{"id":"W2150429539","doi":"10.1007/11691730_5","title":"Frequent Subsequence-Based Protein Localization","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Subsequence; Computer science; Support vector machine; Boosting (machine learning); Extracellular; Artificial intelligence; Computational biology; Biochemistry; Biology; Mathematics","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":[0.0003603285,0.0003266261,0.00021319,0.0002203844,0.0001220519,0.0001131172,0.0006791682,0.0003767734,0.00002266738],"category_scores_gemma":[0.00009497926,0.0003031848,0.00007956082,0.0001435527,0.0005076145,0.000007971291,0.0002054709,0.0003577175,0.00001655621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001114919,"about_ca_system_score_gemma":0.0004376318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000292331,"about_ca_topic_score_gemma":0.00008247716,"domain_scores_codex":[0.9982317,0.00002249511,0.0003622628,0.000590546,0.0004575973,0.0003353872],"domain_scores_gemma":[0.9988644,0.0000213226,0.0002362652,0.0006467474,0.0001626433,0.00006866452],"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":[0.00001904354,0.00002965191,0.0005733887,0.0001408006,0.00001005611,0.00001914026,0.00004305025,0.925106,0.01177909,0.00103546,0.0001626264,0.06108171],"study_design_scores_gemma":[0.0006326899,0.0006339639,0.0001612913,0.000624668,0.00001663363,0.00003558549,8.915704e-8,0.8154001,0.1379513,0.01395174,0.0293164,0.001275594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008144914,0.0001884341,0.9931766,0.000156075,0.0002590831,0.0004037581,0.00000878916,0.00003232185,0.004960469],"genre_scores_gemma":[0.7317557,0.00001687818,0.2618778,0.00279895,0.001025069,0.00003016312,0.0005634455,0.00009679623,0.00183521],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7312987,"threshold_uncertainty_score":0.999942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007828164709343928,"score_gpt":0.2287718827541754,"score_spread":0.2209437180448315,"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."}}