{"id":"W2017093118","doi":"10.1016/j.mimet.2011.03.014","title":"Rethinking microbial diversity analysis in the high throughput sequencing era","year":2011,"lang":"en","type":"article","venue":"Journal of Microbiological Methods","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":357,"is_retracted":false,"has_abstract":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul","keywords":"Pyrosequencing; Biology; Normalization (sociology); Deep sequencing; DNA sequencing; Computational biology; Sequence analysis; Representativeness heuristic; Metagenomics; Phylogenetic tree; Sequence (biology); 16S ribosomal RNA; Genetics; Evolutionary biology; Gene; Statistics; Genome","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002644461,0.0001385692,0.0003423131,0.00008573286,0.0001494737,0.00001323032,0.0005249588,0.0001738904,0.00002297053],"category_scores_gemma":[0.0002034236,0.00008150731,0.0003264611,0.0002486184,0.0001308075,0.000001467028,0.0003924854,0.0002910361,7.432891e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002885696,"about_ca_system_score_gemma":0.00003789885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008364833,"about_ca_topic_score_gemma":0.00003448675,"domain_scores_codex":[0.9982969,0.0008396245,0.0003914016,0.0002021047,0.00006065589,0.0002093569],"domain_scores_gemma":[0.9992561,0.000104966,0.0002930879,0.0002010079,0.0001116105,0.00003318191],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001077673,0.00005262488,0.021051,0.000002593963,0.0004479302,0.0000190435,0.002158879,0.00006830972,0.9744148,0.00008855236,0.0001211096,0.001467413],"study_design_scores_gemma":[0.001455617,0.001768731,0.4921634,0.00002882848,0.001185874,0.0004302871,0.002004436,0.00001192737,0.4788503,0.01695897,0.004547749,0.0005939496],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9868075,0.001270726,0.01124382,0.000108349,0.0002024201,0.00006825341,0.000006426866,9.997511e-7,0.0002915009],"genre_scores_gemma":[0.8090261,0.0003812031,0.1899447,0.0005034801,0.0001289052,6.658914e-7,0.000002337651,0.000003750939,0.000008787841],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4955645,"threshold_uncertainty_score":0.3323772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09077009378519163,"score_gpt":0.314304935185803,"score_spread":0.2235348414006114,"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."}}