Aditya S. Deshpande

This paper introduces MRD-EDGE, a machine learning platform for ultrasensitive ctDNA detection in plasma WGS, showing improved sensitivity and broader applicability for MRD monitoring.

The paper identifies 'loose ends' in cancer genomes, structural variations missed by short-read WGS, and estimates they account for <3% of large-scale structural variation.

dryclean improves somatic copy number alteration detection in cancer genomes by reducing read depth waviness through signal processing.

The paper identifies three novel complex structural variation patterns in cancer genomes using genome graph analysis across 2,833 tumor WGS.

Pore-C reads multi-way chromatin contacts directly off unamplified Nanopore long reads, recovering Hi-C-scale features while also resolving rearranged cancer alleles and supporting de novo assembly.