{"id":"W3212450750","doi":"10.1038/s41598-021-01636-1","title":"Enhancing diversity analysis by repeatedly rarefying next generation sequencing data describing microbial communities","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":214,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Natural Resources Canada; Environment and Climate Change Canada","keywords":"Normalization (sociology); Amplicon sequencing; Amplicon; Metagenomics; Computer science; DNA sequencing; Biology; Computational biology; Sample size determination; Deep sequencing; Statistics; Data mining; Genetics; Genome; Mathematics; Polymerase chain reaction; DNA","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":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002222685,0.0001461112,0.0002549156,0.00008647823,0.00339072,0.0003014681,0.0006073905,0.0001074979,0.004571036],"category_scores_gemma":[0.0001429246,0.0001613287,0.00009126574,0.0009810464,0.0004394454,0.0008179047,0.004395667,0.0002917499,0.00005341903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002628391,"about_ca_system_score_gemma":0.00008382244,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005580528,"about_ca_topic_score_gemma":0.05292111,"domain_scores_codex":[0.997771,0.0005487704,0.0004242182,0.0006836951,0.0002220681,0.0003502934],"domain_scores_gemma":[0.9972789,0.00007701508,0.0002421434,0.002265294,0.00005413425,0.00008246964],"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":[0.000002525589,0.00003551411,0.02691235,0.000004281407,0.00007844322,0.0001016112,0.002460221,0.001346113,0.9446349,0.000001532941,0.0241745,0.0002479675],"study_design_scores_gemma":[0.0003087154,0.00004096457,0.003658133,0.00005845998,0.0009023058,0.0005620006,0.00822512,0.01580816,0.9415078,0.0007934187,0.02707602,0.0010589],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956456,0.00009717752,0.001738261,0.00005635674,0.001511211,0.00008910958,0.00002176001,0.0000487484,0.0007917131],"genre_scores_gemma":[0.9923801,0.00001270684,0.001543594,0.0002029585,0.00003233197,0.000001598878,0.004731866,0.000007570522,0.001087319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04734058,"threshold_uncertainty_score":0.9979067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1422205077476642,"score_gpt":0.2561644236012007,"score_spread":0.1139439158535366,"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."}}