{"id":"W2951000946","doi":"10.1016/j.ajhg.2019.05.016","title":"Bioinformatics-Based Identification of Expanded Repeats: A Non-reference Intronic Pentamer Expansion in RFC1 Causes CANVAS","year":2019,"lang":"en","type":"article","venue":"The American Journal of Human Genetics","topic":"Genetic Neurodegenerative Diseases","field":"Neuroscience","cited_by":285,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Western Hospital; University of Toronto; University Health Network","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Human Genome Research Institute; National Institutes of Health; National Institute of Neurological Disorders and Stroke; National Institute of General Medical Sciences; Wellcome Trust; National Ataxia Foundation","keywords":"Genetics; Biology; Haplotype; Trinucleotide repeat expansion; Computational biology; Alu element; Whole genome sequencing; Reference genome; DNA sequencing; Tandem repeat; Genome; Gene; Bioinformatics; Human genome; Genotype; Allele","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001169767,0.0006904701,0.0006232336,0.00210422,0.0004578343,0.0007548813,0.0004763862,0.0005462294,0.0008602996],"category_scores_gemma":[0.003190252,0.0002046432,0.00084813,0.001440376,0.0002854856,0.0002637709,0.0006071503,0.000410507,0.0006369098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003641696,"about_ca_system_score_gemma":0.0006017519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002400334,"about_ca_topic_score_gemma":0.004196278,"domain_scores_codex":[0.9992107,0.0001400422,0.00008116399,0.0002938051,0.0002002161,0.00007405962],"domain_scores_gemma":[0.9987257,0.000655471,0.0002533069,0.0001068684,0.0001519877,0.0001065389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001898263,0.0004498887,0.4254484,0.0006340802,0.000774205,0.007991698,0.0008205702,0.02875374,0.397833,0.001035325,0.003465341,0.1308956],"study_design_scores_gemma":[0.0002018901,0.0005818572,0.4359342,0.0001307222,0.0007351662,0.01200939,0.0005402668,0.3539275,0.1831973,0.002404626,0.0102005,0.0001365255],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.963661,0.0005115038,0.03014004,0.0001996075,0.00002200306,0.0001558845,0.002606435,0.001362753,0.001340693],"genre_scores_gemma":[0.9283228,0.0002741256,0.06293049,0.0001808214,0.00002252801,0.00009179493,0.007409547,0.0002106552,0.0005572063],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002400334,"threshold_uncertainty_score":0.006186426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03025217651506036,"score_gpt":0.3022048806693841,"score_spread":0.2719527041543237,"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."}}