Kaite Zhang

The paper introduces ChAI-Net, a deep learning model that predicts chromatin co-accessibility from DNA sequences in mouse embryonic stem cells, revealing sequence motifs that govern coordinated TF binding.

The paper introduces LASSI, a method to measure nucleosome spacing in chromatin interactions, revealing fiber homotypy as a structural pattern influenced by genomic features and cohesin dynamics.

This study shows that cohesin is not always necessary for enhancer function, as some enhancers can act independently through synergy or insulators.

HyPR-seq sensitively quantifies up to 100 chosen genes in single cells, achieving high sensitivity for individual transcripts and reducing costs compared to whole-transcriptome scRNA-seq.