{"id":"W4401398698","doi":"10.1007/s00439-024-02680-3","title":"Assessing predictions on fitness effects of missense variants in HMBS in CAGI6","year":2024,"lang":"en","type":"article","venue":"Human Genetics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"Ministero dell'Istruzione e del Merito; National Institute of General Medical Sciences; National Human Genome Research Institute; Southwestern Medical Foundation; Ministero dell’Istruzione, dell’Università e della Ricerca; Welch Foundation; Cancer Prevention and Research Institute of Texas; National Institutes of Health; National Science Foundation","keywords":"Missense mutation; Biology; Correlation; Genetics; Receiver operating characteristic; Genome; Gene; Computational biology; Mutation; Machine learning; Computer science; Mathematics","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":[0.000118379,0.0001336416,0.0001515447,0.0001203006,0.00003947853,0.000031403,0.000104258,0.0001114592,0.000004401186],"category_scores_gemma":[0.00003181017,0.0001365302,0.00004954598,0.0001322374,0.00005871307,8.180368e-7,0.00007355282,0.00009882689,0.000002445495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001878083,"about_ca_system_score_gemma":0.00005573163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002845642,"about_ca_topic_score_gemma":0.0001887135,"domain_scores_codex":[0.9991345,0.0000545423,0.0002354357,0.0002967321,0.00008712497,0.0001916581],"domain_scores_gemma":[0.9996289,0.00003754215,0.00003299201,0.00023953,0.00002698607,0.00003402026],"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":[0.00001196598,0.0001362955,0.01252776,0.0002062436,0.00004981089,0.00005676498,0.0003907184,0.002397385,0.9817275,0.0002808647,0.0002493679,0.001965251],"study_design_scores_gemma":[0.000993831,0.0006745779,0.7210702,0.0004382606,0.00004800728,0.00001772803,0.0001876612,0.001300858,0.2708523,0.0009735476,0.003065757,0.0003772939],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9932609,0.004979048,0.0001254442,0.00002931913,0.0003192774,0.0001758228,0.00001086396,0.000003950379,0.001095338],"genre_scores_gemma":[0.9990194,0.0003791154,0.0002402236,0.00003164917,0.0001260563,0.00001965119,0.00001565978,0.00002335367,0.000144903],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7108753,"threshold_uncertainty_score":0.5567542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01880695160368386,"score_gpt":0.2943341277357667,"score_spread":0.2755271761320828,"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."}}