{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005815929,0.0001621751,0.0001873169,0.0001392058,0.00006746891,0.00002591674,0.0002225803,0.0002135933,0.000005514531],"category_scores_gemma":[0.0003659891,0.0001522896,0.0000446863,0.0002484862,0.00008183409,0.00002792559,0.0001278706,0.00016643,0.000002411943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002844208,"about_ca_system_score_gemma":0.0001705862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003722911,"about_ca_topic_score_gemma":0.0000130059,"domain_scores_codex":[0.9987376,0.00004674969,0.0006368083,0.0001141736,0.0002171779,0.0002475276],"domain_scores_gemma":[0.9991125,0.00001439631,0.0003410649,0.0003598732,0.0001212958,0.00005080426],"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":[0.0001927512,0.0002266901,0.02486185,0.002132136,0.0001513007,8.833794e-7,0.003620922,0.7375822,0.2094819,0.01205194,0.001023466,0.008673979],"study_design_scores_gemma":[0.0004378893,0.0001144658,0.0002026412,0.0001404205,0.00001281369,0.0000135702,0.0001399011,0.9942845,0.003181285,0.0004526784,0.0008684871,0.0001513389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4157997,0.00002314271,0.5751657,0.00003362499,0.00006615615,0.0003490788,0.00003157659,0.0000242984,0.008506702],"genre_scores_gemma":[0.5500876,0.00001273897,0.4494473,0.0001164432,0.00005183808,0.00001348499,0.0001133513,0.00001553584,0.0001417536],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2567023,"threshold_uncertainty_score":0.6210189,"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."}}