{"id":"W2130208436","doi":"10.1093/bib/bbr009","title":"A large-scale benchmark study of existing algorithms for taxonomy-independent microbial community analysis","year":2011,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":168,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Society of Microbiologists","funders":"National Center for Advancing Translational Sciences; National Institutes of Health; University of Michigan; National Institute of Diabetes and Digestive and Kidney Diseases; W. M. Keck Foundation; Alfred P. Sloan Foundation","keywords":"Benchmark (surveying); Cluster analysis; Computer science; Data mining; Hierarchical clustering; Scale (ratio); Machine learning; Algorithm; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02078043,0.002718294,0.001749665,0.003911896,0.0019652,0.002213459,0.003333239,0.00209631,0.0009572747],"category_scores_gemma":[0.04727513,0.0005166459,0.001676317,0.006286425,0.0009482106,0.003071644,0.002031686,0.001840935,0.0006870116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002130032,"about_ca_system_score_gemma":0.002371387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006893257,"about_ca_topic_score_gemma":0.007787733,"domain_scores_codex":[0.9877272,0.005556314,0.001211455,0.001778725,0.003085577,0.0006407088],"domain_scores_gemma":[0.960775,0.02263984,0.001029114,0.00568181,0.009109976,0.0007643199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002691825,0.002598105,0.02470527,0.002791916,0.001657852,0.0003068924,0.0005482362,0.3552891,0.0140639,0.007410598,0.0347212,0.5532151],"study_design_scores_gemma":[0.00064533,0.002264671,0.01370004,0.0002304644,0.000286516,0.0004143267,0.0004903995,0.9380253,0.02260084,0.008997693,0.0121833,0.0001611026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6395909,0.01610638,0.3117063,0.002051825,0.001198985,0.001749815,0.006076763,0.01146431,0.01005482],"genre_scores_gemma":[0.3977385,0.003536023,0.5737252,0.000409826,0.0001928784,0.001076739,0.02039344,0.001312976,0.001614435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02078043,"threshold_uncertainty_score":0.1098987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07934565095866285,"score_gpt":0.3035607196679215,"score_spread":0.2242150687092587,"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."}}