{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007139496,0.0001193666,0.0001446454,0.0001193722,0.001132954,0.0001684448,0.001592106,0.00007637616,0.0001361211],"category_scores_gemma":[0.00009964284,0.0001154949,0.00005482006,0.000124606,0.0006787038,0.00002384808,0.001694332,0.0000700651,0.00003204327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008870437,"about_ca_system_score_gemma":0.0001812014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003342985,"about_ca_topic_score_gemma":0.001250904,"domain_scores_codex":[0.9985676,0.00003994361,0.0002313694,0.0007636683,0.000123735,0.0002736618],"domain_scores_gemma":[0.9958752,0.00000361697,0.0002329949,0.003670656,0.0001235913,0.00009395689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001679115,0.00009396248,0.002267977,0.00004029074,0.00002379583,0.000002207684,0.00002025246,2.399603e-7,0.9601471,0.00004856566,0.03702352,0.0003152422],"study_design_scores_gemma":[0.0007455849,0.0001325317,0.09355474,0.00003744683,0.00003482066,0.00001764548,0.00006960134,0.00001087203,0.135188,0.00002795534,0.7699133,0.0002675603],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9842228,0.0002416441,0.0001654933,0.0001118811,0.000802423,0.0002418702,0.01358143,0.00001145334,0.0006209699],"genre_scores_gemma":[0.9679075,0.00006734736,0.001254198,0.00005113785,0.0001244764,0.00000349985,0.02561044,0.00001393384,0.004967462],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8249592,"threshold_uncertainty_score":0.871388,"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."}}