{"doi":"10.1101/2022.01.21.477189","title":"Deep learning can predict multi-omic biomarkers from routine pathology images: A systematic large-scale study","abstract":"Abstract We assessed the pan-cancer predictability of multi-omic biomarkers from haematoxylin and eosin (H&E)-stained whole slide images (WSI) using deep learning (DL) throughout a systematic study. A total of 13,443 DL models predicting 4,481 multi-omic biomarkers across 32 cancer types were trained and validated. The investigated biomarkers included a broad range of genetic, transcriptomic, proteomic, and metabolic alterations, as well as established markers relevant for prognosis, molecular subtypes and clinical outcomes. Overall, we found that DL can predict multi-omic biomarkers directly from routine histology images across solid cancer types, with 50% of the models performing at an area under the curve (AUC) of more than 0.633 (with 25% of the models having an AUC larger than 0.711). A wide range of biomarkers were detectable from routine histology images across all investigated cancer types, with a mean AUC of at least 0.62 in almost all malignancies. Strikingly, we observed that biomarker predictability was mostly consistent and not dependent on sample size and class ratio, suggesting a degree of true predictability inherent in histomorphology. Together, the results of our study show the potential of DL to predict a multitude of biomarkers across the omics spectrum using only routine slides. This paves the way for accelerating diagnosis and developing more precise treatments for cancer patients.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2022,"id":296966,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":14,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.8394,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2022-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":984967,"name":"Debapriya Mehrotra","orcid":null,"position":1,"is_corresponding":false},{"id":984401,"name":"Julian Schmidt","orcid":"0000-0003-4944-4916","position":2,"is_corresponding":false},{"id":984402,"name":"André Geraldes","orcid":"0000-0002-5113-6587","position":3,"is_corresponding":false},{"id":984403,"name":"Shikha Singhal","orcid":"0000-0001-6306-9484","position":4,"is_corresponding":false},{"id":984404,"name":"Julius Hense","orcid":"0009-0007-1160-1636","position":5,"is_corresponding":false},{"id":984968,"name":"Xiusi Li","orcid":null,"position":6,"is_corresponding":false},{"id":883218,"name":"Cher Bass","orcid":"0000-0002-7928-3394","position":7,"is_corresponding":false},{"id":110000,"name":"Jakob Nikolas Kather","orcid":"0000-0002-3730-5348","position":8,"is_corresponding":false},{"id":984405,"name":"Pahini Pandya","orcid":"0000-0002-5914-1954","position":9,"is_corresponding":false},{"id":984406,"name":"Pandu Raharja-Liu","orcid":"0000-0001-6707-6278","position":10,"is_corresponding":false},{"id":984400,"name":"Salim Arslan","orcid":"0000-0002-4329-0947","position":0,"is_corresponding":true}],"reference_count":65,"raw_metadata":null,"created_at":"2026-07-19T00:31:21.257700Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}