{"id":"W2152856869","doi":"10.1186/1477-5956-9-s1-s4","title":"ATPsite: sequence-based prediction of ATP-binding residues","year":2011,"lang":"en","type":"article","venue":"Proteome Science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":81,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Support vector machine; Dihedral angle; Classifier (UML); Annotation; Computer science; Machine learning; Artificial intelligence; Matthews correlation coefficient; Sequence (biology); Sequence alignment; Computational biology; Data mining; Bioinformatics; Peptide sequence; Biology; Chemistry; Biochemistry; Gene","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006435507,0.00008264177,0.00007377737,0.0000982745,0.000126105,0.00001656167,0.0003816201,0.00005809019,0.00003177553],"category_scores_gemma":[0.000324552,0.0000728015,0.00003107904,0.0003050159,0.0004883211,0.00001585938,0.0001066258,0.00007682901,0.00001285411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001760811,"about_ca_system_score_gemma":0.0001875859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002520271,"about_ca_topic_score_gemma":0.000002087836,"domain_scores_codex":[0.9991034,0.00002113895,0.0001960461,0.0002067704,0.000265621,0.0002070563],"domain_scores_gemma":[0.9993392,0.000004355601,0.0001465449,0.0003183339,0.0001301408,0.00006137739],"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":[0.0000224483,0.00001695126,0.02517197,0.00003022865,0.000002810596,3.853473e-7,0.0003015946,0.00006214066,0.9735093,0.0001116478,0.00003130257,0.0007392925],"study_design_scores_gemma":[0.0001457206,0.0003139935,0.01793923,0.00002906367,0.000003886024,0.000005043104,0.00003511729,0.002516109,0.9780971,0.00004651946,0.0007844148,0.00008378549],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9871611,0.00001966778,0.005588845,0.00003295453,0.00009477264,0.0002383652,0.00001652244,0.00002485861,0.006822933],"genre_scores_gemma":[0.9625444,0.000004776683,0.03713305,0.00004572608,0.00003162445,0.00001695943,0.00001290445,0.000006451422,0.0002040633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0315442,"threshold_uncertainty_score":0.2968759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03824075508694257,"score_gpt":0.2718583389464778,"score_spread":0.2336175838595352,"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."}}