Delphi: A Deep-learning Framework for Polygenic Risk Prediction
Georgantas, C.; Kutalik, Z.; Richiardi, J.
Show abstract
Polygenic scores (PGS) are relative measures of an individuals genetic propensity to a particular trait or disease. Most PGS methods use a regression framework for polygenic modeling and assume that mutation effect estimates are constant across individuals. While these assumptions simplify computation, they increase error, and PGS are particularly less predictive for under-represented genetic ancestries. We developed and provide Delphi (deep learning for phenotype inference), an individual-level deep-learning method that relaxes these assumptions to produce more predictive PGS. Delphi can integrate up to hundreds of thousands of SNPs as input and model non-linear SNP-SNP and SNP-covariate interactions. We compare our results with linear PGS models and a gradient-boosted trees-based method. We show that deep learning can be an effective approach to genetic risk prediction. We report substantial performance gains for a broad range of continuous phenotypes compared to the state-of-the-art. Furthermore, we show that Delphi tends to increase the weight of high-effect mutations. This work demonstrates an effective deep learning method for modeling genetic risk that also generalizes well when evaluated on individuals from non-European ancestries.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- BinomiRare: A carriers-only test for association of rare genetic variants with a binary outcome for mixed models and any case-control proportion 95%
- Evaluation of imputation performance of multiple reference panels in a Pakistani population 95%
- Variational Autoencoder-based Model Improves Polygenic Prediction in Blood Cell Traits 94%
Similar papers in this journal
- Summary statistics from large-scale gene-environment interaction studies for re-analysis and meta-analysis 95%
- Bayesian Estimation of Allele-Specific Expression in the Presence of Phasing Uncertainty 94%
- GNN4DM: A Graph Neural Network-based method to identify overlapping functional disease modules 94%
Similar papers in this journal
- FiMAP: A Fast Identity-by-Descent Mapping Test for Biobank-scale Cohorts 95%
- Joint Modeling of Effect Sizes for Two Correlated Traits: Characterizing Trait Properties to Enhance Polygenic Risk Prediction 95%
- Evaluation of Polygenic Prediction Methodology within a Reference-Standardized Framework 95%
Similar papers in this journal
- Probabilistic inference of the genetic architecture underlying functional enrichment of complex traits 95%
- Fast Kernel-based Association Testing of non-linear genetic effects for Biobank-scale data 95%
- Co-expression-wide association studies link genetically regulated interactions with complex traits 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.