{"id":"W4412423989","doi":"10.1038/s42003-025-08452-7","title":"Prediction of pathogenic mutations in human transmembrane proteins and their associated diseases via utilizing pre-trained Bio-LLMs","year":2025,"lang":"en","type":"article","venue":"Communications Biology","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Novelis (Canada)","funders":"Priority Academic Program Development of Jiangsu Higher Education Institutions; Government of Jiangsu Province; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Missense mutation; Transmembrane protein; Computational biology; Membrane protein; Mutation; Context (archaeology); Disease; Biology; Transmembrane domain; Pathogenicity; Machine learning; Artificial intelligence; Bioinformatics; Genetics; Computer science; Gene; Medicine; Membrane","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000496987,0.0008160531,0.000418472,0.001381757,0.0002014648,0.0005057366,0.0004566623,0.00076694,0.0006385323],"category_scores_gemma":[0.00128717,0.0002080683,0.0006601486,0.0004228195,0.0002663737,0.0006581079,0.000774534,0.0007141893,0.0003848081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006046152,"about_ca_system_score_gemma":0.0007208652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002247468,"about_ca_topic_score_gemma":0.003256086,"domain_scores_codex":[0.9997485,0.00004582942,0.00002605583,0.00009160847,0.00004798904,0.00003987201],"domain_scores_gemma":[0.9993548,0.0002713058,0.0001313579,0.00004509043,0.0001229142,0.00007447069],"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":[0.001371296,0.0007506856,0.1660722,0.0003915423,0.0003807821,0.003675043,0.0002412991,0.342295,0.1501221,0.003657379,0.006693886,0.3243489],"study_design_scores_gemma":[0.00002101409,0.00007059398,0.005854091,0.000009726386,0.00003178562,0.0002715114,0.00003074875,0.9828178,0.008442128,0.001980466,0.0004588763,0.00001121924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7809361,0.001379515,0.2110906,0.0006352275,0.0000633599,0.00006694929,0.001748787,0.002739784,0.001339593],"genre_scores_gemma":[0.9702351,0.0002567731,0.02660979,0.0001424629,0.00003369275,0.00003568709,0.001980253,0.00003069047,0.0006755633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002247468,"threshold_uncertainty_score":0.004468739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0228022592842042,"score_gpt":0.2804073129601028,"score_spread":0.2576050536758986,"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."}}