{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:11:11Z","timestamp":1778285471178,"version":"3.51.4"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014262","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T00:00:00Z","timestamp":1778198400000}}],"reference-count":41,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:00:00Z","timestamp":1777852800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["R01 CA276301"],"award-info":[{"award-number":["R01 CA276301"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Pelatonia Institute","award":["IRP CC13702"],"award-info":[{"award-number":["IRP CC13702"]}]},{"name":"The Ohio State University Department of Pathology and Comprehensive Cancer Center"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Protein expression within oncogenic or suppressive pathways is a hallmark indicator of oncogenesis. While traditional AI models in digital pathology attempt to predict singular proteins, there is a need to predict the downstream expression of proteins to indicate the propagation of signals. RNA expression provides novel information, but does not provide information about the downstream propagation of protein signals or whether those signals are functional. Using Reverse Phase Protein Array (RPPA) data with whole-slide images (WSIs) from the publicly available Cancer Genome Atlas Breast Adenocarcinoma dataset (TCGA-BRCA), we predict the expression of five key proteins identified from the apoptosis cascade, using DNA damage and repair (DDR) cascades as a biological control. Furthermore, we examine the performance of patch- level Vision Transformers (ViT) on the regression task, which was tested against the designed cellular-level ViT, CellRPPA. Our results demonstrate that patch-level vision transformers were unable to obtain statistically significant predictive results, achieving R-squared values\u2009&lt;\u20090.1 for all folds. In addition, CellViT obtained R-squared values &gt;0.1 in all five test folds. We also show that morphologically indicative cascades, such as the apoptosis cascade, provide significantly higher performance compared to the DDR cascade.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1014262","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T17:48:45Z","timestamp":1777916925000},"page":"e1014262","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting protein cascade expression from H&amp;E images"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0731-9383","authenticated-orcid":true,"given":"Alejandro","family":"Leyva","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdul Rehman","family":"Akbar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Khalid Khan","family":"Niazi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,5,4]]},"reference":[{"issue":"5","key":"pcbi.1014262.ref001","article-title":"Mutations in normal breast tissue and breast tumours","volume":"3","author":"IANPM Tomlinson","year":"2001","journal-title":"Breast Cancer Res"},{"issue":"2","key":"pcbi.1014262.ref002","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.trecan.2020.01.007","article-title":"TP53 mutations and outcomes in breast cancer: reading beyond the headlines","volume":"6","author":"A Shahbandi","year":"2020","journal-title":"Trends Cancer"},{"issue":"1","key":"pcbi.1014262.ref003","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1038\/s41467-023-35789-6","article-title":"Oncogenic mutations of PIK3CA lead to increased membrane recruitment driven by reorientation of the ABD, p85 and C-terminus","volume":"14","author":"ML Jenkins","year":"2023","journal-title":"Nat Commun"},{"issue":"4","key":"pcbi.1014262.ref004","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1080\/01926230701320337","article-title":"Apoptosis: a review of programmed cell death","volume":"35","author":"S Elmore","year":"2007","journal-title":"Toxicol Pathol"},{"issue":"3","key":"pcbi.1014262.ref005","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1042\/BCJ20210854","article-title":"The concept of intrinsic versus extrinsic apoptosis","volume":"479","author":"L Lossi","year":"2022","journal-title":"Biochem J"},{"issue":"9","key":"pcbi.1014262.ref006","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1038\/cr.2007.52","article-title":"Apoptosis signaling pathways and lymphocyte homeostasis","volume":"17","author":"G Xu","year":"2007","journal-title":"Cell Research"},{"key":"pcbi.1014262.ref007","article-title":"BH3-only proteins in apoptosis and beyond: an overview","author":"E Lomonosova","year":"2008","journal-title":"Oncogene"},{"issue":"1","key":"pcbi.1014262.ref008","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.drudis.2015.07.014","article-title":"A