{"id":"W4406905918","doi":"10.1128/mbio.02650-24","title":"Machine learning reveals the dynamic importance of accessory sequences for <i>Salmonella</i> outbreak clustering","year":2025,"lang":"en","type":"article","venue":"mBio","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Mitacs; Genome British Columbia; Genome Canada","keywords":"Genome; Computational biology; Bacterial genome size; Cluster analysis; Outbreak; Biology; Genetics; Genotyping; Data mining; Computer science; Artificial intelligence; Gene; Virology; Genotype","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":[0.002415042,0.0004547967,0.0004679657,0.001409095,0.0003960761,0.00111586,0.000542933,0.0006210671,0.0005485595],"category_scores_gemma":[0.005529847,0.0001954496,0.0005649191,0.0007402897,0.0004728682,0.0007389769,0.0006123987,0.0007955442,0.0003107343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005903935,"about_ca_system_score_gemma":0.0004524202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002841865,"about_ca_topic_score_gemma":0.002698254,"domain_scores_codex":[0.9993368,0.0002233507,0.00004153489,0.0002400162,0.000067289,0.00009091516],"domain_scores_gemma":[0.996733,0.001950772,0.0003197649,0.0003580411,0.0004930737,0.0001453837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0009783251,0.0005253404,0.2251014,0.0002659866,0.0003627691,0.0002888894,0.0004900228,0.4683863,0.03952977,0.00307152,0.003242031,0.2577577],"study_design_scores_gemma":[0.000006254621,0.00005975756,0.01693386,0.00001026112,0.00001784357,0.00003166027,0.00004921785,0.9790699,0.002255861,0.001332222,0.0002239859,0.000009120326],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9477234,0.0002939643,0.04989388,0.0002082848,0.0000258068,0.00003242524,0.0002549018,0.0004684946,0.001098938],"genre_scores_gemma":[0.9865762,0.00005029556,0.01256008,0.00003025083,0.00001285574,0.00001066436,0.0004966889,0.00002064535,0.0002424174],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002841865,"threshold_uncertainty_score":0.01277214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02523374509289805,"score_gpt":0.2757108712652237,"score_spread":0.2504771261723256,"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."}}