{"title":"Trait Imputation Enhances Nonlinear Genetic Prediction for Some Traits.","authors":"Ruoyu He,Jinwen Fu,Jingchen Ren,Wei Pan","doi":"10.1093/genetics/iyae148","DOIUrl":null,"url":null,"abstract":"The expansive collection of genetic and phenotypic data within biobanks offers an unprecedented opportunity for biomedical research. However, the frequent occurrence of missing phenotypes presents a significant barrier to fully leveraging this potential. In our target application, on one hand, we have only a small and complete dataset with both genotypes and phenotypes to build a genetic prediction model, commonly called a polygenic (risk) score (PGS or PRS); on the other hand, we have a large dataset of genotypes (e.g. from a biobank) without the phenotype of interest. Our goal is to leverage the large dataset of genotypes (but without the phenotype) and a separate GWAS summary dataset of the phenotype to impute the phenotypes, which are then used as an individual-level dataset, along with the small complete dataset, to build a nonlinear model as PGS. More specifically, we trained some nonlinear models to 7 imputed and observed phenotypes from the UK Biobank data. We then trained an ensemble model to integrate these models for each trait, resulting in higher R2 values in prediction than using only the small complete (observed) dataset. Additionally, for 2 of the 7 traits, we observed that the nonlinear model trained with the imputed traits had higher R2 than using the imputed traits directly as the PGS, while for the remaining 5 traits, no improvement was found. These findings demonstrates the potential of leveraging existing genetic data and accounting for nonlinear genetic relationships to improve prediction accuracy for some traits.","PeriodicalId":12706,"journal":{"name":"Genetics","volume":"11 1","pages":""},"PeriodicalIF":3.3000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Genetics","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1093/genetics/iyae148","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The expansive collection of genetic and phenotypic data within biobanks offers an unprecedented opportunity for biomedical research. However, the frequent occurrence of missing phenotypes presents a significant barrier to fully leveraging this potential. In our target application, on one hand, we have only a small and complete dataset with both genotypes and phenotypes to build a genetic prediction model, commonly called a polygenic (risk) score (PGS or PRS); on the other hand, we have a large dataset of genotypes (e.g. from a biobank) without the phenotype of interest. Our goal is to leverage the large dataset of genotypes (but without the phenotype) and a separate GWAS summary dataset of the phenotype to impute the phenotypes, which are then used as an individual-level dataset, along with the small complete dataset, to build a nonlinear model as PGS. More specifically, we trained some nonlinear models to 7 imputed and observed phenotypes from the UK Biobank data. We then trained an ensemble model to integrate these models for each trait, resulting in higher R2 values in prediction than using only the small complete (observed) dataset. Additionally, for 2 of the 7 traits, we observed that the nonlinear model trained with the imputed traits had higher R2 than using the imputed traits directly as the PGS, while for the remaining 5 traits, no improvement was found. These findings demonstrates the potential of leveraging existing genetic data and accounting for nonlinear genetic relationships to improve prediction accuracy for some traits.
期刊介绍:
GENETICS is published by the Genetics Society of America, a scholarly society that seeks to deepen our understanding of the living world by advancing our understanding of genetics. Since 1916, GENETICS has published high-quality, original research presenting novel findings bearing on genetics and genomics. The journal publishes empirical studies of organisms ranging from microbes to humans, as well as theoretical work.
While it has an illustrious history, GENETICS has changed along with the communities it serves: it is not your mentor''s journal.
The editors make decisions quickly – in around 30 days – without sacrificing the excellence and scholarship for which the journal has long been known. GENETICS is a peer reviewed, peer-edited journal, with an international reach and increasing visibility and impact. All editorial decisions are made through collaboration of at least two editors who are practicing scientists.
GENETICS is constantly innovating: expanded types of content include Reviews, Commentary (current issues of interest to geneticists), Perspectives (historical), Primers (to introduce primary literature into the classroom), Toolbox Reviews, plus YeastBook, FlyBook, and WormBook (coming spring 2016). For particularly time-sensitive results, we publish Communications. As part of our mission to serve our communities, we''ve published thematic collections, including Genomic Selection, Multiparental Populations, Mouse Collaborative Cross, and the Genetics of Sex.