{"id":"W3084007908","doi":"10.1101/2020.09.09.290049","title":"To rarefy or not to rarefy: Enhancing diversity analysis of microbial communities through next-generation sequencing and rarefying repeatedly","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":29,"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; Biology; DNA sequencing; Sample size determination; Computational biology; Statistics; Computer science; Genetics; Mathematics; Polymerase chain reaction; DNA; Bacteria","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007109756,0.0004649824,0.0009575449,0.0002670553,0.0008948002,0.0001140804,0.0009602131,0.0004378409,0.0006837192],"category_scores_gemma":[0.000228997,0.0004980821,0.0001663728,0.001272773,0.0002405754,0.0003008166,0.006363785,0.0008064226,0.00004497811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000585863,"about_ca_system_score_gemma":0.0001531089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006231542,"about_ca_topic_score_gemma":0.004558227,"domain_scores_codex":[0.9972669,0.0006757436,0.0006170805,0.0007445504,0.0002271491,0.0004685107],"domain_scores_gemma":[0.9979319,0.000194683,0.0003619482,0.001146728,0.0001138686,0.0002508671],"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":[0.000201702,0.00004355407,0.007993584,0.0001017005,0.000413171,0.00001473616,0.003044812,0.00536354,0.982446,0.00002145646,0.000353307,0.000002475521],"study_design_scores_gemma":[0.0004867124,0.0003056349,0.1122238,0.000242446,0.001153626,6.628617e-8,0.0002932043,0.001798971,0.8810739,0.000003861943,0.001201475,0.001216335],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9955994,0.00003601499,0.002691867,0.0003222329,0.0003081117,0.000605235,0.0003076071,0.0001185974,0.00001093668],"genre_scores_gemma":[0.9888527,0.00008226309,0.008360251,0.002524939,0.0000989746,0.00002723198,0.000006959511,0.00004150318,0.000005189489],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1042302,"threshold_uncertainty_score":0.9997471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07935693162924079,"score_gpt":0.2525432958231144,"score_spread":0.1731863641938736,"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."}}