{"id":"W2171259901","doi":"10.1093/bioinformatics/btu556","title":"Prediction of Indel flanking regions in protein sequences using a variable-order Markov model","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Indel; Flanking maneuver; Markov chain; Variable (mathematics); Markov model; Computer science; Markov chain Monte Carlo; Order (exchange); Genetics; Mathematics; Statistics; Artificial intelligence; Biology; Gene; Bayesian probability; Geography","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":[0.0009303453,0.0004150217,0.0006405177,0.0008628885,0.0003232765,0.0004370983,0.0006650866,0.0007456036,0.0009838088],"category_scores_gemma":[0.002800101,0.0002674624,0.0006349065,0.0005662773,0.0002838106,0.000777059,0.0003819091,0.0007769127,0.0005706167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003386186,"about_ca_system_score_gemma":0.0008626917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002805905,"about_ca_topic_score_gemma":0.003729049,"domain_scores_codex":[0.9996756,0.00009454984,0.00002443347,0.00009402427,0.00007544053,0.000035969],"domain_scores_gemma":[0.9978402,0.001530804,0.0002640567,0.0001038286,0.0001810803,0.00008004911],"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":[0.001069382,0.0002755809,0.04274595,0.0002782611,0.0001735745,0.0005870599,0.0001303014,0.7769694,0.03433776,0.005182698,0.00212289,0.1361271],"study_design_scores_gemma":[0.000006149263,0.0000441667,0.001004465,0.000004854773,0.00001303188,0.00005525246,0.000004492834,0.9959169,0.001714998,0.00108564,0.0001442328,0.000005791791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3180895,0.0007520986,0.6771975,0.0002567934,0.00003318892,0.00006423944,0.0007064008,0.002151911,0.0007485036],"genre_scores_gemma":[0.8758524,0.0004586167,0.1206974,0.0001107192,0.00004227354,0.00008481994,0.001690986,0.00007710447,0.0009855871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002805905,"threshold_uncertainty_score":0.005579114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01887751051452912,"score_gpt":0.2466155044718355,"score_spread":0.2277379939573063,"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."}}