{"id":"W2995906327","doi":"10.1093/gigascience/giz146","title":"Systematic processing of ribosomal RNA gene amplicon sequencing data","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; National Research Council Canada","funders":"McGill University","keywords":"Amplicon; Computer science; Computational biology; Pipeline (software); Workflow; Ribosomal RNA; Amplicon sequencing; Scripting language; Data mining; Biology; Gene; Genetics; Database; 16S ribosomal RNA; Operating system; Polymerase chain reaction","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":[0.0003662501,0.00009179099,0.000169647,0.00002301654,0.00005981962,0.00002144461,0.000617374,0.00003934824,0.00000285078],"category_scores_gemma":[0.00008396948,0.00007734836,0.00002880464,0.0001017073,0.00009301949,0.000002436259,0.0004091417,0.00002964775,0.000008037087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009285215,"about_ca_system_score_gemma":0.0001392713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001872628,"about_ca_topic_score_gemma":0.000005157309,"domain_scores_codex":[0.9990407,0.0000226303,0.0002393367,0.0003694045,0.0001434211,0.0001845636],"domain_scores_gemma":[0.9990418,0.000009882976,0.0001522275,0.0006867619,0.00007231233,0.00003703638],"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":[0.000003062125,0.000006648518,0.00195756,0.0006123236,0.00001172933,3.391683e-7,0.00008444671,0.0001051899,0.9969809,0.00002701284,0.00001275176,0.0001980081],"study_design_scores_gemma":[0.000285295,0.0002048556,0.005299113,0.0005167759,0.0000363989,0.00003426171,0.0004539338,0.003206694,0.9893837,0.00009942664,0.0002083704,0.0002711512],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954517,0.002254923,0.001107766,0.0000170278,0.0001164927,0.0002167797,0.00002245509,0.000002404063,0.0008104921],"genre_scores_gemma":[0.9971123,0.00005897612,0.002564865,0.00006128737,0.00004341756,0.000005021858,0.00001400313,0.00000743698,0.000132741],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007597204,"threshold_uncertainty_score":0.3154175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0278345674920407,"score_gpt":0.2574009687923783,"score_spread":0.2295664013003376,"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."}}