{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003531898,0.0001817965,0.0003935112,0.0002836575,0.00007660725,0.00004621247,0.0006992606,0.00001988508,0.00006171418],"category_scores_gemma":[0.0001583255,0.0001330689,0.0001067002,0.0004221028,0.0004691581,0.0001001802,0.0000787684,0.0002239204,0.0000256586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006895322,"about_ca_system_score_gemma":0.0002840605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000390647,"about_ca_topic_score_gemma":0.00002580711,"domain_scores_codex":[0.9977019,0.000286082,0.0009869802,0.0002038966,0.0005666036,0.0002545432],"domain_scores_gemma":[0.9972642,0.0002030221,0.001653231,0.0005974043,0.0001946501,0.00008751234],"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":[0.000103843,0.0001214266,0.008455231,0.00002248385,0.000007474643,0.000003961434,0.0008169728,0.00681145,0.9819184,0.00002116682,0.00004533626,0.001672286],"study_design_scores_gemma":[0.0007213777,0.001135247,0.05588934,0.00007001236,0.00004027822,0.00001814502,0.001272641,0.001645267,0.9389351,0.0001122167,0.00001694255,0.0001434176],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9990986,0.00008141976,0.0002199165,0.000101258,0.0001259294,0.0002869768,0.00001330695,0.000005988773,0.00006663412],"genre_scores_gemma":[0.9992275,0.0001456972,0.0001873706,0.0003153543,0.00003390609,0.000006238536,0.00000189571,0.00002183864,0.00006020616],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04743411,"threshold_uncertainty_score":0.5426394,"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."}}