{"id":"W4308678857","doi":"10.1093/bib/bbac443","title":"High-resolution shotgun metagenomics: the more data, the better?","year":2022,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Metagenomics; Shotgun sequencing; Deep sequencing; Workflow; DNA sequencing; Computer science; Sample (material); Shotgun; Data mining; Computational biology; Biology; Genome; Database; Genetics; Gene","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":[0.0006689526,0.0001405156,0.0001256763,0.00002924928,0.0005205278,0.00004937192,0.001029416,0.00004128375,0.00001484471],"category_scores_gemma":[0.00005635992,0.00009322917,0.00005243469,0.0001265412,0.0001468515,0.000002710494,0.001723532,0.0001836458,0.000005349897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002593127,"about_ca_system_score_gemma":0.00005755136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00024996,"about_ca_topic_score_gemma":0.00007678116,"domain_scores_codex":[0.998984,0.00005575554,0.0003404165,0.0001830133,0.0001815134,0.0002552475],"domain_scores_gemma":[0.9988477,0.0000371459,0.0001505478,0.0009172677,0.00002477019,0.00002254395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005607908,0.000562058,0.01223169,0.0002606811,0.001848342,0.00002235788,0.02608397,0.1101579,0.09529012,0.01250882,0.5872202,0.153253],"study_design_scores_gemma":[0.0006883358,0.0001456905,0.01098313,0.00000476254,0.00006605505,0.0000593967,0.003203543,0.02014704,0.001866789,0.0006540031,0.9618245,0.0003567782],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9832423,0.002545199,0.001232267,0.01087347,0.0004350751,0.0005192207,0.0004354572,0.000007551437,0.0007094973],"genre_scores_gemma":[0.9790492,0.0005110955,0.00624981,0.01323452,0.0002142928,0.00009367726,0.0004459991,0.00002454776,0.0001768608],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3746043,"threshold_uncertainty_score":0.4003531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01890786310678922,"score_gpt":0.2353498665392683,"score_spread":0.2164420034324791,"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."}}