{"id":"W7114907792","doi":"10.1093/bib/bbaf631.068","title":"Prediction of protein binding residues for metal ions, nucleic acids, and small molecules","year":2025,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Small molecule; Nucleic acid; Binding site; Cysteine; Ligand (biochemistry); Protein–protein interaction; Python (programming language); Peptide; Plasma protein binding","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":[0.0004298535,0.0001676901,0.000216891,0.0002083846,0.00009699522,0.00003967956,0.0001767949,0.0001908726,0.000001799018],"category_scores_gemma":[0.0005433118,0.000165547,0.00006655177,0.0001789984,0.0001159181,0.00001765356,0.0001708071,0.0001234372,0.000001010806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001775629,"about_ca_system_score_gemma":0.00007833016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002792201,"about_ca_topic_score_gemma":0.00002746881,"domain_scores_codex":[0.9988783,0.00002091126,0.0006306845,0.000139331,0.0001047134,0.0002260528],"domain_scores_gemma":[0.9993479,0.00003153543,0.0002502583,0.0002485441,0.00008521631,0.00003650944],"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":[0.001680645,0.0007472842,0.1221297,0.01980453,0.001231372,0.000004320472,0.008115143,0.003052707,0.6155016,0.07398257,0.01813929,0.1356108],"study_design_scores_gemma":[0.00861195,0.002079014,0.0350747,0.002407876,0.0002885259,0.0000677624,0.003096349,0.2599567,0.5287742,0.003503054,0.1546898,0.001450091],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9387528,0.0005804328,0.05548178,0.000492679,0.0001011146,0.00109264,0.0001390158,0.00004160494,0.00331796],"genre_scores_gemma":[0.5223709,0.0003668556,0.4744503,0.0008692385,0.00006672625,0.0001676164,0.0005974029,0.00004495001,0.001066047],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4189685,"threshold_uncertainty_score":0.675081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01137480711774124,"score_gpt":0.2391244631498523,"score_spread":0.2277496560321111,"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."}}