{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001198261,0.0008482186,0.001854145,0.001877062,0.0003363023,0.0005026557,0.0009176899,0.0005752603,0.0007744568],"category_scores_gemma":[0.001837849,0.0002785895,0.001058654,0.001881665,0.0001994539,0.0008772752,0.0005198449,0.0005912196,0.000318942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000251233,"about_ca_system_score_gemma":0.0006774315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003052903,"about_ca_topic_score_gemma":0.002696664,"domain_scores_codex":[0.9991233,0.0001651749,0.00008709638,0.000206837,0.000316012,0.0001016388],"domain_scores_gemma":[0.9990116,0.0003925806,0.00006297839,0.00008807539,0.0004056269,0.00003904879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006005169,0.0007665416,0.01196947,0.0001705409,0.0003678947,0.0003592155,0.00005315252,0.1028851,0.04259787,0.0006422233,0.006994347,0.8325931],"study_design_scores_gemma":[0.00006724439,0.0001615927,0.005331398,0.000007908195,0.00009278054,0.0001995468,0.00001076648,0.9860666,0.006487509,0.0006031271,0.0009399596,0.00003162204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1707927,0.001032598,0.8225753,0.0002256281,0.0001603116,0.0001748169,0.0008490098,0.003308303,0.0008814399],"genre_scores_gemma":[0.7440061,0.0002591824,0.2515526,0.0001685707,0.0001322472,0.0002921119,0.002501933,0.0001027121,0.0009844673],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003052903,"threshold_uncertainty_score":0.006337106,"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."}}