{"id":"W4413140665","doi":"10.1021/acs.jcim.5c00605","title":"GATRsite: RNA–Ligand Binding Site Prediction Using Graph Attention Networks and Pretrained RNA Language Models","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; Kelowna General Hospital; University of Ottawa","funders":"Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"RNA; Computer science; Graph; Computational biology; RNA-binding protein; Language model; Artificial intelligence; Chemistry; Theoretical computer science; Biology; Biochemistry; Gene","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003080881,0.00008826042,0.0001206046,0.0001124328,0.00006664518,0.00006699164,0.00004623232,0.0001462432,0.000001039784],"category_scores_gemma":[0.0000360717,0.00007897512,0.00005836829,0.00006698599,0.00001800835,0.00009435923,0.00003907543,0.0001053653,1.159883e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001252178,"about_ca_system_score_gemma":0.0000238435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000335917,"about_ca_topic_score_gemma":1.995346e-7,"domain_scores_codex":[0.9993315,0.00001709536,0.0003755673,0.00007030574,0.0001008603,0.0001046414],"domain_scores_gemma":[0.9995833,0.000007262436,0.0001799758,0.00006035397,0.0001089974,0.00006007762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009459754,0.000005854653,0.00002761715,0.00003524578,0.00003394036,3.013669e-7,0.0001213592,0.03321746,0.9608459,0.00004939879,0.00003956997,0.005528709],"study_design_scores_gemma":[0.0005432822,0.00003732693,0.000003972218,0.0001497791,0.0000484284,0.00003162488,0.000189804,0.7654532,0.2331047,0.0003067987,0.00005285291,0.00007827324],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5930195,0.0005533089,0.4061854,0.00003366775,0.00005605634,0.00004866348,0.000003616254,0.000003307961,0.00009639819],"genre_scores_gemma":[0.9964665,0.000574437,0.002695052,0.0001232674,0.00009021066,0.000001223721,0.00003192757,0.000004334588,0.00001306822],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7322357,"threshold_uncertainty_score":0.3220512,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01254123232431525,"score_gpt":0.2447265467905938,"score_spread":0.2321853144662786,"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."}}