Xiaowei Zhu

RetroNet detects low-mosaicism somatic mobile element insertions using deep learning on sequencing read images, achieving high precision and recall with minimal reads.

The paper develops a framework to detect and trace somatic retrotransposition events in human tissues, identifying rare L1 insertions and improving detection accuracy.

DeepMosaic detects mosaic single nucleotide variants without control samples using deep convolutional neural networks, achieving high accuracy and uncovering many variants missed by existing methods.

The paper evaluates brain somatic mosaicism in the adult human to identify rules governing cellular distribution during embryogenesis.

The paper introduces a machine learning method to detect somatic L1 insertions in human brain tissue, revealing their widespread distribution in neurons and glia and potential role in neuropsychiatric diseases.

The paper shows that full-length LINE-1s with functional ORFs are under stronger host-level selection in human genomes, as indicated by higher selection coefficients and SNP depletion in ORFs.

The paper provides a comprehensive whole-genome analysis of K562, identifying genomic structural features and their impact on functional genomics data.

This paper provides a haplotype-resolved genome analysis of the HepG2 cell line, identifying genomic features and allele-specific regulation to support functional genomics studies.

The paper investigates how large genomic deletions affect chromatin interactions and states in human brain development using Hi-C and ChIP-Seq analyses.