I'm working in Prof. I. King Jordan's lab where we study the impact of genetic ancestry on complex health phenotypes in genetically diverse populations. Brief description of my recently completed projects:Genetic ancestry inference in the All of Us research program• Lead developer of the featured demonstration workspace “Genetic Ancestry Inference” hosting reproducible jupyter notebooks in the cloud-based researcher workbench• Inferred & visualized continuous genetic ancestry for over 300k participants using unsupervised and supervised clustering algorithmsBiobank scale analysis• Compiled >100 million electronic health records from >250k individuals into case-control cohort to characterize the landscape of health disparity in the US• Performed phasing & annotation of sequencing data followed by implementation of a fast HAIL pipeline to characterize compound heterozygosity in the UK Biobank WES (>100k) & clinical WGS data (>3k)• Established that self-identified race & ethnicity carries clinically actionable pharmacogenomic information in the UK & US using a suite of machine learning models (random forests, SVM)• Developed a genetic data harmonization pipeline which performs quality control, harmonizes, and merges genotyping & sequencing data from >15 clinical labs

• Identified 9 novel & refined existing ancestral group definitions in the HLA haplotype data from themarrow donor registry containing >1 million individuals• Aimed at improving marrow donor matching accuracy for individuals belonging to minority groups such as Afro-Hispanics & Ashkenazi Jews

I worked at the Genomics Research for Health Equity lab at NIMHD (NIH) through ASRT, Inc. Summary of my work:• Identified health disparities between ethnic groups in the UK and investigated the role of genetic ancestry and socio-economic deprivation in disparate biomarker levels between ethnic groups• Performed association testing between ancestral haplotypes and disparate biomarkers among ethnic groups• Worked on merging, harmonization, and continental & local ancestry inference for several public and clinical WGG & WGS datasets

• Worked on finding the effects of aberrant alternative splicing and mutations existing on messenger-RNAs that can change the regulatory control mechanism of gene expression carried out by micro-RNAs in cancer.

• Served as a Graduate Teaching Assistant for a core bioinformatics graduate level class "Programming for Bioinformatics" (BIOL7200).• Responsible for guiding students during the class, designing and grading assignments, weekly office hours and technology support.

• Performed Variant Calling to ensure the integrity of therapeutic protein producing cell lines sequenced through NGS Amplicon sequencing and RNA-Seq.• Implemented a “One-Key” Variant Calling Pipeline to confidently determine SNVs, InDels, and Fusion Proteins from the wet lab generated NGS Amplicon & RNA-Seq data.

• Integrated overlapping data from popular large-scale public databases to create a one-click link between micro-RNAs, Target Genes, messenger-RNAs, and Biological Pathways.• Created miRDex [www.mirdex.org], a Web Application for micro-RNA - gene; pathway - gene - micro-RNA; and Gene - Pathway; interaction network visualization with additional user-end file support for Cytoscape (Software).• Used Deep Neural Network based Auto-Encoders and Self-Organizing maps for clustering of micro-RNA - Gene - Pathway datasets.

• Developed and deployed university-wide large-scale official web portal for Training & Placement Cell to facilitate the interaction between recruiting companies, students and the university.• A self-initiative project which had features such as: email, text message, and web-based notification system; resume management; news feed; online application to jobs.• Trained and mentored a team of juniors and sophomores in web-development as part of T&Pclub.