{"id":"W2797648554","doi":"10.1101/299347","title":"Rapid Identification of Stable Clusters in Bacterial Populations Using the Adjusted Wallace Coefficient","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Agency of Canada; University of Lethbridge","funders":"Fundação para a Ciência e a Tecnologia; China Scholarship Council; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; Government of Canada; Università di Bologna; European Food Safety Authority","keywords":"Subtyping; Computational biology; Biology; Whole genome sequencing; Similarity (geometry); Cluster (spacecraft); Phylogenetic tree; Campylobacter jejuni; Identification (biology); Stability (learning theory); Concordance; Data mining; Genome; Evolutionary biology; Computer science; Genetics; Artificial intelligence; Machine learning; Gene; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003680564,0.0006007113,0.0006877463,0.004392999,0.0007533327,0.001490927,0.0008634935,0.0005223271,0.00106481],"category_scores_gemma":[0.01683266,0.0003434914,0.0008467416,0.00284004,0.0007536124,0.001090543,0.00160433,0.0008818254,0.0004099915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006092998,"about_ca_system_score_gemma":0.000659377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001786389,"about_ca_topic_score_gemma":0.002076006,"domain_scores_codex":[0.997645,0.0008545389,0.0002540791,0.0005610781,0.0005516634,0.0001337091],"domain_scores_gemma":[0.9927408,0.002931165,0.001950934,0.000747947,0.001323817,0.0003053715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001715349,0.0002248504,0.3246056,0.001311858,0.001928352,0.0009215011,0.00199195,0.119516,0.2228083,0.02298986,0.00770044,0.2942859],"study_design_scores_gemma":[0.00007177205,0.0004090775,0.09747742,0.0001495342,0.0002162722,0.0007533219,0.0006183643,0.8137644,0.06240799,0.01601114,0.007875196,0.0002454905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5084658,0.0009243346,0.4852974,0.0001574268,0.0001126729,0.0001893279,0.001082349,0.001316767,0.002453905],"genre_scores_gemma":[0.7474862,0.0001848517,0.2501573,0.00003294271,0.00002765873,0.0001818125,0.001057407,0.0002520128,0.0006198384],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004392999,"threshold_uncertainty_score":0.01946497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05516287561621689,"score_gpt":0.2522085924657013,"score_spread":0.1970457168494844,"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."}}