{"id":"W4409492537","doi":"10.1101/2025.04.08.647800","title":"Data-efficient protein mutational effect prediction with weak supervision by molecular simulation and protein language models","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; Japan Association for Chemical Innovation; Cybermedia Center, Osaka University; Japan Society for the Promotion of Science; National Institute of Advanced Industrial Science and Technology; Japan Agency for Medical Research and Development","keywords":"Computer science; Computational biology; Biology","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":[0.001941823,0.001010794,0.001241573,0.0006875402,0.0003918139,0.0007875084,0.001673924,0.001112527,0.001027528],"category_scores_gemma":[0.00580232,0.0006108662,0.0008448601,0.0004535844,0.0008069574,0.001320414,0.001364785,0.001889898,0.0005293836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006293158,"about_ca_system_score_gemma":0.00137984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004633229,"about_ca_topic_score_gemma":0.004749589,"domain_scores_codex":[0.9993906,0.0002927154,0.000029138,0.0001270834,0.0001181707,0.00004224899],"domain_scores_gemma":[0.9958584,0.002698852,0.0002721415,0.0005120695,0.0004504841,0.000208118],"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":[0.0003259813,0.0002058722,0.002094013,0.00009789535,0.00006886038,0.0000819343,0.00004108764,0.955681,0.006952004,0.001750433,0.001076204,0.03162481],"study_design_scores_gemma":[0.000003187588,0.000004318296,0.00002266208,7.7479e-7,0.000001055655,0.000001154964,8.250271e-7,0.9991909,0.0004064153,0.0003399681,0.00002762997,0.000001138591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2515298,0.0003959379,0.7388178,0.0008450877,0.00009996859,0.0001095897,0.0003717544,0.006291999,0.001538016],"genre_scores_gemma":[0.8118306,0.0001083967,0.1856109,0.0002303787,0.00006983621,0.0002017635,0.0008379787,0.000298494,0.000811662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004633229,"threshold_uncertainty_score":0.01026952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006293089495488207,"score_gpt":0.2276374524504348,"score_spread":0.2213443629549466,"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."}}