{"id":"W2607313420","doi":"10.1038/sdata.2017.35","title":"A geographically-diverse collection of 418 human gut microbiome pathway genome databases","year":2017,"lang":"en","type":"article","venue":"Scientific Data","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Genome Alberta; King Abdullah University of Science and Technology; Genome British Columbia; Genome Canada; Tula Foundation; School of Medicine, Stanford University; Compute Canada; National Institute of General Medical Sciences; Canadian Institute for Advanced Research","keywords":"Metagenomics; Microbiome; Human Microbiome Project; Compendium; Human microbiome; Computational biology; Annotation; Biology; Data science; Genome; Bioinformatics; Computer science; Genetics; Gene; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002060664,0.001240156,0.001022599,0.006693901,0.001077985,0.001685528,0.001243454,0.000981992,0.01273457],"category_scores_gemma":[0.006158739,0.0006474279,0.001099847,0.0121917,0.0003335547,0.0009077589,0.002751897,0.001087029,0.007285304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006859638,"about_ca_system_score_gemma":0.004602319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00724403,"about_ca_topic_score_gemma":0.0143529,"domain_scores_codex":[0.9983601,0.0002871419,0.0002974143,0.000509182,0.0004184985,0.0001277139],"domain_scores_gemma":[0.9975941,0.0007344794,0.0003616753,0.0004438387,0.0005154893,0.0003504849],"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":[0.004273266,0.000506836,0.08869828,0.02119255,0.002181615,0.002186461,0.001737622,0.00854882,0.07040643,0.007734384,0.4603176,0.3322161],"study_design_scores_gemma":[0.0005876702,0.0002694176,0.1278154,0.00183408,0.0009922696,0.001859999,0.0008222891,0.004562765,0.0220932,0.006130712,0.8328216,0.0002105298],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01915799,0.002561446,0.004267488,0.0002026899,0.00003441194,0.0001686486,0.9686321,0.001598917,0.003376229],"genre_scores_gemma":[0.01353625,0.00103386,0.01372959,0.0001148038,0.0000102705,0.0003073422,0.9706036,0.0001802677,0.0004840237],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01273457,"threshold_uncertainty_score":0.04260135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07441962437904774,"score_gpt":0.336488425230079,"score_spread":0.2620688008510312,"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."}}