Ricardo A Vialle, Lei Yu, Yan Li, Roberto T Raittz, Jose M Farfel, Philip L De Jager, Julie A Schneider, Lisa L Barnes, Shinya Tasaki, David A Bennett
{"title":"利用全基因组测序对TOMM40'523多态性进行基因分型","authors":"Ricardo A Vialle, Lei Yu, Yan Li, Roberto T Raittz, Jose M Farfel, Philip L De Jager, Julie A Schneider, Lisa L Barnes, Shinya Tasaki, David A Bennett","doi":"10.1016/j.xhgg.2025.100488","DOIUrl":null,"url":null,"abstract":"<p><p>The TOMM40'523 poly-T repeat polymorphism (rs10524523) has been associated with cognitive decline and Alzheimer's disease (AD) progression. Challenges in processing whole-genome sequencing (WGS) data traditionally require additional PCR and targeted sequencing assays to genotype these polymorphisms. We introduce a computational pipeline that integrates multiple short tandem repeat (STR) detection tools in an ensemble machine learning model using XGBoost. Using a sample of 1,202 participants from 4 cohort studies, we benchmarked our method against PCR-based measures. Our ensemble model outperformed individual STR tools, improving repeat length estimation accuracy (R<sup>2</sup> = 0.92) and achieving an accuracy rate of 93.2% compared with PCR-derived genotypes. Additionally, we validated our WGS-derived genotypes by replicating previously reported associations between TOMM40'523 variants and cognitive decline. Our computational genotyping tool is a scalable and reliable alternative to PCR-based assays, enabling broader investigations of TOMM40 variation in studies with WGS data.</p>","PeriodicalId":34530,"journal":{"name":"HGG Advances","volume":" ","pages":"100488"},"PeriodicalIF":3.6000,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Genotyping TOMM40'523 poly-T polymorphisms using whole-genome sequencing.\",\"authors\":\"Ricardo A Vialle, Lei Yu, Yan Li, Roberto T Raittz, Jose M Farfel, Philip L De Jager, Julie A Schneider, Lisa L Barnes, Shinya Tasaki, David A Bennett\",\"doi\":\"10.1016/j.xhgg.2025.100488\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>The TOMM40'523 poly-T repeat polymorphism (rs10524523) has been associated with cognitive decline and Alzheimer's disease (AD) progression. Challenges in processing whole-genome sequencing (WGS) data traditionally require additional PCR and targeted sequencing assays to genotype these polymorphisms. We introduce a computational pipeline that integrates multiple short tandem repeat (STR) detection tools in an ensemble machine learning model using XGBoost. Using a sample of 1,202 participants from 4 cohort studies, we benchmarked our method against PCR-based measures. Our ensemble model outperformed individual STR tools, improving repeat length estimation accuracy (R<sup>2</sup> = 0.92) and achieving an accuracy rate of 93.2% compared with PCR-derived genotypes. Additionally, we validated our WGS-derived genotypes by replicating previously reported associations between TOMM40'523 variants and cognitive decline. Our computational genotyping tool is a scalable and reliable alternative to PCR-based assays, enabling broader investigations of TOMM40 variation in studies with WGS data.</p>\",\"PeriodicalId\":34530,\"journal\":{\"name\":\"HGG Advances\",\"volume\":\" \",\"pages\":\"100488\"},\"PeriodicalIF\":3.6000,\"publicationDate\":\"2025-10-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"HGG Advances\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1016/j.xhgg.2025.100488\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/8/7 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"GENETICS & HEREDITY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"HGG Advances","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1016/j.xhgg.2025.100488","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/8/7 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"GENETICS & HEREDITY","Score":null,"Total":0}
Genotyping TOMM40'523 poly-T polymorphisms using whole-genome sequencing.
The TOMM40'523 poly-T repeat polymorphism (rs10524523) has been associated with cognitive decline and Alzheimer's disease (AD) progression. Challenges in processing whole-genome sequencing (WGS) data traditionally require additional PCR and targeted sequencing assays to genotype these polymorphisms. We introduce a computational pipeline that integrates multiple short tandem repeat (STR) detection tools in an ensemble machine learning model using XGBoost. Using a sample of 1,202 participants from 4 cohort studies, we benchmarked our method against PCR-based measures. Our ensemble model outperformed individual STR tools, improving repeat length estimation accuracy (R2 = 0.92) and achieving an accuracy rate of 93.2% compared with PCR-derived genotypes. Additionally, we validated our WGS-derived genotypes by replicating previously reported associations between TOMM40'523 variants and cognitive decline. Our computational genotyping tool is a scalable and reliable alternative to PCR-based assays, enabling broader investigations of TOMM40 variation in studies with WGS data.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
