{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001964039,0.0005682335,0.0007048683,0.0009317922,0.00024789,0.0007856592,0.001246562,0.0008608493,0.0007993227],"category_scores_gemma":[0.009207773,0.0002860659,0.0005955963,0.0008972748,0.0006682233,0.002555641,0.0008907591,0.001220408,0.0005882866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007144364,"about_ca_system_score_gemma":0.0007430848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001231746,"about_ca_topic_score_gemma":0.000866428,"domain_scores_codex":[0.9988509,0.00049136,0.00007260164,0.000168243,0.0003385426,0.00007823078],"domain_scores_gemma":[0.9968599,0.001480647,0.0003946848,0.0006229714,0.0005269391,0.0001149088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004100783,0.0002999436,0.003106943,0.0001591135,0.0000971853,0.0001324082,0.0001087944,0.6298497,0.01070848,0.06399246,0.002113088,0.2890217],"study_design_scores_gemma":[0.000005363543,0.00001672102,0.0002231529,0.000002414499,0.000002424471,0.0000194251,0.000004300198,0.9922694,0.0009720669,0.006243654,0.0002353639,0.000005799942],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.036651,0.000392823,0.9618552,0.0001351645,0.00001438984,0.00002110712,0.00004249636,0.0004222104,0.0004654957],"genre_scores_gemma":[0.7145011,0.0005033953,0.2824583,0.00008030309,0.00005377713,0.0001120848,0.0003804303,0.0001016239,0.001808979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001964039,"threshold_uncertainty_score":0.01038694,"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."}}