{"id":"W2089342580","doi":"10.1186/1745-7580-3-5","title":"Strength in numbers: achieving greater accuracy in MHC-I binding prediction by combining the results from multiple prediction tools","year":2007,"lang":"en","type":"article","venue":"Immunome Research","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Heuristic; Computational biology; Major histocompatibility complex; Linear discriminant analysis; Epitope; MHC class I; Data mining; Machine learning; Proteome; Artificial intelligence; Bioinformatics; Antigen; Biology; Immunology","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":[0.003644163,0.0001618958,0.0001600589,0.0002118961,0.0002242735,0.0001896264,0.0004218585,0.0002086925,0.000009506316],"category_scores_gemma":[0.001222751,0.0001298484,0.00005632214,0.0004415645,0.00007342844,0.00006299974,0.0002949759,0.0006404044,0.00001593864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00012768,"about_ca_system_score_gemma":0.00006432799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001212081,"about_ca_topic_score_gemma":0.0002340047,"domain_scores_codex":[0.99783,0.0001995763,0.0006847502,0.0003411051,0.0003425733,0.0006020081],"domain_scores_gemma":[0.9987642,0.0004542635,0.0001144809,0.0005327135,0.0000849917,0.00004937158],"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":[0.001655485,0.0002356527,0.1862472,0.00003088172,0.00009697877,0.00000615426,0.003486335,0.0002336321,0.7819905,0.00001199241,0.001865925,0.02413918],"study_design_scores_gemma":[0.008386633,0.0007097549,0.8193286,0.0003806004,0.00001217084,0.00001635097,0.01322105,0.007026083,0.1340342,0.00004021024,0.01640438,0.0004399882],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966215,0.0007271484,0.00009184596,0.0001525586,0.0001307768,0.000468897,0.0003453619,0.00001424467,0.001447635],"genre_scores_gemma":[0.9973596,0.000388428,0.0001195229,0.00001554024,0.0001152757,0.00004258922,0.001726951,0.00002338271,0.0002087096],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6479564,"threshold_uncertainty_score":0.5295064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06078619695299838,"score_gpt":0.3230145463935503,"score_spread":0.262228349440552,"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."}}