Zhirong Yang

KMAP is a method for visualizing DNA sequences by projecting kmers into 2D space, showing it can detect patterns comparable to MEME and find biologically relevant interactions in ChIP-seq and gene editing data.

The paper introduces a self-supervised deep learning framework for DNA sequence analysis that improves variant effect prediction and open chromatin region prediction across human and plant genomes.

Mandrake reduces the dimensionality of large microbial genome datasets to visualize population structure, using both a pipeline and an interactive web application.