{"id":"W4412686559","doi":"10.1016/j.neunet.2025.107923","title":"Nucleotide-level circRNA-RBP binding sites prediction based on hybrid encoding scheme and enhanced feature extraction","year":2025,"lang":"en","type":"article","venue":"Neural Networks","topic":"Circular RNAs in diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Fundamental Research Funds for the Central Universities; Shaanxi Normal University; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Robustness (evolution); Pattern recognition (psychology); Feature extraction; Computational biology; Benchmark (surveying); Encoding (memory); Deep learning; Feature (linguistics); Gene; Biology; Genetics","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":[0.0000963916,0.0001855089,0.0001278205,0.00007968813,0.0001901692,0.00006987852,0.0001116141,0.000156924,0.00001365978],"category_scores_gemma":[0.0001400539,0.0001939934,0.00008957469,0.0001381578,0.00005278441,0.00001187036,0.0000624686,0.0002356227,0.000001543828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003240908,"about_ca_system_score_gemma":0.00002483084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002410307,"about_ca_topic_score_gemma":0.000005463985,"domain_scores_codex":[0.9989722,0.00005829145,0.000149457,0.0004517586,0.0001220802,0.0002461564],"domain_scores_gemma":[0.9994759,0.00004462951,0.00007446738,0.0002805816,0.00004925222,0.00007520145],"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":[0.0001950175,0.00006096931,0.01363489,0.00003644685,0.00004443589,0.000009884653,0.000004119269,0.01192848,0.9527014,0.00001915309,0.005648836,0.01571629],"study_design_scores_gemma":[0.001750646,0.0003311038,0.06161551,0.0002861859,0.0001201343,0.00002685305,0.00004771632,0.3307462,0.6009377,0.00005801077,0.003518625,0.0005612771],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9776296,0.0007669645,0.0195727,0.0002228438,0.0006119371,0.0002270397,0.00003271502,0.00005666412,0.0008795133],"genre_scores_gemma":[0.9979047,0.0001259293,0.0003080118,0.0006129646,0.0004203056,0.00002266,0.0003041354,0.00002230876,0.0002789965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3517638,"threshold_uncertainty_score":0.7910823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01242074712081579,"score_gpt":0.259358016312815,"score_spread":0.2469372691919992,"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."}}