potential role of x-linked inhibitor of apoptosis protein in mitochondrial membrane permeabilization and its implication in cancer therapy","volume":"21","author":"AK Chaudhary","year":"2016","journal-title":"Drug Discov Today"},{"issue":"41","key":"pcbi.1014262.ref009","doi-asserted-by":"crossref","first-page":"5789","DOI":"10.1038\/sj.onc.1204810","article-title":"Analysis of FasL and TRAIL induced apoptosis pathways in glioma cells","volume":"20","author":"MJ Knight","year":"2001","journal-title":"Oncogene"},{"key":"pcbi.1014262.ref010","volume-title":"Traumatic brain injury","author":"J Grafman","year":"2015"},{"issue":"1","key":"pcbi.1014262.ref011","article-title":"Implications of DNA damage response and immunotherapy in tumor therapy","volume":"23","author":"W Li","year":"2025","journal-title":"Cell Commun Signal"},{"issue":"1","key":"pcbi.1014262.ref012","doi-asserted-by":"crossref","first-page":"17573","DOI":"10.1038\/s41598-020-74250-2","article-title":"BRCA1 and BRCA2 genes mutations among high risk breast cancer patients in Jordan","volume":"10","author":"M Abu-Helalah","year":"2020","journal-title":"Scientific Reports"},{"key":"pcbi.1014262.ref013","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1038\/ncomms1825","article-title":"Polyploid cells rewire DNA damage response networks to overcome replication stress-induced barriers for tumour progression","volume":"3","author":"L Zheng","year":"2012","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1014262.ref014","doi-asserted-by":"crossref","first-page":"523","DOI":"10.3390\/ijms23010523","article-title":"ATM: functions of ATM kinase and its relevance to hereditary tumors","volume":"23","author":"S Ueno","year":"2022","journal-title":"Int J Mol Sci"},{"key":"pcbi.1014262.ref015","article-title":"Rad51 determines pathway usage in post-replication repair","author":"D Meyer","year":"2026","journal-title":"Nature Commun"},{"issue":"2","key":"pcbi.1014262.ref016","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1086\/341943","article-title":"A CHEK2 genetic variant contributing to a substantial fraction of familial breast cancer","volume":"71","author":"P Vahteristo","year":"2002","journal-title":"Am J Hum Genet"},{"issue":"6","key":"pcbi.1014262.ref017","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.1086\/426403","article-title":"CHEK2 is a multiorgan cancer susceptibility gene","volume":"75","author":"C Cybulski","year":"2004","journal-title":"Am J Hum Genet"},{"issue":"18","key":"pcbi.1014262.ref018","doi-asserted-by":"crossref","first-page":"2233","DOI":"10.1101\/gad.1103603","article-title":"Integral role of Noxa in p53-mediated apoptotic response","volume":"17","author":"T Shibue","year":"2003","journal-title":"Genes Dev"},{"issue":"8","key":"pcbi.1014262.ref019","doi-asserted-by":"crossref","first-page":"993","DOI":"10.3390\/biom14080993","article-title":"The function of H2A histone variants and their roles in diseases","volume":"14","author":"X Yin","year":"2024","journal-title":"Biomolecules"},{"issue":"19","key":"pcbi.1014262.ref020","doi-asserted-by":"crossref","first-page":"3627","DOI":"10.1016\/j.molcel.2024.08.021","article-title":"An RNA-centric view of transcription and genome organization","volume":"84","author":"JE Henninger","year":"2024","journal-title":"Mol Cell"},{"issue":"1","key":"pcbi.1014262.ref021","doi-asserted-by":"crossref","first-page":"9886","DOI":"10.1038\/s41467-024-54182-5","article-title":"Digital profiling of gene expression from histology images with linearized attention","volume":"15","author":"M Pizurica","year":"2024","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1014262.ref022","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1038\/s41591-025-04060-4","article-title":"AI-enabled virtual spatial proteomics from histopathology for interpretable biomarker discovery in lung cancer","volume":"32","author":"Z Li","year":"2026","journal-title":"Nat Med"},{"issue":"4","key":"pcbi.1014262.ref023","doi-asserted-by":"crossref","first-page":"355","DOI":"10.3945\/an.111.000554","article-title":"Proteomics and systems biology: current and future applications in the nutritional sciences","volume":"2","author":"JB Moore","year":"2011","journal-title":"Adv Nutri"},{"issue":"7","key":"pcbi.1014262.ref024","article-title":"Prediction of HER2 status based on deep learning in H&E-stained histopathology images of bladder cancer","volume":"12","author":"P