstructured":"Bouwman, P. & Jonkers, J. The effects of deregulated DNA damage signalling on cancer chemotherapy response and resistance. Nat. Rev. Cancer 12, 587\u2013598. https:\/\/doi.org\/10.1038\/nrc3342 (2012).","journal-title":"Nat. Rev. Cancer"},{"key":"52094_CR5","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1038\/nrc3088","volume":"11","author":"AJ Deans","year":"2011","unstructured":"Deans, A. J. & West, S. C. DNA interstrand crosslink repair and cancer. Nat. Rev. Cancer 11, 467\u2013480. https:\/\/doi.org\/10.1038\/nrc3088 (2011).","journal-title":"Nat. Rev. Cancer"},{"key":"52094_CR6","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1200\/po.19.00345","volume":"4","author":"ES Sokol","year":"2020","unstructured":"Sokol, E. S. et al. Pan-Cancer Analysis of BRCA1 and BRCA2 genomic Alterations and their association with genomic instability as measured by genome-wide loss of heterozygosity. JCO Precis. Oncol. 4, 442\u2013465. https:\/\/doi.org\/10.1200\/po.19.00345 (2020).","journal-title":"JCO Precis. Oncol."},{"key":"52094_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1200\/PO.16.00031","volume":"1","author":"WD den Brok","year":"2017","unstructured":"den Brok, W. D. et al. Homologous recombination deficiency in breast cancer: A clinical review. JCO Precis Oncol 1, 1\u201313. https:\/\/doi.org\/10.1200\/PO.16.00031 (2017).","journal-title":"JCO Precis Oncol"},{"key":"52094_CR8","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.1158\/1078-0432.CCR-18-1443","volume":"25","author":"MM de Jonge","year":"2019","unstructured":"de Jonge, M. M. et al. Frequent homologous recombination deficiency in high-grade endometrial carcinomas. Clin. Cancer Res. 25, 1087\u20131097. https:\/\/doi.org\/10.1158\/1078-0432.CCR-18-1443 (2019).","journal-title":"Clin. Cancer Res."},{"key":"52094_CR9","doi-asserted-by":"publisher","first-page":"3764","DOI":"10.1158\/1078-0432.CCR-15-2477","volume":"22","author":"ML Telli","year":"2016","unstructured":"Telli, M. L. et al. Homologous recombination deficiency (HRD) score predicts response to platinum-containing neoadjuvant chemotherapy in patients with triple-negative breast cancer. Clin. Cancer Res. 22, 3764\u20133773. https:\/\/doi.org\/10.1158\/1078-0432.CCR-15-2477 (2016).","journal-title":"Clin. Cancer Res."},{"key":"52094_CR10","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/S1470-2045(22)00739-2","volume":"24","author":"E Rodler","year":"2023","unstructured":"Rodler, E. et al. Cisplatin with veliparib or placebo in metastatic triple-negative breast cancer and BRCA mutation-associated breast cancer (S1416): A randomised, double-blind, placebo-controlled, phase 2 trial. Lancet. Oncol. 24, 162\u2013174. https:\/\/doi.org\/10.1016\/S1470-2045(22)00739-2 (2023).","journal-title":"Lancet. Oncol."},{"key":"52094_CR11","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1038\/s41416-023-02326-7","volume":"129","author":"D Bhamidipati","year":"2023","unstructured":"Bhamidipati, D., Haro-Silerio, J. I., Yap, T. A. & Ngoi, N. PARP inhibitors: Enhancing efficacy through rational combinations. Br. J. Cancer 129, 904\u2013916. https:\/\/doi.org\/10.1038\/s41416-023-02326-7 (2023).","journal-title":"Br. J. Cancer"},{"key":"52094_CR12","doi-asserted-by":"publisher","first-page":"2394","DOI":"10.1056\/NEJMoa2105215","volume":"384","author":"ANJ Tutt","year":"2021","unstructured":"Tutt, A. N. J. et al. Adjuvant Olaparib for Patients with BRCA1- or BRCA2-Mutated Breast Cancer. N Engl J Med 384, 2394\u20132405. https:\/\/doi.org\/10.1056\/NEJMoa2105215 (2021).","journal-title":"N Engl J Med"},{"key":"52094_CR13","doi-asserted-by":"publisher","first-page":"3633","DOI":"10.1200\/JCO.20.03318","volume":"39","author":"SS Ramalingam","year":"2021","unstructured":"Ramalingam, S. S. et al. Veliparib in combination with platinum-based chemotherapy for first-line treatment of advanced squamous cell lung cancer: A randomized, multicenter phase III study. J. Clin. Oncol. 