Pooya Zakeri

BfBio predicts angiogenic stalk cell genes using a Personalized PageRank algorithm, achieving high AUC-ROC performance and identifying novel cancer-related genes.

This study benchmarks nine joint multi-omics dimensionality reduction methods using simulated and real cancer data, finding intNMF excels in clustering and MCIA shows consistent performance across contexts.

The paper analyzes genetic variation in ACE2 across Iranian populations to assess its association with COVID-19 severity, finding limited impact of exonic variants on disease outcomes.

The paper uses multi-task learning to link drug targets and pathway activation, revealing interactions that guide tissue-specific combination therapies.