{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004898128,0.001667129,0.0009468389,0.001533012,0.0009582621,0.001450024,0.002594336,0.00148993,0.01330205],"category_scores_gemma":[0.01211206,0.0008131802,0.001434798,0.001303951,0.0008881048,0.00101366,0.001833884,0.003288181,0.009110318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008261514,"about_ca_system_score_gemma":0.002004915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001973371,"about_ca_topic_score_gemma":0.004727728,"domain_scores_codex":[0.9976636,0.0006343455,0.0002261438,0.000689629,0.0006328208,0.0001535364],"domain_scores_gemma":[0.9960331,0.002062165,0.0001685799,0.0006112221,0.000994686,0.0001301579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001347285,0.0007429891,0.004068339,0.0007211217,0.0003992195,0.0004179062,0.0005595596,0.04280658,0.118492,0.01440179,0.04517737,0.7708658],"study_design_scores_gemma":[0.0001316922,0.0002401411,0.002352725,0.00004573786,0.00005743897,0.0002874968,0.00008075973,0.8557959,0.09371403,0.02046573,0.02669621,0.0001321992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001973837,0.00002466269,0.9785097,0.000058635,0.0000320689,0.0003102936,0.0006586528,0.01805873,0.0003734],"genre_scores_gemma":[0.0199908,0.00002586683,0.9738137,0.0001424971,0.00002066668,0.001503288,0.001632084,0.001457536,0.001413716],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01330205,"threshold_uncertainty_score":0.04449981,"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."}}