Genetics-driven Risk Predictions with Differentiable Mendelian Randomization
Sens, D. W.; Gräph, L.; Shilova, L.; Casale, F.-P.
Show abstract
Accurate predictive models of future disease onset are crucial for effective preventive healthcare, yet longitudinal datasets linking early risk factors to subsequent health outcomes are scarce. To address this challenge, we introduce Differentiable Mendelian Randomization (DMR), an extension of the classical Mendelian Randomization framework to learn risk predictors without longitudinal data. To do so, DMR leverages risk factors and genetic data from a healthy cohort, along with results from genome-wide association studies (GWAS) of diseases of interest. After training, the learned predictor can be used to assess risk for new patients solely based on risk factors. We validated DMR through comprehensive simulations and in future type 2 diabetes predictions in UK Biobank participants without diabetes, using follow-up onset labels for validation. Finally, we apply DMR to predict future Alzheimers onset from brain imaging biomarkers. Overall, with DMR we offer a new perspective in predictive modeling, showing it is possible to learn risk predictors leveraging genetics rather than longitudinal data.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Co-expression-wide association studies link genetically regulated interactions with complex traits 95%
- Multi-context genetic modeling of transcriptional regulation resolves novel disease loci 95%
- Calibrated rare variant genetic risk scores for complex disease prediction using large exome sequence repositories 94%
Similar papers in this journal
- Summary statistics from large-scale gene-environment interaction studies for re-analysis and meta-analysis 94%
- Accurate, scalable cohort variant calls using DeepVariant and GLnexus 93%
- Incorporating family disease history and controlling case-control imbalance for population based genetic association studies 93%
Similar papers in this journal
Similar papers in this journal
- Redefining tissue specificity of genetic regulation of gene expression in the presence of allelic heterogeneity 95%
- An integrative multi-context Mendelian randomization method for identifying risk genes across human tissues 95%
- Welch-weighted Egger regression reduces false positives due to correlated pleiotropy in Mendelian randomization 94%
Similar papers in this journal
"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.