{"id":"W4415046037","doi":"10.1093/bib/bbaf536","title":"Data-efficient protein mutational effect prediction with weak supervision by molecular simulation and protein language models","year":2025,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; Japan Society for the Promotion of Science; Cybermedia Center, Osaka University; Japan Association for Chemical Innovation; New Energy and Industrial Technology Development Organization; Japan Agency for Medical Research and Development; Japan Society for the Promotion of Science London; National Institute of Advanced Industrial Science and Technology","keywords":"Benchmark (surveying); Training set; Experimental data; Training (meteorology); Protein engineering; Pathogenicity; Computational model; Mutation","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001625937,0.0009678141,0.001277621,0.0005824557,0.0004347828,0.0009460007,0.001896451,0.001024795,0.00128534],"category_scores_gemma":[0.005503106,0.0007032151,0.001067451,0.000454604,0.0007192135,0.001500236,0.001542717,0.002159517,0.0007485645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005539818,"about_ca_system_score_gemma":0.001365931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004173618,"about_ca_topic_score_gemma":0.005064994,"domain_scores_codex":[0.9993136,0.0002861829,0.00004388502,0.0001523974,0.0001592843,0.00004470451],"domain_scores_gemma":[0.996986,0.001861617,0.000195548,0.0004396877,0.0003615414,0.0001557012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003086968,0.0002079227,0.002774428,0.000181248,0.0001019743,0.0001617134,0.00008145502,0.8940209,0.01250276,0.003585684,0.002413014,0.08366015],"study_design_scores_gemma":[0.000003914754,0.000006984882,0.00004211748,0.000001472355,0.000002087556,0.000003184439,0.00000138788,0.9983562,0.0007189459,0.0007561089,0.0001052474,0.000002385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09830332,0.0005853666,0.8938405,0.0007388262,0.0001239254,0.00008291859,0.0003585056,0.004717895,0.001248647],"genre_scores_gemma":[0.646386,0.0004237451,0.348611,0.0003701356,0.0001507132,0.0003165835,0.001733986,0.0004459856,0.001561717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004173618,"threshold_uncertainty_score":0.008598924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004676397131470881,"score_gpt":0.2416921666111629,"score_spread":0.2370157694796921,"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."}}