{"id":"W4415125891","doi":"10.1101/2025.10.11.25337795","title":"Population-scale disease-associated tandem repeat analysis reveals locus and ancestry-specific insights","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada","keywords":"Locus (genetics); Penetrance; Linkage disequilibrium; Phylogenetic tree; Allele; Tandem repeat; Variable number tandem repeat; Sequence (biology)","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":[0.0007101474,0.000185739,0.0002255516,0.0006047921,0.0002109802,0.0005486654,0.0001846997,0.0002732609,0.0009909488],"category_scores_gemma":[0.0007669408,0.0001128418,0.0002171486,0.0005962097,0.0002455043,0.0001872524,0.000430169,0.0004930797,0.0003357289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001414897,"about_ca_system_score_gemma":0.0001277155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006283167,"about_ca_topic_score_gemma":0.0009654886,"domain_scores_codex":[0.9998034,0.00004221371,0.00001219184,0.00007839892,0.00003545392,0.0000284565],"domain_scores_gemma":[0.9996696,0.0001240337,0.00009408998,0.00004994589,0.00002727913,0.00003508902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00043861,0.0001155354,0.2492892,0.000137306,0.0003277413,0.0007764369,0.0009244876,0.006770508,0.6938593,0.002438982,0.0009470459,0.04397483],"study_design_scores_gemma":[0.00003709135,0.0002821714,0.8488937,0.00004778921,0.0002286112,0.002361007,0.0007545044,0.04192977,0.0909067,0.006118533,0.008368908,0.00007114028],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9835778,0.0003302189,0.01429489,0.00005294372,0.000007445219,0.000005547134,0.0008350743,0.0001316283,0.0007644799],"genre_scores_gemma":[0.9913467,0.0001270885,0.007136106,0.00003193656,0.000009528246,0.000004799572,0.0009914915,0.00004689957,0.0003054538],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0009909488,"threshold_uncertainty_score":0.003755629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01460000538994786,"score_gpt":0.2575625608601693,"score_spread":0.2429625554702214,"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."}}