Amit G. Deshwar

The paper introduces BigRNA, an RNA foundation model that predicts RNA biology from DNA sequence and identifies therapeutic effects of SBOs on gene expression and splicing.

The paper benchmarks 31 subclonal reconstruction algorithms on simulated tumours, finding that algorithm choice significantly impacts performance and no single algorithm excels across all tasks.

This study evaluates off-target effects of steric-blocking oligonucleotides using RNA-seq and finds that in silico methods have limited utility for predicting these effects.

This paper shows that the ATP7B variant c.1934T>G causes exon 6 skipping, leading to loss of function and confirming its pathogenicity in Wilson Disease.

This study develops quantitative metrics and simulated datasets to evaluate subclonal reconstruction methods in tumours.

COSSMO predicts competitive alternative splice site selection using deep learning, achieving 70% accuracy in identifying the most used splice site and 60% R2 in modeling PSI distribution.

This paper introduces PhyloWGS, a method for subclonal reconstruction from whole genome sequencing data, showing it can accurately recover subclonal composition, genotype, and phylogeny using both SSMs and CNVs.