{"id":"W1598700272","doi":"10.1137/1.9781611972795.12","title":"Learning Random-Walk Kernels for Protein Remote Homology Identification and Motif Discovery","year":2009,"lang":"en","type":"article","venue":"","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":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Ontario Genomics Institute; Genome Canada","keywords":"Random walk; Kernel (algebra); Random forest; Computer science; Artificial intelligence; Homology (biology); Smith–Waterman algorithm; Machine learning; Mathematics; Pattern recognition (psychology); Computational biology; Sequence alignment; Combinatorics; Biology; Statistics; Genetics; Peptide sequence; Gene","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002115486,0.0006226882,0.001051096,0.00128455,0.0003409791,0.0006292145,0.00121777,0.001025882,0.0007193085],"category_scores_gemma":[0.00655607,0.0003366543,0.0007740728,0.001084547,0.0006121096,0.002142124,0.000837708,0.0009987692,0.0007117687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004871972,"about_ca_system_score_gemma":0.00053431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009221885,"about_ca_topic_score_gemma":0.001124564,"domain_scores_codex":[0.998865,0.0004929727,0.00007599223,0.0002257697,0.0002625639,0.00007778507],"domain_scores_gemma":[0.9969432,0.001651381,0.0004168141,0.0005097822,0.000375625,0.0001032433],"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":[0.0004411248,0.0004171906,0.005985636,0.0002299844,0.0001860554,0.0002091378,0.0001259624,0.5273284,0.025718,0.02424669,0.002075662,0.4130362],"study_design_scores_gemma":[0.000008304103,0.00003331174,0.0004567394,0.000004459591,0.000005771288,0.00005430231,0.000008832273,0.9879814,0.004043515,0.007073484,0.0003178469,0.00001214804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04644741,0.0002531083,0.9520093,0.00006743651,0.000007138693,0.00002760467,0.00003743955,0.0008155109,0.0003349474],"genre_scores_gemma":[0.5950482,0.0002809255,0.4028473,0.00006502425,0.00002106158,0.0001051471,0.0004078179,0.0001232981,0.001101168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002115486,"threshold_uncertainty_score":0.01118791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005541963861312761,"score_gpt":0.2530038942527729,"score_spread":0.2474619303914602,"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."}}