39, 3633\u20133644. https:\/\/doi.org\/10.1200\/JCO.20.03318 (2021).","journal-title":"J. Clin. Oncol."},{"key":"52094_CR14","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1158\/2159-8290.CD-11-0206","volume":"2","author":"NJ Birkbak","year":"2012","unstructured":"Birkbak, N. J. et al. Telomeric allelic imbalance indicates defective DNA repair and sensitivity to DNA-damaging agents. Cancer Discov. 2, 366\u2013375. https:\/\/doi.org\/10.1158\/2159-8290.CD-11-0206 (2012).","journal-title":"Cancer Discov."},{"key":"52094_CR15","doi-asserted-by":"publisher","first-page":"1776","DOI":"10.1038\/bjc.2012.451","volume":"107","author":"V Abkevich","year":"2012","unstructured":"Abkevich, V. et al. Patterns of genomic loss of heterozygosity predict homologous recombination repair defects in epithelial ovarian cancer. Br. J. Cancer 107, 1776\u20131782. https:\/\/doi.org\/10.1038\/bjc.2012.451 (2012).","journal-title":"Br. J. Cancer"},{"key":"52094_CR16","doi-asserted-by":"publisher","first-page":"5454","DOI":"10.1158\/0008-5472.CAN-12-1470","volume":"72","author":"T Popova","year":"2012","unstructured":"Popova, T. et al. Ploidy and large-scale genomic instability consistently identify basal-like breast carcinomas with BRCA1\/2 inactivation. Cancer Res. 72, 5454\u20135462. https:\/\/doi.org\/10.1158\/0008-5472.CAN-12-1470 (2012).","journal-title":"Cancer Res."},{"key":"52094_CR17","doi-asserted-by":"publisher","first-page":"3556","DOI":"10.1038\/s41388-023-02839-8","volume":"42","author":"C Callens","year":"2023","unstructured":"Callens, C. et al. Shallow whole genome sequencing approach to detect homologous recombination deficiency in the PAOLA-1\/ENGOT-OV25 phase-III trial. Oncogene 42, 3556\u20133563. https:\/\/doi.org\/10.1038\/s41388-023-02839-8 (2023).","journal-title":"Oncogene"},{"key":"52094_CR18","doi-asserted-by":"publisher","first-page":"7521","DOI":"10.1158\/1078-0432.CCR-17-1941","volume":"23","author":"EY Zhao","year":"2017","unstructured":"Zhao, E. Y. et al. Homologous recombination deficiency and platinum-based therapy outcomes in advanced breast cancer. Clin. Cancer Res. 23, 7521\u20137530. https:\/\/doi.org\/10.1158\/1078-0432.CCR-17-1941 (2017).","journal-title":"Clin. Cancer Res."},{"key":"52094_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-19406-4","volume":"11","author":"L Nguyen","year":"2020","unstructured":"Nguyen, L., J, W. M. M., Van Hoeck, A. & Cuppen, E. Pan-cancer landscape of homologous recombination deficiency. Nat. Commun. 11, 5584. https:\/\/doi.org\/10.1038\/s41467-020-19406-4 (2020).","journal-title":"Nat. Commun."},{"key":"52094_CR20","doi-asserted-by":"publisher","first-page":"1606","DOI":"10.1016\/j.annonc.2020.08.2102","volume":"31","author":"RE Miller","year":"2020","unstructured":"Miller, R. E. et al. ESMO recommendations on predictive biomarker testing for homologous recombination deficiency and PARP inhibitor benefit in ovarian cancer. Ann. Oncol. 31, 1606\u20131622. https:\/\/doi.org\/10.1016\/j.annonc.2020.08.2102 (2020).","journal-title":"Ann. Oncol."},{"key":"52094_CR21","doi-asserted-by":"publisher","first-page":"W102","DOI":"10.1093\/nar\/gky406","volume":"46","author":"J Lee","year":"2018","unstructured":"Lee, J. et al. Mutalisk: A web-based somatic mutation analysis toolkit for genomic, transcriptional and epigenomic signatures. Nucl. Acids Res. 46, W102\u2013W108. https:\/\/doi.org\/10.1093\/nar\/gky406 (2018).","journal-title":"Nucl. Acids Res."},{"key":"52094_CR22","doi-asserted-by":"publisher","first-page":"4714","DOI":"10.1158\/1078-0432.CCR-22-0749","volume":"28","author":"F Batalini","year":"2022","unstructured":"Batalini, F. et al. Mutational signature 3 detected from clinical panel sequencing is associated with responses to Olaparib in breast and ovarian cancers. Clin. Cancer Res. 28, 4714\u20134723. https:\/\/doi.org\/10.1158\/1078-0432.CCR-22-0749 (2022).","journal-title":"Clin. Cancer Res."