{"id":"W4401162536","doi":"10.1101/2024.07.30.605945","title":"Introducing ‘identification probability’ for automated and transferable assessment of metabolite identification confidence in metabolomics and related studies","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Common Fund; Pacific Northwest National Laboratory; National Institute of Environmental Health Sciences; Natural Sciences and Engineering Research Council of Canada; National Institute of General Medical Sciences; Battelle; National Cancer Institute; National Institutes of Health; U.S. Environmental Protection Agency; U.S. Department of Energy","keywords":"Metabolomics; Identification (biology); Context (archaeology); Computer science; Ambiguity; Metabolite; Mass spectrometry; Data mining; Computational biology; Chemistry; Chromatography; Biology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04990979,0.001535411,0.001879402,0.008379122,0.001122499,0.008136514,0.003700384,0.003195899,0.003200928],"category_scores_gemma":[0.2277188,0.001048308,0.001933432,0.005376216,0.003882102,0.01243817,0.008044511,0.004347432,0.001005847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001992227,"about_ca_system_score_gemma":0.00222435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001521727,"about_ca_topic_score_gemma":0.0009084724,"domain_scores_codex":[0.9507396,0.0236186,0.004905515,0.00681797,0.01295267,0.0009655659],"domain_scores_gemma":[0.7021983,0.2176583,0.02515028,0.02984678,0.0228761,0.002270242],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001262583,0.0005488433,0.07160353,0.001317135,0.0007078198,0.000742488,0.001956942,0.1954786,0.01462037,0.1704778,0.008101263,0.5331826],"study_design_scores_gemma":[0.00007557675,0.0003232088,0.01094478,0.0003141898,0.0001513278,0.0005287232,0.0003376227,0.7897734,0.01472223,0.1751134,0.007467027,0.0002484652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01572602,0.0003421133,0.9789782,0.0007703997,0.00008621113,0.0001340898,0.0003389835,0.001868104,0.001755764],"genre_scores_gemma":[0.3703189,0.000221612,0.6272192,0.0003442767,0.0001765634,0.0003186284,0.0005868826,0.0003316337,0.00048236],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9500902,"threshold_uncertainty_score":0.2639513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01548800368846703,"score_gpt":0.280534268488618,"score_spread":0.265046264800151,"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."}}