Pramod Bharadwaj Chandrashekar

CellTRIP uses multi-agent reinforcement learning to infer dynamic virtual cell environments from single-cell gene expression data, enabling simulation and prediction of cell interactions and changes over time and space.

DeepCORE identifies co-operative regulatory elements by modeling genetic, epigenetic, and transcriptional patterns across 25 cell lines, outperforming existing methods and providing interpretable insights.

DeepGAMI improves phenotype prediction from multimodal data by integrating biological knowledge and imputing missing modalities, outperforming existing methods and providing interpretable insights.

TreeMap identifies causal eQTL variants by accounting for multisite effects and linkage, showing improved accuracy and enabling genome-wide analysis of long-range eQTL.

This study introduces a computational method to classify cancer driver genes as oncogenes or tumor suppressors based on mutation patterns across 33 cancer types, identifying novel genes and revealing context-specific functions.