{"id":"W4385813836","doi":"10.1016/j.xcrm.2023.101173","title":"Deep learning integrates histopathology and proteogenomics at a pan-cancer level","year":2023,"lang":"en","type":"article","venue":"Cell Reports Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Mount Sinai Hospital","funders":"National Institute of Environmental Health Sciences; National Institute of General Medical Sciences; National Institute on Aging; National Cancer Institute; U.S. Department of Health and Human Services; National Institutes of Health; National Center for Advancing Translational Sciences; Government of South Australia; Clinical and Translational Science Institute, Boston University","keywords":"Proteogenomics; Interpretability; Proteomics; Transcriptome; Predictive power; Artificial intelligence; Generalizability theory; Cancer; Computer science; Biology; Computational biology; Bioinformatics; Machine learning; Pathology; Medicine; Internal medicine; Gene; Psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001066,0.0002307708,0.0005713796,0.0002564344,0.0001961399,0.000009597591,0.00006090504,0.0001266047,0.0004254529],"category_scores_gemma":[0.001954471,0.0001692872,0.00006140713,0.0003074065,0.0004383693,0.00003467218,0.0001325555,0.0006980342,0.0000298227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001602323,"about_ca_system_score_gemma":0.0001026867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001843962,"about_ca_topic_score_gemma":0.00001133651,"domain_scores_codex":[0.9981268,0.00006291608,0.0005451055,0.00053208,0.0003146778,0.0004183937],"domain_scores_gemma":[0.9987836,0.0001485161,0.0002939357,0.0003004019,0.00009826539,0.0003752945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001719453,0.00008499182,0.456219,0.0007776312,0.00007128467,0.01463723,0.005399046,0.000228864,0.3292588,0.00005517852,0.01680821,0.1762878],"study_design_scores_gemma":[0.00476842,0.001330785,0.353664,0.001345268,0.00076013,0.01443159,0.002219643,0.04662326,0.005684949,0.0009107125,0.567423,0.0008381948],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9744638,0.005888714,0.001256706,0.009283775,0.000886503,0.0005034399,6.657646e-7,0.0002878813,0.007428543],"genre_scores_gemma":[0.9543274,0.00358101,0.000921856,0.001370954,0.0006245928,0.00008388019,0.00009571115,0.00007445662,0.03892012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5506148,"threshold_uncertainty_score":0.6903332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02498740379555147,"score_gpt":0.3002621467212433,"score_spread":0.2752747429256918,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}