{"id":"W4399303086","doi":"10.1038/s42003-024-06332-0","title":"SOFB is a comprehensive ensemble deep learning approach for elucidating and characterizing protein-nucleic-acid-binding residues","year":2024,"lang":"en","type":"article","venue":"Communications Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Fundamental Research Funds for the Central Universities; People's Government of Jilin Province; National Natural Science Foundation of China","keywords":"Interpretability; Nucleic acid; Artificial intelligence; Computer science; Deep learning; Machine learning; Sequence (biology); Computational biology; Chemistry; Biology; Biochemistry","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":[0.000304396,0.0001788569,0.0001922662,0.00009816319,0.0004873552,0.0001051614,0.0004579868,0.0002061924,0.000006367377],"category_scores_gemma":[0.0002482712,0.0001743905,0.00007200041,0.000114266,0.0002224589,0.00001300586,0.0006741172,0.0003390594,0.000009490131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001729095,"about_ca_system_score_gemma":0.00003697558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007461573,"about_ca_topic_score_gemma":0.000005243006,"domain_scores_codex":[0.9988856,0.0001840194,0.0003087167,0.0003108028,0.00004213466,0.0002687754],"domain_scores_gemma":[0.9988788,0.0001095401,0.0001307235,0.0007321056,0.00009690745,0.00005188206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002015586,0.00001916042,0.001191305,0.0002122742,0.00009293346,1.665492e-7,0.0008681108,0.00001462995,0.9709016,0.002973149,0.0001289651,0.02357756],"study_design_scores_gemma":[0.0007741566,0.0008333718,0.0007600389,0.0002264855,0.00009518706,0.0001199942,0.002011199,0.2388442,0.1557978,0.0006501971,0.5990036,0.0008837163],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8122747,0.01384118,0.1636277,0.001921445,0.00013115,0.001387313,0.00008492024,0.0002515964,0.006480071],"genre_scores_gemma":[0.8541277,0.0006723524,0.1427513,0.0002551531,0.0000920108,0.0002099987,0.001540492,0.00003716298,0.0003138792],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8151038,"threshold_uncertainty_score":0.7111439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02940020867987616,"score_gpt":0.3119802113803305,"score_spread":0.2825800027004544,"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."}}