Ashmita Dey

SRSA-VAE improves single-cell clustering by using self-attention and residual connections, outperforming existing methods on scRNA-seq and CITE-seq data.

The paper investigates how HDAC and LSD1 inhibition alters chromatin accessibility and nucleosome positioning in cancer cells, revealing a JunB-mediated mechanism that highlights therapeutic vulnerabilities.

BRDKRM classifies drugs as disease-modifying or symptomatic using a graph-based framework, achieving 86.78% accuracy and identifying 530 genes involved in both categories.

The paper proposes a framework to identify diagnostic and therapeutic autoantibodies for neurodegenerative diseases and multiple sclerosis using statistical and structural analysis.