{"id":"W3040929481","doi":"10.1186/s12859-023-05509-4","title":"Cross-study analyses of microbial abundance using generalized common factor methods","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Nova Scotia Health Research Foundation","keywords":"Metagenomics; Interpretability; Computer science; Leverage (statistics); Microbiome; Bootstrapping (finance); Abundance (ecology); Covariance; Computational biology; Projection (relational algebra); Data mining; Machine learning; Data science; Biology; Ecology; Bioinformatics; Statistics; Mathematics; Algorithm; Genetics; Econometrics","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":["metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.0309693,0.002125125,0.002436885,0.004308551,0.001477863,0.00203863,0.003161435,0.002047461,0.002736934],"category_scores_gemma":[0.05822139,0.000882934,0.008216875,0.003024844,0.002263815,0.001675214,0.002925733,0.002497098,0.0005958973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000918044,"about_ca_system_score_gemma":0.001719682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005541047,"about_ca_topic_score_gemma":0.005559286,"domain_scores_codex":[0.9827032,0.01118305,0.0007271011,0.003897692,0.001059681,0.0004291652],"domain_scores_gemma":[0.9345138,0.04934394,0.003422747,0.008715494,0.003003595,0.001000363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.002132828,0.0008739608,0.1230329,0.0008350355,0.01715909,0.001266321,0.001744309,0.3339221,0.01759852,0.02278062,0.004713526,0.4739408],"study_design_scores_gemma":[0.0001187781,0.0006006724,0.01364744,0.00006616625,0.0006585171,0.0002549405,0.0002385046,0.9420342,0.002833856,0.03672391,0.00271067,0.0001124093],"study_design_candidate":"meta_analysis","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04187347,0.0003783057,0.9559697,0.0001517362,0.00006076581,0.0001773511,0.0003227711,0.0008783214,0.0001875609],"genre_scores_gemma":[0.4740628,0.0002776588,0.521086,0.0002013679,0.0001859541,0.0007798315,0.002264465,0.0004196779,0.0007222728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9975631,"threshold_uncertainty_score":0.1637833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1483872749104191,"score_gpt":0.4792971469326862,"score_spread":0.330909872022267,"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."}}