},{"key":"52094_CR23","doi-asserted-by":"publisher","first-page":"6159","DOI":"10.1158\/1078-0432.CCR-10-1027","volume":"16","author":"M Graeser","year":"2010","unstructured":"Graeser, M. et al. A marker of homologous recombination predicts pathologic complete response to neoadjuvant chemotherapy in primary breast cancer. Clin. Cancer Res. 16, 6159\u20136168. https:\/\/doi.org\/10.1158\/1078-0432.CCR-10-1027 (2010).","journal-title":"Clin. Cancer Res."},{"key":"52094_CR24","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17678-4","volume":"11","author":"B Schmauch","year":"2020","unstructured":"Schmauch, B. et al. A deep learning model to predict RNA-Seq expression of tumours from whole slide images. Nat. Commun. 11, 3877. https:\/\/doi.org\/10.1038\/s41467-020-17678-4 (2020).","journal-title":"Nat. Commun."},{"key":"52094_CR25","doi-asserted-by":"publisher","first-page":"1780","DOI":"10.1109\/JBHI.2023.3249354","volume":"27","author":"X Liu","year":"2023","unstructured":"Liu, X. et al. Development of prognostic biomarkers by TMB-guided WSI analysis: A two-step approach. IEEE J. Biomed. Health Inform. 27, 1780\u20131789. https:\/\/doi.org\/10.1109\/JBHI.2023.3249354 (2023).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"52094_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01131-7","volume":"7","author":"CW Wang","year":"2024","unstructured":"Wang, C. W. et al. Deep learning to assess microsatellite instability directly from histopathological whole slide images in endometrial cancer. npj Digit. Med. 7, 143. https:\/\/doi.org\/10.1038\/s41746-024-01131-7 (2024).","journal-title":"npj Digit. Med."},{"key":"52094_CR27","doi-asserted-by":"publisher","first-page":"3550","DOI":"10.1200\/JCO.23.02641","volume":"42","author":"EN Bergstrom","year":"2024","unstructured":"Bergstrom, E. N. et al. Deep learning artificial intelligence predicts homologous recombination deficiency and platinum response from histologic slides. J. Clin. Oncol. 42, 3550\u20133560. https:\/\/doi.org\/10.1200\/JCO.23.02641 (2024).","journal-title":"J. Clin. Oncol."},{"key":"52094_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2022.100872","volume":"3","author":"T Lazard","year":"2022","unstructured":"Lazard, T. et al. Deep learning identifies morphological patterns of homologous recombination deficiency in luminal breast cancers from whole slide images. Cell Rep. Med. 3, 100872. https:\/\/doi.org\/10.1016\/j.xcrm.2022.100872 (2022).","journal-title":"Cell Rep. Med."},{"key":"52094_CR29","doi-asserted-by":"publisher","DOI":"10.1186\/s12915-024-02022-9","volume":"22","author":"CML Loeffler","year":"2024","unstructured":"Loeffler, C. M. L. et al. Prediction of homologous recombination deficiency from routine histology with attention-based multiple instance learning in nine different tumor types. BMC Biol. 22, 225. https:\/\/doi.org\/10.1186\/s12915-024-02022-9 (2024).","journal-title":"BMC Biol."},{"key":"52094_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.esmoop.2021.100144","volume":"6","author":"NYL Ngoi","year":"2021","unstructured":"Ngoi, N. Y. L. & Tan, D. S. P. The role of homologous recombination deficiency testing in ovarian cancer and its clinical implications: Do we need it?. ESMO Open 6, 100144. https:\/\/doi.org\/10.1016\/j.esmoop.2021.100144 (2021).","journal-title":"ESMO Open"},{"key":"52094_CR31","doi-asserted-by":"publisher","DOI":"10.3390\/jpm11070612","author":"S Wagener-Ryczek","year":"2021","unstructured":"Wagener-Ryczek, S., Merkelbach-Bruse, S. & Siemanowski, J. Biomarkers for homologous recombination deficiency in cancer. J. Pers. Med. https:\/\/doi.org\/10.3390\/jpm11070612 (2021).","journal-title":"J. Pers. Med."