{"doi":"10.1101/2025.01.06.631535","title":"Population-scale variability at short tandem repeat loci reveals pathogenicity signature","abstract":"Summary Short tandem repeat (STR) instability is a major cause of disease association, yet their full length-distributions and sequence content have been difficult to resolve with short-read sequencing. By analyzing long-read sequencing genomes from 2,645 participants of the All of Us Research Program, we establish a comprehensive STR resource of 23 billion alleles covering a catalog of 4.4 million loci. We find that known disease-associated STR loci exhibit markedly elevated allelic variability relative to genome-wide distributions, which is most pronounced when based on the length of uninterrupted, pure repeat motifs (Odds Ratio: 244, p=1.62e-29). We establish the Pure Length Variability Index (PLVI) as a measure of this instability, which is robust across ancestries and replicated in 500 samples from the 1000 Genomes Project (Odds Ratio: 84, p=2.72e-28). To illustrate, we identify 55 unstable coding CAG and 5’-UTR CGG STR loci with this metric, 60% of which have not been associated with disease. From this set, we document potential pathogenic repeat expansions for FAM193B and EP400 by integrating PLVI with single-genome length outlier analysis. These data establish a population-scale framework for STR discovery in rare and common diseases using long-read sequencing cohorts.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2025,"id":554675,"datarank":0.4611183928911512,"base_score":2.4849066497880004,"endowment":2.4849066497880004,"self_citation_contribution":0.37273599746820013,"citation_network_contribution":0.08838239542295108,"self_endowment_contribution":0.37273599746820013,"citer_contribution":0.08838239542295108,"corpus_percentile":58.89224104587298,"corpus_rank":5315,"citation_count":11,"citer_count":9,"citers_with_citation_signal":4,"citers_with_endowment":4,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.6016,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":890766,"name":"Isaac Xu","orcid":"0000-0003-4443-0582","position":1,"is_corresponding":false},{"id":333915,"name":"Sarah Fazal","orcid":"0000-0001-9064-6152","position":2,"is_corresponding":false},{"id":246634,"name":"Egor Dolzhenko","orcid":"0000-0002-3296-0677","position":3,"is_corresponding":false},{"id":841726,"name":"David Pellerin","orcid":"0000-0002-5807-995X","position":4,"is_corresponding":false},{"id":997,"name":"Ben Weisburd","orcid":"0000-0001-9898-9109","position":5,"is_corresponding":false},{"id":129025,"name":"Chloe Reuter","orcid":"0000-0002-0429-9922","position":6,"is_corresponding":false},{"id":344368,"name":"Jacinda B. Sampson","orcid":"0000-0002-4991-6496","position":8,"is_corresponding":false},{"id":957809,"name":"Chiara Folland","orcid":"0000-0002-6346-4828","position":9,"is_corresponding":false},{"id":995,"name":"Anne H. O’Donnell-Luria","orcid":"0000-0001-6418-9592","position":10,"is_corresponding":false},{"id":21507,"name":"Stefan Wuchty","orcid":"0000-0001-8916-6522","position":11,"is_corresponding":false},{"id":242872,"name":"Gianina Ravenscroft","orcid":"0000-0003-3634-211X","position":12,"is_corresponding":false},{"id":62166,"name":"Michael A. Eberle","orcid":"0000-0001-8965-1253","position":13,"is_corresponding":false},{"id":88911,"name":"Stephan Züchner","orcid":"0000-0002-8498-5235","position":14,"is_corresponding":false},{"id":1452977,"name":"Sophia B. Gibson","orcid":null,"position":15,"is_corresponding":false},{"id":308538,"name":"Daniel G. Calame","orcid":"0000-0001-6860-372X","position":16,"is_corresponding":false},{"id":398081,"name":"Haloom Rafehi","orcid":"0000-0002-8954-4930","position":17,"is_corresponding":false},{"id":942396,"name":"Penny Snell","orcid":"0000-0002-9821-5282","position":18,"is_corresponding":false},{"id":1452978,"name":"Kate Kotschet","orcid":null,"position":19,"is_corresponding":false},{"id":1452979,"name":"Kayli C. Davies","orcid":null,"position":20,"is_corresponding":false},{"id":620471,"name":"Igor Stevanovski","orcid":"0000-0002-7713-1979","position":21,"is_corresponding":false},{"id":620467,"name":"Ira W. Deveson","orcid":"0000-0003-3861-0472","position":22,"is_corresponding":false},{"id":24426,"name":"Danny E. Miller","orcid":"0000-0001-6096-8601","position":23,"is_corresponding":false},{"id":69030,"name":"Chia-Lin Wei","orcid":null,"position":24,"is_corresponding":false},{"id":252352,"name":"Jane Grimwood","orcid":"0000-0002-8356-8325","position":25,"is_corresponding":false},{"id":1751,"name":"Donna M. Muzny","orcid":"0000-0002-3055-0359","position":26,"is_corresponding":false},{"id":1452980,"name":"Niall Lennon","orcid":null,"position":27,"is_corresponding":false},{"id":285434,"name":"Melanie Bahlo","orcid":"0000-0001-5132-0774","position":28,"is_corresponding":false},{"id":243312,"name":"Paul J. Lockhart","orcid":"0000-0003-2531-8413","position":29,"is_corresponding":false},{"id":919409,"name":"Matthew L. Wheeler","orcid":"0009-0004-6516-8549","position":30,"is_corresponding":false},{"id":1452981,"name":"Kiran V. Garimella","orcid":null,"position":35,"is_corresponding":false},{"id":49032,"name":"Fritz J. Sedlazeck","orcid":"0000-0001-6040-2691","position":36,"is_corresponding":false},{"id":1025,"name":"Michael E. Talkowski","orcid":"0000-0003-2889-0992","position":37,"is_corresponding":false},{"id":24539,"name":"Michael C. Schatz","orcid":"0000-0002-4118-4446","position":38,"is_corresponding":false},{"id":2125,"name":"Evan E. Eichler","orcid":"0000-0002-8246-4014","position":39,"is_corresponding":false},{"id":298704,"name":"Matt C. Danzi","orcid":"0000-0003-1568-5965","position":0,"is_corresponding":true}],"reference_count":40,"raw_metadata":null,"created_at":"2026-07-19T02:54:54.542303Z","pmid":"39868092","pmcid":"PMC11760257","fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}