Penalised neural network with weight correlation descent for predicting polygenic risk score
Kim, S. b.; Kang, J. H.; Cheon, M.; Kim, D. J.; Lee, B.-C.
Show abstract
In this study, we developed a deep neural network (DNN) model with weight correlation descent (WCD) regularization to improve polygenic risk score predictions for complex diseases, specifically gender-specific cancers, using the UK Biobank dataset. Our DNN model with WCD outperformed both conventional PRS models and DNN models without WCD, demonstrating the importance of regularization techniques in enhancing model performance and capturing non-linear effects and interactions in genomic data. These findings contribute to a better understanding of genetic architecture, facilitating personalized interventions based on individual genetic profiles and ultimately benefiting patient care and health outcomes.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- DeepInsight-3D for precision oncology: an improved anti-cancer drug response prediction from high-dimensional multi-omics data with convolutional neural networks 93%
- Synthetic data for privacy-preserving clinical risk prediction 93%
- Hybrid Autoencoder with Orthogonal Latent Space for Robust Population Structure Inference 93%
Similar papers in this journal
- kTWAS: integrating kernel-machine with transcriptome-wide association studies improves statistical power and reveals novel genes 95%
- BayesKAT: Bayesian Optimal Kernel-based Test for genetic association studies reveals joint genetic effects in complex diseases 94%
- Computationally scalable regression modeling for ultrahigh-dimensional omics data with ParProx 94%
Similar papers in this journal
Similar papers in this journal
- Multi-Omic Graph Diagnosis (MOGDx) : A data integration tool to perform classification tasks for heterogeneous diseases 94%
- 3Cnet: Pathogenicity prediction of human variants using knowledge transfer with deep recurrent neural networks 94%
- Incorporating family disease history and controlling case-control imbalance for population based genetic association studies 94%
"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.