{"id":"W2047429137","doi":"10.1089/cmb.2008.0031","title":"Learned Random-Walk Kernels and Empirical-Map Kernels for Protein Sequence Classification","year":2009,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"String kernel; Kernel (algebra); Support vector machine; Random walk; Computer science; Kernel method; Pairwise comparison; Sequence (biology); Artificial intelligence; Pattern recognition (psychology); Random forest; Similarity (geometry); Protein sequencing; Mathematics; Machine learning; Radial basis function kernel; Biology; Peptide sequence; Combinatorics; Statistics; Genetics","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":[],"consensus_categories":[],"category_scores_codex":[0.0005761259,0.000115745,0.0002071032,0.00007747008,0.00007080541,0.00002497104,0.0001480649,0.000147795,0.000009772348],"category_scores_gemma":[0.0006472078,0.00009434915,0.00009141605,0.00005196728,0.00009687227,0.00001047655,0.00002291765,0.0001441086,0.000002496005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001616024,"about_ca_system_score_gemma":0.0001510891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.73835e-7,"about_ca_topic_score_gemma":3.342922e-7,"domain_scores_codex":[0.9990201,0.0001151414,0.0004745881,0.000138602,0.0001055974,0.0001459732],"domain_scores_gemma":[0.9988899,0.00009855233,0.0004867671,0.00008731324,0.0003496679,0.00008776347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002561231,0.000251271,0.007498794,0.0001168335,0.0002743744,0.000005091006,0.0003421976,0.02259085,0.8481206,0.01054617,0.005976746,0.1017158],"study_design_scores_gemma":[0.02367779,0.01671383,0.07243971,0.000242157,0.0001966698,0.001355905,0.000262882,0.1844511,0.03481072,0.2841774,0.3801603,0.001511489],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6826909,0.0004243748,0.3080783,0.007978795,0.0001460044,0.0003849687,0.00002222884,0.00001002356,0.0002644247],"genre_scores_gemma":[0.9530387,0.00003025014,0.04544652,0.0009504565,0.0002737933,0.000005633322,0.0001251566,0.000007015558,0.0001225046],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8133099,"threshold_uncertainty_score":0.3847447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04333806705082064,"score_gpt":0.3668126152849401,"score_spread":0.3234745482341195,"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."}}