Kaiqian Zhang

A Principled Framework for Using Correlated Traits to Improve Risk Prediction

This paper develops a framework to improve polygenic risk scores by using correlated traits, showing that helper traits can significantly enhance prediction accuracy for type 2 diabetes.

Learning probabilistic protein-DNA recognition codes from DNA-binding specificities using structural mappings

This paper introduces rCLAMPS, a method to infer protein-DNA recognition codes from DNA-binding specificities, enabling prediction of TF specificities and mutation effects.