I work on integrative cross-species data analysis and explainability of deep learning models in genomics.
I am primarily trained as a computational scientist. During my Ph.D., I worked on the developing probabilistic machine learning methodologies for various computational problems in engineering systems (uncertainty quantification, stochastic partial differential equations, dynamical systems, inverse problems etc.). As a postdoc, I worked on the problems pertaining to the interpretability of sequence-function relationships learned by DNN models from high-throughput sequencing functional assay datasets. As a computational scientist at JAX, I work on integration of cross-species and multi-omics data.