{"id":"W2810921553","doi":"10.4236/jbise.2018.116013","title":"Improved Protein Phosphorylation Site Prediction by a New Combination of Feature Set and Feature Selection","year":2018,"lang":"en","type":"article","venue":"Journal of Biomedical Science and Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Institute of Genetics; University of Tokyo; Institute of Medical Science, University of Tokyo; Research Organization of Information and Systems","keywords":"Phosphorylation; Feature selection; Computer science; Random forest; Feature (linguistics); Set (abstract data type); Support vector machine; Artificial intelligence; Selection (genetic algorithm); Posttranslational modification; Data mining; Pattern recognition (psychology); Chemistry; Enzyme; Biochemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004513346,0.00005476367,0.00006904698,0.00007983847,0.00005194456,0.00002429873,0.00005649421,0.0000929175,0.000001630612],"category_scores_gemma":[0.0002769937,0.00004310692,0.00001285753,0.0002275886,0.000123159,0.00002789718,0.00002743739,0.0001192394,8.086513e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001674353,"about_ca_system_score_gemma":0.00006897805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000537714,"about_ca_topic_score_gemma":7.876701e-7,"domain_scores_codex":[0.9994806,0.000005696008,0.0001302223,0.00007138366,0.0002214372,0.00009064401],"domain_scores_gemma":[0.9995754,0.0000040149,0.0001247452,0.00003637169,0.0001558678,0.0001035808],"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":[0.0000211682,0.000007582912,0.0004774873,0.00002321332,0.000006149186,7.510702e-8,0.0001161954,0.00001158394,0.9910324,0.000006148874,0.00216531,0.006132698],"study_design_scores_gemma":[0.001479688,0.003802149,0.02592955,0.000189405,0.00003198646,0.000210211,0.00008126141,0.2803687,0.6454639,0.00002829912,0.04221898,0.0001957567],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9720947,0.0001863594,0.02706286,0.0004614597,0.0001068619,0.0000648287,0.000003538798,0.000004211632,0.00001520099],"genre_scores_gemma":[0.9933404,0.00003993509,0.006344934,0.00002374152,0.0001699649,4.557577e-7,0.000008601148,0.000003274753,0.00006871406],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3455684,"threshold_uncertainty_score":0.1757849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.002311722839920661,"score_gpt":0.211172616447291,"score_spread":0.2088608936073704,"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."}}