{"id":"W2773939681","doi":"10.1038/nmeth.4458","title":"Critical Assessment of Metagenome Interpretation—a benchmark of metagenomics software","year":2017,"lang":"en","type":"article","venue":"Nature Methods","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":948,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Engineering and Physical Sciences Research Council; National Institute of Allergy and Infectious Diseases; Medical Research Council; Isaac Newton Institute for Mathematical Sciences; Deutsche Forschungsgemeinschaft; Biotechnology and Biological Sciences Research Council; Office of Science; Australian Research Council; Agency for Science, Technology and Research; Joint Genome Institute; U.S. Department of Energy; Division of Mathematical Sciences; Villum Fonden; H. Lundbeck A/S; Lundbeckfonden; National Science Foundation","keywords":"Metagenomics; Computational biology; Benchmark (surveying); Software; Computer science; Interpretation (philosophy); Biology; Genetics; Gene; Programming language; Geography; Cartography","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":[0.001100137,0.0001269273,0.0003216286,0.00005102763,0.0001105852,0.00002103402,0.0004180846,0.0003612247,0.00004600067],"category_scores_gemma":[0.001262109,0.0001135843,0.0001689535,0.00003296173,0.0001865384,0.000006672423,0.0001944518,0.0002850422,4.74237e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001432635,"about_ca_system_score_gemma":0.0001670741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001135519,"about_ca_topic_score_gemma":0.000008127377,"domain_scores_codex":[0.9989093,0.000251589,0.0003110924,0.0002624498,0.00009765258,0.0001679261],"domain_scores_gemma":[0.9985663,0.0001061839,0.0002633323,0.0007399902,0.0002640432,0.00006011649],"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":[0.00003635617,0.00005908704,0.002416963,0.0001318118,0.0001282693,8.462294e-7,0.00004562399,0.000006191614,0.9822875,0.002138156,0.0001795122,0.01256966],"study_design_scores_gemma":[0.0005771549,0.0004355721,0.187742,0.00004962743,0.0002692898,0.00001308617,0.00005933814,0.000163221,0.7800742,0.001612343,0.02870547,0.000298701],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2807111,0.008718172,0.7011687,0.0005846858,0.001458068,0.0003949252,0.0002260638,0.00001254866,0.006725806],"genre_scores_gemma":[0.5254588,0.00007684168,0.4741438,0.000134012,0.00005010066,0.000003252898,0.00003051863,0.000009545645,0.00009305378],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2447477,"threshold_uncertainty_score":0.4631832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01749655809789689,"score_gpt":0.4659042282284851,"score_spread":0.4484076701305882,"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."}}