{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007233658,0.001158488,0.001116768,0.00342618,0.0008264714,0.002017657,0.001107928,0.001407491,0.0007938679],"category_scores_gemma":[0.02064059,0.0006134786,0.001920663,0.002364727,0.001121622,0.002443212,0.00226572,0.002350877,0.0008724798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000688219,"about_ca_system_score_gemma":0.001054793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001100452,"about_ca_topic_score_gemma":0.002188791,"domain_scores_codex":[0.9960073,0.001234279,0.0002679522,0.001010032,0.001262395,0.0002180968],"domain_scores_gemma":[0.9921005,0.004464005,0.0009775071,0.001105784,0.001141048,0.0002110875],"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":[0.0005483482,0.0002825714,0.03206832,0.001134778,0.0005272895,0.0006636893,0.002181764,0.03395582,0.5813585,0.01235679,0.001517988,0.3334042],"study_design_scores_gemma":[0.00007128644,0.0006569911,0.0354044,0.000241883,0.0004829685,0.002363526,0.0006056026,0.3606202,0.5178782,0.04686224,0.03435963,0.00045314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09034698,0.0007096379,0.9048731,0.0002440111,0.00009659901,0.0001036614,0.0005268128,0.001955351,0.001143824],"genre_scores_gemma":[0.1930651,0.0006799996,0.8027028,0.000357256,0.00009917577,0.0002800366,0.001780048,0.0004183665,0.000617323],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007233658,"threshold_uncertainty_score":0.03825575,"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."}}