Mahfuza Sharmin

This paper introduces ConcuRx, a statistical framework that improves gene prioritization across heterogeneous CRISPR drug-response datasets by modeling between-study variability, leading to better identification of MOA-associated genes.

GEO-BERT improves dataset retrieval from GEO by using a retrieval-augmented LLM framework with a hierarchical hybrid field-aware system, enhancing semantic search and traditional search performance.

This study identifies compound #63 as a potent LZK inhibitor that suppresses tumor growth and enhances EGFR and PI3K pathway blockade in HNSCC and ESCC.

The paper investigates chromatin accessibility changes in neurogenic niche cells during aging, identifying defects in NSC adhesion and migration and proposing ROCK inhibition as a potential therapeutic strategy.

The paper identifies dynamic cis-regulatory elements in epidermal differentiation using multi-omic data and deep learning, revealing combinatorial motif rules linked to gene expression and polygenic skin disease.

The paper identifies 71,946 genetic interactions in cancer using a novel method, revealing non-synthetic-lethal interactions that explain driver gene specificity and drug response.

This study develops TRISECT, an ensemble method to identify heterogeneous TF binding rules across cell types, showing improved accuracy in predicting TF occupancy and revealing shared binding rules with functionally coherent targets.

The paper identifies hypomethylated blocks in colon cancer and shows they are marked by specific epigenomic and transcription factor features, including H3K4me3 and CTCF sites.