{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004051713,0.0003818395,0.000264615,0.0005519426,0.0001500449,0.0004943527,0.0002998292,0.0003058772,0.002030543],"category_scores_gemma":[0.0005737648,0.0001153184,0.0005497377,0.0005026698,0.0001107887,0.0006752242,0.0002967723,0.0003367691,0.001507167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001897742,"about_ca_system_score_gemma":0.0003203801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001679632,"about_ca_topic_score_gemma":0.004675208,"domain_scores_codex":[0.9998918,0.00001956549,0.000009617334,0.00003312357,0.00003121769,0.0000146484],"domain_scores_gemma":[0.9997162,0.0001678777,0.00002161497,0.00001457649,0.0000642481,0.00001552161],"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":[0.0007589298,0.0004513043,0.01560473,0.0003136639,0.0001679921,0.0004341526,0.00008218409,0.03023395,0.1319518,0.002444638,0.009858612,0.807698],"study_design_scores_gemma":[0.00008642298,0.0006318949,0.01769528,0.00007047533,0.0002615668,0.0005170766,0.0001574752,0.8621423,0.08841886,0.01124399,0.01870005,0.0000745658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5358577,0.00324883,0.4268499,0.0005854266,0.0003505004,0.0001641409,0.007143862,0.0073147,0.01848498],"genre_scores_gemma":[0.6964495,0.001125251,0.2756677,0.0002738828,0.0001552929,0.000120135,0.0132568,0.0002502571,0.01270115],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002030543,"threshold_uncertainty_score":0.006792843,"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."}}