{"id":"W4409324328","doi":"10.1016/j.xpro.2025.103705","title":"Protocol for obtaining cancer type and subtype predictions using subSCOPE","year":2025,"lang":"en","type":"article","venue":"STAR Protocols","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Institutes of Health; Canada's Michael Smith Genome Sciences Centre; National Cancer Institute; Foundation for the National Institutes of Health","keywords":"Protocol (science); Type (biology); Cancer; Computational biology; Computer science; Biology; Medicine; Genetics; Pathology; Paleontology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.006816084,0.0009399537,0.001074963,0.002446778,0.001451708,0.001221174,0.001419144,0.00135212,0.1299463],"category_scores_gemma":[0.01494834,0.001245801,0.0008959498,0.001432314,0.0006537028,0.0006955499,0.001462577,0.002785072,0.05158446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008046608,"about_ca_system_score_gemma":0.003285549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002694299,"about_ca_topic_score_gemma":0.004533886,"domain_scores_codex":[0.9973179,0.0008653974,0.0005340551,0.0005495867,0.0005464415,0.000186658],"domain_scores_gemma":[0.9894608,0.002589198,0.0004504102,0.003834246,0.003177392,0.0004878668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.008909484,0.001576543,0.01436885,0.002600921,0.0003907924,0.001495973,0.002008059,0.003210554,0.0877324,0.00956491,0.5707533,0.2973883],"study_design_scores_gemma":[0.00199156,0.001263968,0.02482051,0.0008494403,0.000271352,0.002626899,0.0009061867,0.009022571,0.06496304,0.01433355,0.8786194,0.0003314926],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"protocol","genre_scores_codex":[0.04473962,0.002410899,0.4915458,0.004141828,0.002245561,0.135688,0.2233494,0.04066265,0.05521622],"genre_scores_gemma":[0.06203437,0.001352207,0.4237167,0.003381622,0.000542499,0.2993629,0.1523292,0.004957661,0.05232285],"genre_candidate":"protocol","genre_consensus":null,"teacher_disagreement_score":0.1299463,"threshold_uncertainty_score":0.4347137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06690811567861747,"score_gpt":0.4626135912829332,"score_spread":0.3957054756043157,"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."}}