{"id":"W4394738894","doi":"10.1101/2024.02.13.580048","title":"Common data models to streamline metabolomics processing and annotation, and implementation in a Python pipeline","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":2,"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); Metabolomics; Annotation; Standardization; Data mining; Data quality; Data processing; Data science; Bioinformatics; Database; Artificial intelligence; Engineering; Biology; 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":[0.009681297,0.003095527,0.001355226,0.002842695,0.001805224,0.005253145,0.00733765,0.001508725,0.01859249],"category_scores_gemma":[0.02217976,0.00262288,0.004022002,0.002737488,0.002560374,0.007184986,0.008487815,0.006466981,0.01599213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002393994,"about_ca_system_score_gemma":0.007616696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006361873,"about_ca_topic_score_gemma":0.004599181,"domain_scores_codex":[0.9946744,0.0007808557,0.0009588051,0.001246231,0.001822585,0.0005170043],"domain_scores_gemma":[0.9900694,0.00246371,0.0006636746,0.003924874,0.002201083,0.0006772584],"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":[0.003615644,0.00111857,0.01922803,0.003203362,0.0008871808,0.001790799,0.002270961,0.08209573,0.04588792,0.1071884,0.4629017,0.2698117],"study_design_scores_gemma":[0.0005424506,0.0002319551,0.00388326,0.0005092403,0.0002074504,0.0005801547,0.0002190838,0.3965611,0.1115564,0.1024859,0.3826452,0.0005779185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.002695698,0.0000860379,0.7450976,0.0006161916,0.0001853891,0.0005589892,0.01453244,0.2333651,0.002862514],"genre_scores_gemma":[0.05270252,0.0004203021,0.7906559,0.001540006,0.0001268802,0.004030097,0.0724327,0.07189287,0.006198806],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01859249,"threshold_uncertainty_score":0.0621981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02328455525994449,"score_gpt":0.285433986057001,"score_spread":0.2621494307970565,"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."}}