},{"key":"52094_CR32","doi-asserted-by":"publisher","DOI":"10.3390\/jpm13020284","author":"A Mangogna","year":"2023","unstructured":"Mangogna, A. et al. Homologous recombination deficiency in ovarian cancer: From the biological rationale to current diagnostic approaches. J. Pers. Med. https:\/\/doi.org\/10.3390\/jpm13020284 (2023).","journal-title":"J. Pers. Med."},{"key":"52094_CR33","doi-asserted-by":"publisher","first-page":"937","DOI":"10.2217\/fon-2021-1113","volume":"18","author":"A Leith","year":"2022","unstructured":"Leith, A. et al. Real-world homologous recombination repair mutation testing in metastatic castration-resistant prostate cancer in the USA, Europe and Japan. Future Oncol. 18, 937\u2013951. https:\/\/doi.org\/10.2217\/fon-2021-1113 (2022).","journal-title":"Future Oncol."},{"key":"52094_CR34","doi-asserted-by":"publisher","first-page":"3239","DOI":"10.1158\/1078-0432.CCR-20-0418","volume":"26","author":"W Park","year":"2020","unstructured":"Park, W. et al. Genomic methods identify homologous recombination deficiency in pancreas adenocarcinoma and optimize treatment selection. Clin. Cancer Res. 26, 3239\u20133247. https:\/\/doi.org\/10.1158\/1078-0432.CCR-20-0418 (2020).","journal-title":"Clin. Cancer Res."},{"key":"52094_CR35","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1109\/JAS.2022.106004","volume":"10","author":"W Wu","year":"2023","unstructured":"Wu, W., L., Z., L., D. & D., Z. A survey on negative transfer. IEEE\/CAA J. Autom. Sin. 10, 305\u2013329. https:\/\/doi.org\/10.1109\/JAS.2022.106004 (2023).","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"52094_CR36","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJPQ Yang","year":"2010","unstructured":"Yang, S. J. P. Q. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22, 1345\u20131359. https:\/\/doi.org\/10.1109\/TKDE.2009.191 (2010).","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"52094_CR37","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1016\/0002-9378(62)90694-4","volume":"83","author":"MR Abell","year":"1962","unstructured":"Abell, M. R. & Gosling, J. R. Gland cell carcinoma (adenocarcinoma) of the uterine cervix. Am. J. Obstet. Gynecol. 83, 729\u2013755. https:\/\/doi.org\/10.1016\/0002-9378(62)90694-4 (1962).","journal-title":"Am. J. Obstet. Gynecol."},{"key":"52094_CR38","doi-asserted-by":"publisher","DOI":"10.3390\/cancers16223879","author":"N Shahadat","year":"2024","unstructured":"Shahadat, N., Lama, R. & Nguyen, A. Lung and colon cancer detection using a deep AI model. Cancers (Basel) https:\/\/doi.org\/10.3390\/cancers16223879 (2024).","journal-title":"Cancers (Basel)"},{"key":"52094_CR39","doi-asserted-by":"publisher","first-page":"1024","DOI":"10.1002\/1878-0261.12813","volume":"15","author":"LA Moukarzel","year":"2021","unstructured":"Moukarzel, L. A. et al. The genetic landscape of metaplastic breast cancers and uterine carcinosarcomas. Mol. Oncol. 15, 1024\u20131039. https:\/\/doi.org\/10.1002\/1878-0261.12813 (2021).","journal-title":"Mol. Oncol."},{"key":"52094_CR40","doi-asserted-by":"publisher","DOI":"10.1200\/PO.22.00085","volume":"6","author":"S Takamatsu","year":"2022","unstructured":"Takamatsu, S. et al. Utility of homologous recombination deficiency biomarkers across cancer types. JCO Precis. Oncol. 6, e2200085. https:\/\/doi.org\/10.1200\/PO.22.00085 (2022).","journal-title":"JCO Precis. Oncol."},{"key":"52094_CR41","doi-asserted-by":"publisher","DOI":"10.3390\/ijms231911326","author":"C Nero","year":"2022","unstructured":"Nero, C. et al. Deep-learning to predict BRCA mutation and survival from digital H&E slides of epithelial ovarian cancer. Int. J. Mol. Sci. https:\/\/doi.org\/10.3390\/ijms231911326 (2022).","journal-title":"Int. J. Mol. Sci."