Pankaj Vats

This paper presents near-complete, haplotype-resolved assemblies of a pancreatic cancer genome and normal tissue, identifying extensive somatic variants and epigenetic changes in previously excluded regions.

DeepSAP improves RNA-seq alignment by combining transcriptome-guided alignment with a transformer-based model for splice junction scoring, achieving the highest F1 score on simulated datasets.

This paper introduces an EHR foundation model integrating Polygenic Risk Scores to improve disease prediction and personalized healthcare using All of Us data.

Parabricks accelerates genomic analysis using GPU acceleration, reducing processing time while maintaining accuracy across various sequencing modalities.

The paper identifies recurrent SLC30A1 mutations in aldosterone-producing adenomas and shows they cause abnormal ion transport leading to aldosterone excess in primary aldosteronism.

The paper identifies de novo variants in the 1000 Genomes Project using a GPU-based workflow, revealing cell line artifacts and cancer-related mutation profiles.