{"id":"W4292388628","doi":"10.1101/2022.08.19.504330","title":"Implications of taxonomic bias for microbial differential-abundance analysis","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of General Medical Sciences; U.S. Department of Energy; Office of Science; National Science Foundation; National Institutes of Health; Research Nova Scotia","keywords":"Interpretability; Relative species abundance; Abundance (ecology); Commit; Microbiome; Computer science; Ecology; Data science; Statistics; Data mining; Biology; Bioinformatics; Artificial intelligence; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09737011,0.001253773,0.001185449,0.001978715,0.00159922,0.002967443,0.002866946,0.001160096,0.00276818],"category_scores_gemma":[0.3187968,0.0005585055,0.001696029,0.002565861,0.00360153,0.003659377,0.003539622,0.003107962,0.0007266873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003097616,"about_ca_system_score_gemma":0.002457781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003653129,"about_ca_topic_score_gemma":0.003040404,"domain_scores_codex":[0.9277885,0.0460855,0.004216067,0.008403076,0.01252265,0.0009841182],"domain_scores_gemma":[0.7305667,0.2104356,0.01516025,0.02514002,0.01756031,0.001137056],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001838424,0.0005231804,0.1852743,0.00309491,0.002973177,0.001393311,0.003316229,0.1500117,0.04843378,0.293892,0.02869416,0.2805549],"study_design_scores_gemma":[0.0001412884,0.0003074067,0.02855583,0.0007674266,0.0004162877,0.000935184,0.0006614419,0.4335062,0.04362486,0.4682588,0.02256021,0.0002652156],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05877539,0.001552233,0.9290116,0.002972404,0.0009226112,0.0002567623,0.001024753,0.001437649,0.004046535],"genre_scores_gemma":[0.6626267,0.0005301263,0.3296628,0.002961336,0.0002995579,0.0005729272,0.001354444,0.001128559,0.0008635289],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9026299,"threshold_uncertainty_score":0.5149485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02290430979130305,"score_gpt":0.2542282694697396,"score_spread":0.2313239596784366,"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."}}