{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008357274,0.0001657586,0.0003427741,0.0001788212,0.0001776049,0.00001716399,0.0003120181,0.0001525781,0.00001624478],"category_scores_gemma":[0.00006420352,0.0001697006,0.0001415031,0.0002876684,0.0000500505,0.00001017533,0.0002215321,0.0001864302,0.000001414374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002735867,"about_ca_system_score_gemma":0.00007403931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001339705,"about_ca_topic_score_gemma":0.003900328,"domain_scores_codex":[0.9986498,0.00007049731,0.0007003318,0.000149555,0.00009105916,0.0003387593],"domain_scores_gemma":[0.9989934,0.00002532233,0.0003470061,0.0004444165,0.0001257921,0.00006403661],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002072911,0.02224549,0.5105826,0.003742178,0.004853956,0.00001187397,0.2940113,0.0006863253,0.1291748,0.0004563693,0.01247309,0.01968912],"study_design_scores_gemma":[0.02852203,0.01114197,0.5748315,0.0003515227,0.002502556,0.00008612406,0.1942339,0.02624134,0.103681,0.0002809156,0.0546964,0.003430779],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9770614,0.00003149287,0.02047599,0.000009049747,0.00005878733,0.000784042,0.0001218811,0.000008812013,0.001448529],"genre_scores_gemma":[0.9466692,0.00001310414,0.05259411,0.0003012634,0.00002883019,0.0000565527,0.0002562841,0.00001333512,0.00006730785],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09977739,"threshold_uncertainty_score":0.692019,"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."}}