Transfer Learning in Genome-Wide Association Studies with Knockoffs
Shuangning Li1, Zhimei Ren2, Chiara Sabatti3
1Department of Statistics, Harvard University, Stanford, CA 94305, USA.
Sankhya. Series B (2008)
|August 11, 2025
Summary
This study introduces transfer learning to enhance conditional testing via knockoffs, improving the discovery of genetic associations in diverse populations. This approach aids in developing more accurate polygenic risk scores by leveraging external data.
Area of Science:
- Genetics
- Statistical Genetics
- Machine Learning
Background:
- Genome-wide association studies (GWAS) require methods to analyze genetic variation across diverse ancestries.
- Leveraging external datasets is crucial for improving statistical power in genetic association testing.
Purpose of the Study:
- To present and compare transfer learning methods for enhancing conditional testing via knockoffs.
- To address the need for principled methods to account for and learn from genetic variation in diverse populations.
- To improve the discovery of genetic associations in underrepresented groups.
Main Methods:
- Development and comparison of alternative transfer learning techniques.
- Application of transfer learning to conditional testing using knockoffs.
- Analysis of UK Biobank data for multiple phenotypes.
Main Results:
- Transfer learning significantly increases the power of conditional testing via knockoffs.
- The methods effectively leverage prior information from external datasets.
- Improved discovery of genetic associations in data from minority populations was observed.
Conclusions:
- Transfer learning offers a principled approach to incorporate external data in genetic association studies.
- This methodology enhances the identification of genetic associations, particularly in diverse ancestries.
- The findings pave the way for more accurate polygenic risk score development.
More Related Videos
Related Concept Videos
01:11Genome-wide Association Studies-GWAS
14.2K
Genome-wide association studies or GWAS are used to identify whether common SNPs are associated with certain diseases. Suppose specific SNPs are more frequently observed in individuals with a particular disease than those without the disease. In that case, those SNPs are said to be associated with the disease. Chi-square analysis is performed to check the probability of the allele likely to be associated with the disease.
GWAS does not require the identification of the target gene involved in...
GWAS does not require the identification of the target gene involved in...
14.2K
02:07Improving Translational Accuracy
11.9K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.9K
02:26Comparing Copy Number Variations and SNPs
17.9K
Sequencing of the human genome has opened up several best-kept secrets of the genome. Scientists have identified thousands of genome variations that exist within a population. These variations can be a single nucleotide or a larger chromosomal variation.
Copy number variations or CNVs are the structural variations that cover more than 1kb of DNA sequence. The single nucleotide polymorphism (SNP), on the other hand, is a single nucleotide change or a point mutation that is found in more than 1%...
Copy number variations or CNVs are the structural variations that cover more than 1kb of DNA sequence. The single nucleotide polymorphism (SNP), on the other hand, is a single nucleotide change or a point mutation that is found in more than 1%...
17.9K
01:16In-vitro Mutagenesis
14.2K
To learn more about the function of a gene, researchers can observe what happens when the gene is inactivated or “knocked out,” by creating genetically engineered knockout animals. Knockout mice have been particularly useful as models for human diseases such as cancer, Parkinson’s disease, and diabetes.
14.2K
01:05Single Nucleotide Polymorphisms-SNPs
15.9K
A single nucleotide polymorphism or SNP is a single nucleotide variation at a specific genomic position in a large population. It is the most prevalent type of sequence variation found in the human genome. Point mutations that occur in more than 1% of the population qualify as SNPs. These are present once every 1000 nucleotides on an average in the human genome. Replacement of a purine with another purine (A/G) or a pyrimidine with another pyrimidine (C/T) is known as a transition. In contrast,...
15.9K
02:54Evolutionary Relationships through Genome Comparisons
6.1K
Genome comparison is one of the excellent ways to interpret the evolutionary relationships between organisms. The basic principle of genome comparison is that if two species share a common feature, it is likely encoded by the DNA sequence conserved between both species. The advent of genome sequencing technologies in the late 20th century enabled scientists to understand the concept of conservation of domains between species and helped them to deduce evolutionary relationships across diverse...
6.1K