{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002085632,0.0001189376,0.0001713477,0.0001436144,0.00005304212,0.00004152245,0.0000921143,0.00005692596,0.000003408842],"category_scores_gemma":[0.000031498,0.0001098313,0.00001101091,0.000157383,0.00004846951,0.00001603623,0.0002654182,0.00006071539,9.886691e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008503996,"about_ca_system_score_gemma":0.00005199085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003758062,"about_ca_topic_score_gemma":0.0002256284,"domain_scores_codex":[0.9990489,0.00004823579,0.0002441572,0.0004583572,0.00005565948,0.0001446511],"domain_scores_gemma":[0.9996923,0.00004488838,0.00003843044,0.0001168543,0.00006342724,0.00004414647],"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":[0.0004264214,0.000362991,0.03266275,0.0004836582,0.0005841756,0.00001630699,0.001817222,0.01468227,0.4478963,0.06850372,0.00409356,0.4284706],"study_design_scores_gemma":[0.001785286,0.00060213,0.01935128,0.00007031556,0.0001508016,0.00005601185,0.0007510576,0.871583,0.007368531,0.08236963,0.01520305,0.0007088502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9469859,0.00985258,0.04099661,0.001398413,0.00006008488,0.0002541974,0.0003744295,0.00001858848,0.00005920658],"genre_scores_gemma":[0.9799692,0.0006661799,0.01640719,0.000325932,0.0001023898,0.00002156482,0.002479547,0.00001327564,0.00001471805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8569008,"threshold_uncertainty_score":0.4478792,"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."}}