{"id":"W4283394500","doi":"10.1186/s40793-022-00425-1","title":"Metadata harmonization–Standards are the key for a better usage of omics data for integrative microbiome analysis","year":2022,"lang":"en","type":"letter","venue":"Environmental Microbiome","topic":"Research Data Management Practices","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Horizon 2020 Framework Programme","keywords":"Metadata; Microbiome; Computer science; Interoperability; Harmonization; Data science; Ontology; World Wide Web; Bioinformatics; Biology","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00274833,0.0005778128,0.0008499245,0.0009001835,0.0005370363,0.002081188,0.01398057,0.0002306692,0.0002290252],"category_scores_gemma":[0.0002600623,0.0004475769,0.0004678629,0.001279831,0.0004657257,0.01051502,0.009971969,0.0009039044,0.000009057168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000645262,"about_ca_system_score_gemma":0.0001220915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005101721,"about_ca_topic_score_gemma":0.00002135995,"domain_scores_codex":[0.9951259,0.0005212625,0.0008084947,0.001950284,0.0008812679,0.0007128216],"domain_scores_gemma":[0.9914822,0.001096364,0.001285214,0.006020335,0.00005696294,0.00005894939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005758014,0.0001591038,0.00005953362,0.0002267718,0.004502302,0.00002850369,0.0002337061,0.00002772506,0.01571187,0.0001448047,0.9781024,0.00074566],"study_design_scores_gemma":[0.0005482289,0.0001357103,0.00005789941,0.00002016158,0.00139659,0.000008666981,0.0002047633,0.001911951,0.002216278,0.00006319632,0.9929608,0.0004758079],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.000152141,0.0005691637,0.6124277,0.1788698,0.0003021093,0.002298678,0.2053294,0.00003251462,0.00001853409],"genre_scores_gemma":[0.001436904,0.002002647,0.232779,0.2802555,0.001155932,0.001747789,0.457448,0.000338194,0.02283599],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3796487,"threshold_uncertainty_score":0.9997976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06388592106245132,"score_gpt":0.3156390226104956,"score_spread":0.2517531015480443,"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."}}