Google · Japan · Meta · Google Research
Transfer learning for genomic prediction in underrepresented populations
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
Joey Poomarin Phloyphisut, Software Engineer, and Cory McLean, Senior Staff Software Engineer, Google Research.
Key facts
- In UKB, the estimated fraction of trait variance explained by the measured genetic variants (single nucleotide polymorphism heritability ) ranged from 0.07–0.28
- Specifically, they evaluate transferability of PRS ascertained in hundreds of thousands of European individuals within the UK Biobank (UKB) to samples within Biobank Japan (BBJ), a deeply-phenotyped
- The team observe that “conserved” traits, or those with higher genetic correlations between the two populations, retain the benefits of pooling UKB European training data up to much larger target sample
- For target sample sizes under 25k, PRS-CSx performs worse than the strongest corresponding elastic net model in all phenotypes except BMI
Summary
The team evaluate ways to improve cross-population genetic risk prediction and find that while transfer learning from European cohorts improves prediction in small underrepresented populations, it degrades accuracy once target cohort sample sizes grow, especially for traits with population-specific genetic architectures. Polygenic risk scores (PRSs) are used to predict disease risk from genetic variants. Moreover, conducting de novo GWASs across hundreds of thousands of individuals is cost-prohibitive for most healthcare systems. To that end, in this blog post they describe a study evaluating PRS performance in a target non-European population while varying the size of both the target population and European populations used to create the predictive model across eight clinical traits.