Jiao","year":"2024","journal-title":"Biomed"},{"issue":"12","key":"pcbi.1014262.ref025","doi-asserted-by":"crossref","first-page":"2127","DOI":"10.1158\/2767-9764.CRC-25-0155","article-title":"Deep learning predicts EGFR mutation status from histology images in non-small cell lung cancer","volume":"5","author":"J Park","year":"2025","journal-title":"Cancer Res Commun"},{"issue":"1","key":"pcbi.1014262.ref026","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1038\/s41421-025-00791-3","article-title":"Caspases: structural and molecular mechanisms and functions in cell death, innate immunity, and disease","volume":"11","author":"EK Nadendla","year":"2025","journal-title":"Cell Discov"},{"issue":"1","key":"pcbi.1014262.ref027","doi-asserted-by":"crossref","first-page":"15","DOI":"10.7171\/jbt.21-3202-001","article-title":"Reverse-phase protein array: technology, application, data processing, and integration","volume":"32","author":"C Coarfa","year":"2021","journal-title":"J Biomol Tech"},{"key":"pcbi.1014262.ref028","author":"A Dosovitskiy","year":"2020"},{"key":"pcbi.1014262.ref029","author":"F H\u00f6rst","year":"2023"},{"key":"pcbi.1014262.ref030","author":"ARE Akbar","year":"2025"},{"issue":"3","key":"pcbi.1014262.ref031","doi-asserted-by":"crossref","first-page":"100141","DOI":"10.1016\/j.xinn.2021.100141","article-title":"ClusterProfiler 4.0: a universal enrichment tool for interpreting omics data","volume":"2","author":"T Wu","year":"2021","journal-title":"The Innovation"},{"issue":"6","key":"pcbi.1014262.ref032","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1089\/ars.2012.4938","article-title":"New insights into the link between DNA damage and apoptosis","volume":"19","author":"D De Zio","year":"2013","journal-title":"Antioxid Redox Signal"},{"key":"pcbi.1014262.ref033","volume-title":"DNA damage response and cancer metastasis: clinical implications and therapeutic opportunities","author":"M Yin","year":"2022"},{"key":"pcbi.1014262.ref034","unstructured":"10x Genomics. Visium spatial gene expression. 2020. https:\/\/www.10xgenomics.com\/products\/visium-spatial-gene-expression"},{"key":"pcbi.1014262.ref035","unstructured":"RareCyte, Inc. Orion spatial biology platform. RareCyte technical documentation. 2023. https:\/\/rarecyte.com\/orion\/"},{"issue":"6","key":"pcbi.1014262.ref036","article-title":"Gene expression prediction from histology images via hypergraph neural networks","volume":"25","author":"B Li","year":"2024","journal-title":"Brief Bioinform"},{"key":"pcbi.1014262.ref037","article-title":"Multi-dataset integration and residual connections improve proteome prediction from transcriptomes using deep learning","author":"CW Cranney","year":"2024","journal-title":"bioRxiv"},{"issue":"7","key":"pcbi.1014262.ref038","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btaf363","article-title":"HECLIP: histology-enhanced contrastive learning for imputation of transcriptomics profiles","volume":"41","author":"Q Wang","year":"2025","journal-title":"Bioinformatics"},{"issue":"5","key":"pcbi.1014262.ref039","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1159\/000539678","article-title":"Artificial intelligence in colorectal cancer: from patient screening over tailoring treatment decisions to identification of novel biomarkers","volume":"105","author":"NG Reitsam","year":"2024","journal-title":"Digestion"},{"issue":"1","key":"pcbi.1014262.ref040","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1002\/path.70039","article-title":"Deep learning-based H&E-derived risk scores in colorectal cancer: associations with tumour morphology, biology, and predicted drug response","volume":"269","author":"NG Reitsam","year":"2026","journal-title":"J Pathol"},{"issue":"5","key":"pcbi.1014262.ref041","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1038\/s43018-025-00943-0","article-title":"UnitedMet harnesses RNA-metabolite covariation to impute metabolite levels in clinical samples","volume":"6","author":"AX Xie","year":"2025","journal-title":"Nat Cancer"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014262","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T00:00:00Z","timestamp":1778198400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014262","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T23:11:35Z","timestamp":1778281895000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014262"}},"subtitle":[],"editor":[{"given":"Sophia","family":"Rudorf","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,4]]},"references-count":41,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,4]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014262","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,4]]}}}