{"id":"W4366778979","doi":"10.1016/j.prevetmed.2023.105924","title":"Predictive analysis for pathogenicity classification of H5Nx avian influenza strains using machine learning techniques","year":2023,"lang":"en","type":"article","venue":"Preventive Veterinary Medicine","topic":"Influenza Virus Research Studies","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Pathogenicity; Influenza A virus subtype H5N1; Lasso (programming language); Naive Bayes classifier; Biology; Artificial intelligence; Machine learning; Random forest; Support vector machine; In silico; Virulence; Genetics; Computational biology; Gene; Computer science; Virus; Microbiology","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":[0.001736477,0.0002756867,0.000881926,0.001242681,0.0002275445,0.000006197923,0.0001666845,0.0001260827,0.00008938948],"category_scores_gemma":[0.001836838,0.0002271868,0.000319011,0.002097204,0.0004732865,0.0001418107,0.0001932443,0.000344743,0.000004581899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001948404,"about_ca_system_score_gemma":0.00009899161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001628959,"about_ca_topic_score_gemma":0.00001118765,"domain_scores_codex":[0.99739,0.0003320711,0.0007169921,0.0004929003,0.0006119377,0.0004561329],"domain_scores_gemma":[0.9980633,0.0003800409,0.0003779355,0.0003752997,0.0006482211,0.0001552173],"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":[0.001920532,0.0002092274,0.1668061,0.0008707864,0.003159321,0.00007154542,0.002761781,0.0001431837,0.8178769,0.00009318907,0.00006060226,0.006026841],"study_design_scores_gemma":[0.003629972,0.01033208,0.8916105,0.001047648,0.003626977,0.00004500805,0.002573092,0.0625744,0.01906126,0.0003529188,0.004763988,0.0003821335],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9781275,0.0007607067,0.01795938,0.0002856396,0.00006560317,0.001813293,0.0002605952,0.0002893228,0.000437939],"genre_scores_gemma":[0.9946855,0.0003525087,0.003738455,0.00008857079,0.0001977252,0.0002578784,0.0003087693,0.00004381142,0.0003267846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7988157,"threshold_uncertainty_score":0.926441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2743898765360103,"score_gpt":0.4658937878507989,"score_spread":0.1915039113147886,"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."}}