{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003912875,0.0001737561,0.0003145066,0.0001167441,0.0001303777,0.00004285955,0.0002425326,0.0001464775,0.00002541498],"category_scores_gemma":[0.00006547164,0.0001550879,0.0001429824,0.0003191828,0.00009474254,0.000009658325,0.0001897185,0.00008061509,0.00001853743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001893712,"about_ca_system_score_gemma":0.0001534292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001378223,"about_ca_topic_score_gemma":0.00008939352,"domain_scores_codex":[0.9986936,0.0001156024,0.0006270969,0.0001591263,0.000104068,0.0003005476],"domain_scores_gemma":[0.9990809,0.00002603428,0.0002839493,0.0004337878,0.0001035118,0.00007184942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005730653,0.00007267472,0.03406844,0.0002095172,0.0000657932,5.296328e-7,0.0004952941,0.00138295,0.9626474,0.000005526224,0.0003701294,0.000624483],"study_design_scores_gemma":[0.002940083,0.0005971494,0.1421683,0.00004900358,0.0001158937,0.00002643626,0.001129887,0.05381562,0.7931037,0.0000193147,0.005397887,0.0006367274],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9778219,0.0001135087,0.02127215,0.000005509624,0.0002083496,0.0003063167,0.0001227527,0.00002820479,0.0001212923],"genre_scores_gemma":[0.6413873,0.00009575541,0.3573847,0.0001667924,0.0001407245,0.000007334005,0.0003211176,0.00003617723,0.0004601091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3364346,"threshold_uncertainty_score":0.6324301,"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."}}