},{"key":"52094_CR42","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-025-01045-9","volume":"5","author":"Y Cheng","year":"2025","unstructured":"Cheng, Y. et al. Synergistic H&E and IHC image analysis by AI predicts cancer biomarkers and survival outcomes in colorectal and breast cancer. Commun. Med. 5, 328. https:\/\/doi.org\/10.1038\/s43856-025-01045-9 (2025).","journal-title":"Commun. Med."},{"key":"52094_CR43","doi-asserted-by":"publisher","DOI":"10.1038\/s41523-024-00620-y","volume":"10","author":"H Liu","year":"2024","unstructured":"Liu, H., Xie, X. & Wang, B. Deep learning infers clinically relevant protein levels and drug response in breast cancer from unannotated pathology images. npj Breast Cancer 10, 18. https:\/\/doi.org\/10.1038\/s41523-024-00620-y (2024).","journal-title":"npj Breast Cancer"},{"key":"52094_CR44","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13050946","author":"JA How","year":"2021","unstructured":"How, J. A. et al. Modification of homologous recombination deficiency score threshold and association with long-term survival in epithelial ovarian cancer. Cancers (Basel) https:\/\/doi.org\/10.3390\/cancers13050946 (2021).","journal-title":"Cancers (Basel)"},{"key":"52094_CR45","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.jncc.2024.05.005","volume":"4","author":"D Zhao","year":"2024","unstructured":"Zhao, D. et al. Establishing the homologous recombination score threshold in metastatic prostate cancer patients to predict the efficacy of PARP inhibitors. J. Natl. Cancer Cent. 4, 280\u2013287. https:\/\/doi.org\/10.1016\/j.jncc.2024.05.005 (2024).","journal-title":"J. Natl. Cancer Cent."},{"key":"52094_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103143","volume":"94","author":"F Horst","year":"2024","unstructured":"Horst, F. et al. CellViT: Vision transformers for precise cell segmentation and classification. Med. Image Anal. 94, 103143. https:\/\/doi.org\/10.1016\/j.media.2024.103143 (2024).","journal-title":"Med. Image Anal."},{"key":"52094_CR47","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-021-09082-y","volume":"22","author":"Z Lai","year":"2022","unstructured":"Lai, Z. et al. Landscape of homologous recombination deficiencies in solid tumours: Analyses of two independent genomic datasets. BMC Cancer 22, 13. https:\/\/doi.org\/10.1186\/s12885-021-09082-y (2022).","journal-title":"BMC Cancer"},{"key":"52094_CR48","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-025-03780-x","author":"G Campanella","year":"2025","unstructured":"Campanella, G. et al. Real-world deployment of a fine-tuned pathology foundation model for lung cancer biomarker detection. Nat. Med. https:\/\/doi.org\/10.1038\/s41591-025-03780-x (2025).","journal-title":"Nat. Med."},{"key":"52094_CR49","doi-asserted-by":"publisher","first-page":"1108","DOI":"10.1158\/2159-8290.CD-13-0219","volume":"3","author":"MJ Ellis","year":"2013","unstructured":"Ellis, M. J. et al. Connecting genomic alterations to cancer biology with proteomics: The NCI Clinical Proteomic Tumor Analysis Consortium. Cancer Discov. 3, 1108\u20131112. https:\/\/doi.org\/10.1158\/2159-8290.CD-13-0219 (2013).","journal-title":"Cancer Discov."},{"key":"52094_CR50","doi-asserted-by":"publisher","DOI":"10.1177\/03000605221133655","volume":"50","author":"J Kang","year":"2022","unstructured":"Kang, J., Lee, J., Lee, A. & Lee, Y. S. Prediction of homologous recombination deficiency from cancer gene expression data. J. Int. Med. Res. 50, 3000605221133655. https:\/\/doi.org\/10.1177\/03000605221133655 (2022).","journal-title":"J. Int. Med. Res."},{"key":"52094_CR51","doi-asserted-by":"publisher","DOI":"10.1186\/s40364-015-0033-4","volume":"3","author":"AM Marquard","year":"2015","unstructured":"Marquard, A. M. et al. Pan-cancer analysis of genomic scar signatures associated with homologous recombination deficiency suggests novel indications for existing cancer drugs. Biomark. Res. 3, 9. https:\/\/doi.org\/10.1186\/s40364-015-0033-4 (2015).","journal-title":"Biomark. Res."