{"id":"W4415116989","doi":"10.3390/bioengineering12101098","title":"Disease-Specific Prediction of Missense Variant Pathogenicity with DNA Language Models and Graph Neural Networks","year":2025,"lang":"en","type":"article","venue":"Bioengineering","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Canada First Research Excellence Fund","keywords":"ENCODE; Pathogenicity; Missense mutation; Convolutional neural network; Artificial neural network; Human genome; Classifier (UML); Genomics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006564245,0.00009803274,0.00008945121,0.00003811867,0.00002747725,0.00001043258,0.00005363769,0.00005931459,0.000001560776],"category_scores_gemma":[0.000007160136,0.00008523018,0.00003442322,0.0000715818,0.00002121939,0.000003735347,0.0000307494,0.00003425315,4.98989e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000327771,"about_ca_system_score_gemma":0.000008805401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003845704,"about_ca_topic_score_gemma":0.000001070843,"domain_scores_codex":[0.999538,0.00001609202,0.0001015706,0.0001787917,0.00005002071,0.0001154968],"domain_scores_gemma":[0.9997117,0.000006509974,0.00002488636,0.0001851543,0.00001998737,0.00005177766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000135462,0.00001745544,0.0001435765,0.00004853711,0.00004456346,0.00002212711,0.00002547809,0.03778647,0.9583287,0.0005477443,0.00003084244,0.002869015],"study_design_scores_gemma":[0.001096804,0.0003395165,0.006242768,0.0002272345,0.0001210808,0.00007183906,0.0001466398,0.407791,0.582381,0.0002781119,0.0008492675,0.0004546671],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6671101,0.004441531,0.3281697,0.00001973326,0.00006992719,0.0001114816,0.00002422065,0.0000166117,0.00003670119],"genre_scores_gemma":[0.9983571,0.0002605817,0.001223914,0.00001750534,0.00005479496,0.00001325209,0.00002482985,0.00001128021,0.00003675195],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3759477,"threshold_uncertainty_score":0.3475586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008387351122493973,"score_gpt":0.1890641949045245,"score_spread":0.1806768437820306,"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."}}