Department of Biostatistics, University of Michigan School of Public Health, Ann Arbor, MI 48109, USA.
Department of Biostatistics, University of Michigan School of Public Health, Ann Arbor, MI 48109, USA; Rogel Cancer Center, University of Michigan Medicine, Ann Arbor, MI 48109, USA.
Am J Hum Genet. 2022 Nov 3;109(11):1998-2008. doi: 10.1016/j.ajhg.2022.09.010. Epub 2022 Oct 13.
As most existing genome-wide association studies (GWASs) were conducted in European-ancestry cohorts, and as the existing polygenic risk score (PRS) models have limited transferability across ancestry groups, PRS research on non-European-ancestry groups needs to make efficient use of available data until we attain large sample sizes across all ancestry groups. Here we propose a PRS method using transfer learning techniques. Our approach, TL-PRS, uses gradient descent to fine-tune the baseline PRS model from an ancestry group with large sample GWASs to the dataset of target ancestry. In our application of constructing PRS for seven quantitative and two dichotomous traits for 10,285 individuals of South Asian ancestry and 8,168 individuals of African ancestry in UK Biobank, TL-PRS using PRS-CS as a baseline method obtained 25% average relative improvement for South Asian samples and 29% for African samples compared to the standard PRS-CS method in terms of predicted R. Our approach increases the transferability of PRSs across ancestries and thereby helps reduce existing inequities in genetics research.
由于大多数现有的全基因组关联研究（GWAS）都是在欧洲血统队列中进行的，而且现有的多基因风险评分（PRS）模型在不同血统群体之间的可转移性有限，因此，在我们获得所有血统群体的大样本量之前，非欧洲血统群体的 PRS 研究需要有效地利用现有数据。在这里，我们提出了一种使用迁移学习技术的 PRS 方法。我们的方法 TL-PRS 使用梯度下降来微调来自具有大量样本 GWAS 的血统群体的基线 PRS 模型，以适应目标血统的数据集。在我们为 UK Biobank 中 10285 名南亚血统和 8168 名非洲血统的个体构建七个定量和两个二分性状的 PRS 的应用中，TL-PRS 使用 PRS-CS 作为基线方法，与标准的 PRS-CS 方法相比，南亚样本的平均相对改善为 25%，非洲样本的平均相对改善为 29%，在预测 R 方面。我们的方法提高了 PRS 在不同血统之间的可转移性，从而有助于减少遗传研究中的现有不平等现象。
