{"id":"W2782879881","doi":"10.1099/mgen.0.000151","title":"Comprehensive assessment of the quality of Salmonella whole genome sequence data available in public sequence databases using the Salmonella in silico Typing Resource (SISTR)","year":2018,"lang":"en","type":"article","venue":"Microbial Genomics","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological Sciences","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Agency of Canada","funders":"Public Health Agency; Public Health Agency of Canada","keywords":"In silico; Multilocus sequence typing; Salmonella; Genome; Whole genome sequencing; Biology; Typing; Serotype; Computational biology; Concordance; Genetics; Database; 1000 Genomes Project; Data quality; Data mining; Computer science; Gene; Microbiology; Genotype; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001782718,0.0002164089,0.0005014983,0.00003033079,0.0001919654,0.0000376334,0.001744956,0.0001187554,0.00009824191],"category_scores_gemma":[0.0001940852,0.00009283661,0.00008701842,0.0006934434,0.0008107985,0.0001461912,0.001279193,0.0002872355,0.000008976029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001771188,"about_ca_system_score_gemma":0.0001424532,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006745689,"about_ca_topic_score_gemma":0.004749777,"domain_scores_codex":[0.9968728,0.0009692839,0.0009178598,0.0006118015,0.0001508224,0.0004773977],"domain_scores_gemma":[0.9978995,0.0006527925,0.0005710084,0.0006867094,0.0001352227,0.00005472036],"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":[0.00003228393,0.00006988617,0.08102642,0.00002123487,0.0000130999,0.000001185482,0.0001136955,0.0001905599,0.9178249,0.00006519665,0.0001798947,0.0004616951],"study_design_scores_gemma":[0.0006517359,0.0001735524,0.7793503,0.0001911966,0.00004223435,0.00005831038,0.002277781,0.005860907,0.02388649,0.000180074,0.1866157,0.0007117538],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969966,0.0003794305,0.00002067905,0.0005403169,0.0001502228,0.0003763742,0.001291235,0.00001050157,0.000234598],"genre_scores_gemma":[0.9980629,0.000118986,0.0007584303,0.0004678312,0.0001542071,0.000003181595,0.000373517,0.000003552362,0.0000573691],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8939384,"threshold_uncertainty_score":0.9998685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2991486640787514,"score_gpt":0.3640092327917008,"score_spread":0.06486056871294937,"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."}}