{"id":"W3120180752","doi":"10.1016/j.jmb.2021.166810","title":"ELASPIC2 (EL2): Combining Contextualized Language Models and Graph Neural Networks to Predict Effects of Mutations","year":2021,"lang":"en","type":"article","venue":"Journal of Molecular Biology","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Machine learning; Artificial intelligence; Leverage (statistics); Artificial neural network; Language model; Web server; The Internet","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":[0.0001297705,0.0001210982,0.0002830942,0.00007086303,0.00003017008,0.0000098562,0.0001239134,0.0001704654,0.000001849314],"category_scores_gemma":[0.0002198021,0.0001062805,0.0001293673,0.0001053819,0.00008365901,0.000004511543,0.0001042813,0.0001393839,8.04913e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004848303,"about_ca_system_score_gemma":0.00005207611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005760293,"about_ca_topic_score_gemma":0.000006631266,"domain_scores_codex":[0.9991068,0.0001739706,0.0003188729,0.0001636456,0.00007132808,0.0001654439],"domain_scores_gemma":[0.9992806,0.00004119826,0.0002066879,0.0001698443,0.0001974252,0.0001042271],"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":[0.0001219488,0.00002993917,0.0004779676,0.00002495284,0.0001833666,0.0001216509,0.0001145825,0.007897542,0.9866084,0.00113265,0.00003699885,0.003250012],"study_design_scores_gemma":[0.005309714,0.003679722,0.001502484,0.0001399806,0.0002969603,0.001398157,0.0003593298,0.01332575,0.9647877,0.008389936,0.0003462903,0.0004639357],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7373878,0.006191659,0.2560187,0.0000844481,0.0001596915,0.00009331464,0.000006948215,0.000002442667,0.00005494802],"genre_scores_gemma":[0.9934596,0.0001506111,0.005711583,0.0005413432,0.00006126201,0.000004066988,0.00004381223,0.00001352021,0.00001412958],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2560718,"threshold_uncertainty_score":0.4333991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004099539784084971,"score_gpt":0.2559829125733331,"score_spread":0.2518833727892482,"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."}}