{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007914157,0.001750709,0.001596429,0.001759919,0.0004838002,0.0005751794,0.002084067,0.001343382,0.001347147],"category_scores_gemma":[0.0009984463,0.0005934663,0.001407854,0.001262963,0.0004455971,0.001544472,0.001124298,0.001958718,0.0007090633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001017381,"about_ca_system_score_gemma":0.001374371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0110409,"about_ca_topic_score_gemma":0.01563171,"domain_scores_codex":[0.9996642,0.00005678433,0.00001921617,0.0000863067,0.0001126337,0.00006097457],"domain_scores_gemma":[0.9996961,0.00008372934,0.00004452595,0.00003901087,0.0000988363,0.00003779809],"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":[0.0002281635,0.0003110735,0.005779038,0.0001990626,0.0004774097,0.0001895849,0.0001018371,0.5775758,0.02163411,0.007467033,0.008713323,0.3773235],"study_design_scores_gemma":[0.000003661226,0.00002036531,0.0001927352,0.000006126063,0.00001722165,0.00001814688,0.000005015746,0.9950258,0.001387744,0.002617493,0.000699422,0.00000623759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05013496,0.002189963,0.9418345,0.0003541711,0.0001074719,0.00004873002,0.0007587779,0.00287642,0.001695002],"genre_scores_gemma":[0.6422432,0.002946771,0.3378681,0.0008494588,0.0001586677,0.0002681173,0.007115491,0.0004315751,0.008118663],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0110409,"threshold_uncertainty_score":0.02195328,"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."}}