{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00410704,0.000783873,0.001021226,0.001152973,0.000567024,0.001294401,0.001146497,0.000938619,0.0009781879],"category_scores_gemma":[0.008697794,0.0004819655,0.001287879,0.0008518695,0.001075344,0.001631658,0.001792216,0.001791748,0.0007550123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000503009,"about_ca_system_score_gemma":0.000750526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009076228,"about_ca_topic_score_gemma":0.00143689,"domain_scores_codex":[0.9978237,0.0005436936,0.0001048018,0.000592504,0.0007594738,0.0001758508],"domain_scores_gemma":[0.9971094,0.001406424,0.0004272485,0.0005024066,0.0004098336,0.0001448479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005440222,0.0002812811,0.0117764,0.0005145117,0.0002564476,0.0004373109,0.0006385279,0.02167808,0.6921535,0.007568142,0.001718834,0.2624329],"study_design_scores_gemma":[0.0000550775,0.0005349814,0.007380017,0.0000997104,0.0001768912,0.0008798141,0.0001948396,0.2838312,0.6805051,0.0125497,0.01357147,0.0002210936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1701627,0.001118146,0.8233315,0.0005132772,0.0002080143,0.0001484129,0.0002434451,0.00309478,0.001179616],"genre_scores_gemma":[0.3751875,0.0007558735,0.619725,0.0008234427,0.000112577,0.0003154117,0.0007614456,0.0005772976,0.001741503],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00410704,"threshold_uncertainty_score":0.02172041,"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."}}