{"id":"W4388148234","doi":"10.1016/j.xpro.2023.102661","title":"A user-driven machine learning approach for RNA-based sample discrimination and hierarchical classification","year":2023,"lang":"en","type":"article","venue":"STAR Protocols","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Preprocessor; Machine learning; Sample (material); Feature selection; Pattern recognition (psychology); Data pre-processing; Data mining","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":[0.0003754709,0.0001258985,0.0001134921,0.0001047528,0.0001663438,0.00005312598,0.0001389601,0.0001521998,0.000008476454],"category_scores_gemma":[0.0003777055,0.000123448,0.00006361669,0.0001791392,0.00006219686,0.000004798416,0.00009271769,0.0001746889,0.000002791693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002375555,"about_ca_system_score_gemma":0.0001112697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002083237,"about_ca_topic_score_gemma":0.00001813335,"domain_scores_codex":[0.9988112,0.000130744,0.0001596663,0.0004200173,0.0002012743,0.0002771314],"domain_scores_gemma":[0.9994764,0.00003920367,0.00006190126,0.0002362256,0.00009943447,0.00008684221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004757772,0.00007622979,0.0002566022,0.0002499215,0.00003248541,9.336375e-7,0.00005846558,0.002165859,0.982763,0.001305908,0.0003908578,0.01222398],"study_design_scores_gemma":[0.003443003,0.00170299,0.001627615,0.00006025696,0.00002275546,0.000003122417,0.0001038257,0.5590715,0.3247104,0.0006069601,0.1082509,0.0003966673],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0179546,0.0000211915,0.9300872,0.0004270755,0.00001922556,0.05104462,0.0001683936,0.00008386874,0.0001937969],"genre_scores_gemma":[0.6671522,0.00002671867,0.05983239,0.0001389124,0.0002376134,0.265389,0.006253682,0.0001204695,0.0008490167],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8702549,"threshold_uncertainty_score":0.5034062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05038008013228811,"score_gpt":0.3519156868178682,"score_spread":0.3015356066855801,"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."}}