{"id":"W4399394743","doi":"10.1371/journal.pcbi.1011912","title":"Common data models to streamline metabolomics processing and annotation, and implementation in a Python pipeline","year":2024,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Institute of Allergy and Infectious Diseases; National Cancer Institute; National Human Genome Research Institute; National Institutes of Health","keywords":"Python (programming language); Computer science; Pipeline (software); Annotation; Metabolomics; Standardization; Data mining; Data processing; Data quality; Data science; Bioinformatics; Database; Artificial intelligence; Biology; Engineering; Programming language","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":[0.008745657,0.0024461,0.001455748,0.00246466,0.001682774,0.004724144,0.007143113,0.001412778,0.01750724],"category_scores_gemma":[0.02038683,0.002348061,0.003759393,0.003045425,0.002334687,0.005995051,0.008095008,0.006847717,0.01413247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00225475,"about_ca_system_score_gemma":0.009007752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007038113,"about_ca_topic_score_gemma":0.007342826,"domain_scores_codex":[0.996013,0.0006049524,0.0007541728,0.0008805501,0.001335834,0.0004114158],"domain_scores_gemma":[0.9923832,0.001950565,0.0005358421,0.002875111,0.001641077,0.0006143138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002714806,0.001052821,0.0208328,0.003534132,0.0009899174,0.001516427,0.002790886,0.08766529,0.04118636,0.1572796,0.4751854,0.2052517],"study_design_scores_gemma":[0.0004811132,0.0001437489,0.003999399,0.0004012103,0.0001893482,0.0006546022,0.0002757597,0.3312564,0.05898855,0.1402503,0.4629087,0.0004509264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00322709,0.00009340235,0.8000885,0.0008119803,0.0002095693,0.0005484312,0.01942837,0.171068,0.004524649],"genre_scores_gemma":[0.04632968,0.0004970715,0.800824,0.001555993,0.000122307,0.0043662,0.07509115,0.06451413,0.006699339],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01750724,"threshold_uncertainty_score":0.05856758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03772739808309164,"score_gpt":0.337090973441497,"score_spread":0.2993635753584054,"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."}}