{"id":"W6930782644","doi":"10.5281/zenodo.15346211","title":"Multi-view deep learning of highly multiplexed imaging data improves association of cell states with clinical outcomes","year":2025,"lang":"en","type":"preprint","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Ubiquitin and proteasome pathways","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Deep learning; Association (psychology); Multiplexing; Pattern recognition (psychology); Convolutional neural network; Artificial neural network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00270417,0.001135295,0.0008585103,0.001413187,0.0003159275,0.001660011,0.0009687159,0.001890365,0.0311766],"category_scores_gemma":[0.0115885,0.0003870862,0.001563871,0.0007931401,0.0004342663,0.0007945945,0.001135077,0.00210155,0.01209806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000828106,"about_ca_system_score_gemma":0.001151077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005279874,"about_ca_topic_score_gemma":0.005334447,"domain_scores_codex":[0.999249,0.0001481934,0.00004698308,0.000289935,0.0001658804,0.00009989916],"domain_scores_gemma":[0.9964059,0.002071836,0.000198911,0.0005581443,0.0004458589,0.0003192365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.007651655,0.001372786,0.1165328,0.001239952,0.001544235,0.0008326047,0.0001857388,0.04789533,0.03028845,0.002417929,0.5697176,0.220321],"study_design_scores_gemma":[0.00255871,0.001538173,0.1892757,0.00070046,0.001162279,0.002561857,0.0004403523,0.5700009,0.1064905,0.02917163,0.09570017,0.0003992847],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.3278236,0.003661367,0.112944,0.008828814,0.003175694,0.0004608873,0.5056138,0.02255906,0.01493286],"genre_scores_gemma":[0.6096151,0.0008245939,0.05264515,0.001474936,0.00043943,0.0004708707,0.3161764,0.003026419,0.01532706],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0311766,"threshold_uncertainty_score":0.1042961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04179144739734362,"score_gpt":0.3020585208946097,"score_spread":0.260267073497266,"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."}}