{"id":"W4385067933","doi":"10.1101/2023.07.20.549584","title":"A Taxonomically-informed Mass Spectrometry Search Tool for Microbial Metabolomics Data","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Complementary and Integrative Health; National Institute of Diabetes and Digestive and Kidney Diseases; Biotechnology and Biological Sciences Research Council; Agricultural Research Service; National Institutes of Health; Junta de Andalucía; Novo Nordisk Fonden; Norges Forskningsråd; Universidad de Costa Rica; Instituto Tecnológico y de Estudios Superiores de Monterrey; Fundação de Amparo à Pesquisa do Estado do Amazonas; Ministerio de Ciencia e Innovación; Ministry of Science and ICT, South Korea; Deutsches Zentrum für Infektionsforschung; Novo Nordisk; Ford Foundation; National Research Foundation of Korea; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Consejo Nacional de Ciencia y Tecnología; National Research Foundation; Austrian Science Fund; Deutsche Forschungsgemeinschaft; Fundação de Apoio ao Desenvolvimento do Ensino, Ciência e Tecnologia do Estado de Mato Grosso do Sul; Eidgenössische Technische Hochschule Zürich; Fundação de Amparo à Pesquisa do Estado de São Paulo; Francis Crick Institute; Universidad de Málaga; National Academies of Sciences, Engineering, and Medicine; Canadian Institute for Advanced Research; Gordon and Betty Moore Foundation; Max-Planck-Gesellschaft; Simons Foundation; U.S. Department of Agriculture; Howard Hughes Medical Institute; National Science Foundation","keywords":"Metabolomics; Fragmentation (computing); Computational biology; Identification (biology); Annotation; Microbial ecology; Metabolite; Mass spectrometry; A priori and a posteriori; Biology; Computer science; Chemistry; Ecology; Bacteria; Bioinformatics; Biochemistry; Chromatography; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003306501,0.002556314,0.00129977,0.007368803,0.001265983,0.002810327,0.001801313,0.001824346,0.01111437],"category_scores_gemma":[0.00892315,0.0008753263,0.001246566,0.003751705,0.000534907,0.002658259,0.003512142,0.001198209,0.006606349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005780451,"about_ca_system_score_gemma":0.001348521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009612793,"about_ca_topic_score_gemma":0.00207558,"domain_scores_codex":[0.9984945,0.0002942734,0.000208655,0.0004021507,0.0004942509,0.0001061519],"domain_scores_gemma":[0.9977143,0.001133695,0.0003107738,0.0003483298,0.0003100991,0.0001828275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005174426,0.0007187182,0.02013372,0.004177306,0.001958372,0.005952503,0.001325383,0.01399696,0.2958136,0.02213135,0.2072677,0.42135],"study_design_scores_gemma":[0.001251965,0.000543142,0.01676843,0.0007550448,0.0005942629,0.006133702,0.0009578175,0.423195,0.2353556,0.07379113,0.2401267,0.0005272073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04433654,0.001669652,0.6121981,0.0009376817,0.0002143193,0.0003872695,0.05883645,0.2764108,0.005009122],"genre_scores_gemma":[0.140446,0.0006536365,0.7633028,0.0004904338,0.0001270261,0.0004501217,0.07880408,0.01353337,0.002192479],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01111437,"threshold_uncertainty_score":0.03718132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03970207097338779,"score_gpt":0.2690631329212702,"score_spread":0.2293610619478824,"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."}}