{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003455929,0.0001204899,0.0001301727,0.00003725999,0.0001124841,0.00007292847,0.0001042499,0.0001300499,0.000008147294],"category_scores_gemma":[0.0006068626,0.0001067775,0.00005665654,0.00003912776,0.00004661612,0.00001139467,0.00004146571,0.0001047918,0.000004961295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000663867,"about_ca_system_score_gemma":0.00002697637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009491197,"about_ca_topic_score_gemma":0.00000459276,"domain_scores_codex":[0.9992211,0.00005468601,0.0002463823,0.0002235094,0.00006940393,0.0001848588],"domain_scores_gemma":[0.999548,0.00001617079,0.000125884,0.0002048876,0.00005367627,0.00005134576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003431729,0.00003023244,0.0006592963,0.00007078735,0.00003786238,8.163248e-7,0.0001305185,0.0005749068,0.9336519,0.001467639,0.0006464146,0.06238647],"study_design_scores_gemma":[0.01040069,0.00419522,0.02398324,0.00009047959,0.000113458,0.0001816353,0.0003503327,0.09784118,0.7824275,0.009087813,0.06999119,0.001337219],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7071799,0.0001201086,0.2892052,0.0006723568,0.00004943546,0.0005622105,0.000003406656,0.0000316306,0.00217572],"genre_scores_gemma":[0.9731075,0.00004359286,0.01048556,0.0002562839,0.00010186,0.00001189272,0.000130213,0.00001223897,0.01585085],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2787197,"threshold_uncertainty_score":0.4354258,"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."}}