{"id":"W2578210650","doi":"10.1101/099127","title":"Critical Assessment of Metagenome Interpretation – a benchmark of computational metagenomics software","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Office of Science; Joint Genome Institute; Engineering and Physical Sciences Research Council; Isaac Newton Institute for Mathematical Sciences; Deutsche Forschungsgemeinschaft; U.S. Department of Energy; Division of Mathematical Sciences; National Science Foundation","keywords":"Metagenomics; Benchmarking; Profiling (computer programming); Benchmark (surveying); Computer science; Software; Genome; Data science; Computational biology; Data mining; Biology; Geography; Genetics; Gene; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004864181,0.0003572015,0.0006279735,0.000119385,0.0001128497,0.00005753969,0.0005685726,0.0003298065,0.00001081248],"category_scores_gemma":[0.0003741164,0.000393311,0.0002755735,0.00005685556,0.0003123377,0.000003146575,0.0007975687,0.0002194606,0.000001215087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000472115,"about_ca_system_score_gemma":0.0006538039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002003026,"about_ca_topic_score_gemma":0.000001931161,"domain_scores_codex":[0.9981163,0.0001086559,0.0006236109,0.0006392511,0.0002565897,0.0002556502],"domain_scores_gemma":[0.9972226,0.00007019305,0.0006844476,0.0009944194,0.0009311744,0.00009715743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00004089535,0.0001505856,0.009567085,0.0004697028,0.0009115404,0.000003501885,0.00001286731,0.00285886,0.9850418,0.0008882086,0.00004449623,0.00001046478],"study_design_scores_gemma":[0.0007795464,0.0004110809,0.563817,0.000281539,0.0008678624,5.054088e-8,0.00000853808,0.00271204,0.4278609,0.0001423532,0.002088159,0.001030948],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9626172,0.003344951,0.03199312,0.0000489656,0.0006269696,0.0003735237,0.0009624742,0.000008648773,0.00002416139],"genre_scores_gemma":[0.9258763,0.0003469792,0.07347502,0.00004342989,0.0001469991,0.00005987344,0.000004182398,0.00004536564,0.000001906347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5571809,"threshold_uncertainty_score":0.9998519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01429977339638401,"score_gpt":0.270568447096628,"score_spread":0.256268673700244,"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."}}