{"id":"W4312276303","doi":"10.56530/lcgc.na.tn9486s6","title":"Turning Metabolomics Data Processing from a “Black Box” to a “White Box”","year":2022,"lang":"en","type":"article","venue":"LCGC North America","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Institutes of Health; University of British Columbia","keywords":"Metabolomics; Feature extraction; Feature selection; Computer science; Black box; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Data mining; Chemistry; Chromatography","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":[0.006626401,0.002491029,0.002203354,0.004275354,0.001333776,0.00582124,0.001984121,0.001514271,0.01363106],"category_scores_gemma":[0.01453374,0.001599434,0.001895241,0.002680755,0.00205376,0.005081136,0.004897728,0.0051599,0.01160484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009724031,"about_ca_system_score_gemma":0.001320341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001598641,"about_ca_topic_score_gemma":0.001895293,"domain_scores_codex":[0.9969471,0.0008241993,0.0002903774,0.0007751003,0.001021359,0.0001419499],"domain_scores_gemma":[0.9860907,0.006595158,0.0008522845,0.003076861,0.002675983,0.0007091406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0023001,0.0004411006,0.006299765,0.00165789,0.0009357776,0.0009416224,0.001375972,0.006671794,0.1529783,0.01984767,0.1856004,0.6209496],"study_design_scores_gemma":[0.000595969,0.001045839,0.01873137,0.001206118,0.0005917654,0.001578095,0.001158457,0.1202036,0.2465315,0.1692398,0.4382053,0.0009122809],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01135729,0.001167913,0.921467,0.006658658,0.001618085,0.0004878778,0.003420711,0.04814197,0.005680399],"genre_scores_gemma":[0.05165692,0.001821622,0.9176039,0.006985839,0.001184506,0.0008147055,0.004711475,0.009264592,0.005956409],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01363106,"threshold_uncertainty_score":0.04560041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01701638394116192,"score_gpt":0.2566565022593248,"score_spread":0.2396401183181629,"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."}}