{"id":"W3173226351","doi":"10.1101/2021.06.19.449110","title":"Ensuring that fundamentals of quantitative microbiology are reflected in microbial diversity analyses based on next-generation sequencing","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Alberta Innovates; University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Alpha diversity; Sample (material); Computer science; Amplicon; Statistics; Sample size determination; Inference; Data mining; Mathematics; Artificial intelligence; Biology; Species diversity; Genetics; Ecology","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":[0.02910354,0.0009720223,0.001258793,0.001833022,0.001227571,0.005972546,0.001583717,0.002300966,0.002282492],"category_scores_gemma":[0.06651808,0.001041078,0.001135756,0.001516294,0.003871908,0.004605039,0.002795766,0.003972636,0.003341974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001635562,"about_ca_system_score_gemma":0.004676037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001710609,"about_ca_topic_score_gemma":0.001879582,"domain_scores_codex":[0.9722507,0.01025864,0.001467097,0.00337607,0.01194258,0.0007049911],"domain_scores_gemma":[0.9606041,0.01865809,0.003472746,0.00941787,0.007272356,0.000574807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004294686,0.000520975,0.03827646,0.001914081,0.0003609883,0.000477335,0.002707043,0.03891704,0.3385578,0.2248027,0.01192531,0.3411108],"study_design_scores_gemma":[0.00007609212,0.0007588916,0.02640009,0.001442124,0.0001743019,0.001245181,0.001130883,0.1765117,0.2697913,0.3816044,0.1404148,0.0004502295],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009733437,0.000586752,0.9833978,0.001494847,0.0003020623,0.000167031,0.000349601,0.0007141476,0.003254303],"genre_scores_gemma":[0.1452149,0.001249801,0.8473678,0.001747482,0.0002555409,0.0007039327,0.0004898875,0.0004961303,0.00247455],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02910354,"threshold_uncertainty_score":0.153916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1238982246965084,"score_gpt":0.3045675343945226,"score_spread":0.1806693096980142,"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."}}