Manqi Cai

The paper introduces a supervised learning algorithm for multi-phenotype genomic prediction, showing improved performance in gene expression and DNA methylation analysis and cell type deconvolution.

BLEND improves cellular deconvolution by selecting optimal references and avoiding data preprocessing, showing better performance on real and simulated data.

HiDecon estimates rare cell type fractions in bulk transcriptomics data using hierarchical deconvolution with single-cell references and cell type trees.

scMD estimates cell type fractions from bulk DNAm data using single-cell DNA methylation references, showing improved performance in identifying Alzheimer's disease-related methylation patterns.