{"id":"W4364379153","doi":"10.1016/j.isci.2023.106610","title":"DEcancer: Machine learning framework tailored to liquid biopsy based cancer detection and biomarker signature selection","year":2023,"lang":"en","type":"article","venue":"iScience","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Liquid biopsy; Biomarker; Cancer; Cancer biomarkers; Biopsy; Medicine; Surgical oncology; Lung cancer; Biomarker discovery; Feature selection; Cohort; Oncology; Proteomics; Internal medicine; Machine learning; Computer science; Biology","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":[0.001271908,0.0009579915,0.0009954191,0.0007724801,0.0003988776,0.0008421523,0.001850972,0.001124008,0.002873966],"category_scores_gemma":[0.002571644,0.0004225822,0.0009091474,0.0005595133,0.0003477164,0.0006182772,0.001543424,0.001280993,0.001307799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007013308,"about_ca_system_score_gemma":0.001778166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004517263,"about_ca_topic_score_gemma":0.006681522,"domain_scores_codex":[0.9995381,0.00009792651,0.00002177692,0.0001506051,0.0001320263,0.00005958578],"domain_scores_gemma":[0.9995547,0.0001844867,0.00003545362,0.00004652551,0.0001174011,0.00006137585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001755387,0.0006936371,0.01042204,0.0004027341,0.0004344609,0.0009591332,0.0001319805,0.3000033,0.04970792,0.008217934,0.03512316,0.5921482],"study_design_scores_gemma":[0.00005567968,0.00009019381,0.0005861867,0.000007128222,0.00001958317,0.0001419297,0.000009635971,0.9866689,0.005230143,0.00333791,0.003834241,0.00001850356],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01616349,0.0004167036,0.9670313,0.0003911079,0.00008016358,0.0002455795,0.0008343253,0.01372316,0.001114192],"genre_scores_gemma":[0.2482695,0.0004961728,0.7362162,0.001227573,0.0001773689,0.000709511,0.005068727,0.0009439567,0.006890895],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004517263,"threshold_uncertainty_score":0.009614348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01307486008061387,"score_gpt":0.3008075965719427,"score_spread":0.2877327364913288,"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."}}