{"id":"W4385255511","doi":"10.1007/978-3-031-36886-8_7","title":"Incorporating Natural Language-Based and Sequence-Based Features to Predict Protein Sumoylation Sites","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"SUMO protein; Computational biology; Biology; Phosphorylation; Proteomics; Cell biology; Bioinformatics; Genetics; Gene; Ubiquitin","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003614777,0.0003636992,0.0003489804,0.0001426435,0.00009503011,0.0001363523,0.0001257709,0.0006533533,0.000002068256],"category_scores_gemma":[0.0002503512,0.0003092847,0.00005539346,0.00007273461,0.00007309762,0.0000043134,0.00008574281,0.000568377,0.000001434407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002892047,"about_ca_system_score_gemma":0.00006218883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008142334,"about_ca_topic_score_gemma":0.000634115,"domain_scores_codex":[0.998715,0.00006794772,0.000372583,0.0004021036,0.0001982345,0.0002440603],"domain_scores_gemma":[0.9991782,0.0001188872,0.000266469,0.0002872161,0.00006605068,0.00008314818],"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":[0.0002487664,0.00001255588,0.007813052,0.001504481,0.0001144223,0.00005439117,0.0002761802,0.9565449,0.01318873,0.0007920856,0.0005268353,0.01892363],"study_design_scores_gemma":[0.0009165225,0.0006070649,0.0008662344,0.00258982,0.00005302199,0.00003537169,0.00002064801,0.9892386,0.0009152923,0.0002660667,0.003433621,0.001057775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3897065,0.1086724,0.4465317,0.003263334,0.005488452,0.02022056,0.0009119453,0.001209939,0.02399514],"genre_scores_gemma":[0.9929988,0.0000235943,0.001412089,0.0003005984,0.0007136701,0.00005050526,0.001317949,0.00007243473,0.003110294],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6032923,"threshold_uncertainty_score":0.9999359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01110490623859676,"score_gpt":0.2443790469431087,"score_spread":0.2332741407045119,"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."}}