},{"key":"52094_CR52","doi-asserted-by":"publisher","first-page":"2416","DOI":"10.1056\/NEJMoa1911361","volume":"381","author":"I Ray-Coquard","year":"2019","unstructured":"Ray-Coquard, I. et al. Olaparib plus Bevacizumab as first-line maintenance in ovarian cancer. N. Engl. J. Med. 381, 2416\u20132428. https:\/\/doi.org\/10.1056\/NEJMoa1911361 (2019).","journal-title":"N. Engl. J. Med."},{"key":"52094_CR53","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-022-00276-6","volume":"6","author":"E Rempel","year":"2022","unstructured":"Rempel, E. et al. Pan-cancer analysis of genomic scar patterns caused by homologous repair deficiency (HRD). npj Precis. Oncol. 6, 36. https:\/\/doi.org\/10.1038\/s41698-022-00276-6 (2022).","journal-title":"npj Precis. Oncol."},{"key":"52094_CR54","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-59671-3","volume":"10","author":"H Takaya","year":"2020","unstructured":"Takaya, H., Nakai, H., Takamatsu, S., Mandai, M. & Matsumura, N. Homologous recombination deficiency status-based classification of high-grade serous ovarian carcinoma. Sci. Rep. 10, 2757. https:\/\/doi.org\/10.1038\/s41598-020-59671-3 (2020).","journal-title":"Sci. Rep."},{"key":"52094_CR55","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1979.4310076","author":"N Otsu","year":"1979","unstructured":"Otsu, N. A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. https:\/\/doi.org\/10.1109\/TSMC.1979.4310076 (1979).","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"52094_CR56","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu, M. Y. et al. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat. Biomed. Eng. 5, 555\u2013570. https:\/\/doi.org\/10.1038\/s41551-020-00682-w (2021).","journal-title":"Nat. Biomed. Eng."},{"key":"52094_CR57","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","volume":"30","author":"RJ Chen","year":"2024","unstructured":"Chen, R. J. et al. Towards a general-purpose foundation model for computational pathology. Nat. Med. 30, 850\u2013862. https:\/\/doi.org\/10.1038\/s41591-024-02857-3 (2024).","journal-title":"Nat. Med."},{"key":"52094_CR58","doi-asserted-by":"publisher","first-page":"D1243","DOI":"10.1093\/nar\/gkae974","volume":"53","author":"G Perez","year":"2025","unstructured":"Perez, G. et al. The UCSC Genome Browser database: 2025 update. Nucl. Acids Res. 53, D1243\u2013D1249. https:\/\/doi.org\/10.1093\/nar\/gkae974 (2025).","journal-title":"Nucleic Acids Res"},{"key":"52094_CR59","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2019.01289","volume":"9","author":"E Franzese","year":"2019","unstructured":"Franzese, E. et al. Genomic profile and BRCA-1 promoter methylation status in BRCA mutated ovarian cancer: New insights in predictive biomarkers of Olaparib response. Front. Oncol. 9, 1289. https:\/\/doi.org\/10.3389\/fonc.2019.01289 (2019).","journal-title":"Front. Oncol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52094-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52094-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52094-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T23:08:13Z","timestamp":1783897693000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52094-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,12]]},"references-count":59,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["52094"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-52094-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,12]]},"assertion":[{"value":"19 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This study utilized exclusively publicly available, de-identified data from The Cancer Genome Atlas (TCGA) and Clinical Proteomic Tumor Analysis Consortium (CPTAC). Therefore, ethical approval and informed consent were waived for this secondary analysis.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"21704"}}