Dinghao Wang

MOKA: A pipeline for multi-omics bridged SNP-set kernel association test

MOKA integrates multi-omics data into GWAS using a kernel association test pipeline, identifying 89 significant genes in schizophrenia with 15.7% validation in DisGeNET.

cLD: Rare-variant disequilibrium between genomic regions identifies novel genomic interactions

The paper introduces cLD, a statistic for measuring rare-variant linkage disequilibrium between genomic regions, and shows it identifies novel genomic interactions and associations.

The Bias of Using Cross-Validation in Genomic Predictions and Its Correction

This study identifies and corrects cross-validation bias in genomic prediction methods using CVc, showing effectiveness for most methods except Lasso and ENET.

Tissue-specific transfer-learning enables retasking of a general comprehensive model to a specific domain

The paper applies transfer learning to adapt a general-purpose model to a specific domain using limited data, demonstrating improved performance in breast cancer-related tasks.

Gradient-based implementation of linear model outperforms deep learning models

This paper shows that re-implementing a traditional linear mixed model with a modern gradient solver can outperform deep learning models in speed and accuracy for biological data.