Building and managing a cross-disciplinary research group of computational scientists that brings powerful techniques associated with AI/ML/Statistics, Systems Biology, and Omics Data Science to create reverse translational solutions for target identification and biomarker discovery, significantly contributing to the understanding of complex biological processes, facilitate new treatments and cures, and improve public health outcomes

Led multiple data science projects providing end-to-end bioinformatics and biostatistics support across all stages of biomarker discovery and development including assay quality control, drafting SAP, and performing statistical analyses

Supported Merck’s internal efforts in the single-cell and spatial transcriptomics initiatives for translational oncology studies

Liaised with digital pathology scientists and bioinformaticians on crucial statistical analyses for both exploratory and clinical development purposes

Employed machine learning classification to the discovery of clinically actionable biomarkers from integrated multi-omics profiles to enable better disease outcome prediction and patient stratification

Secured funding to initiate and execute multiple academic collaborations to conduct research on various 5-year strategic initiatives specified by the organization

Successfully hired and co-mentored four Ph.D. summer interns towards the development and implementation of sophisticated statistical and AI/ML approaches for enabling personalized medicine

Published research across several disease areas (infectious diseases, oncology, and microbiology) that utilized innovative statistical methodology and systems biology techniques spanning a wide range of translational applications

Lead developer of MaAsLin 2, a R/Bioconductor package for associating microbial multi-omic data with arbitrarily complex clinical metadata (>10K official downloads)

Lead developer of MelonnPan, a computational method to predict metabolite profiles from metagenomic sequencing data using concepts from machine learning and ecology, implemented in R (>100 citations)

Contributed to grant writing, manuscript preparation, interdisciplinary collaborations, and teaching and mentoring of graduate and undergraduate students and trainees

Developed Bayesian adaptive trial designs for clinical trials utilizing surrogate endpoints in the presence of biomarkers

Developed novel Bayesian methods to conduct heterogeneity of treatment effect (HTE) analyses in phase III clinical trials

Developed methods for detecting maternal-fetal gene-gene interactions associated with obstructive heart defects in newborns from mother-offspring paired genetic data

Developed Bayesian machine learning methods for high-dimensional feature selection in personalized medicine applications

Developed and validated risk prediction models for assessing short-term mortality in obese adults

Conducted high-dimensional predictive modeling of zero-inflated count phenotypes to identify genetic susceptibility markers in Rheumatoid Arthritis patients

Performed research on non-linear statistical modeling of cross-sectional growth curve data by the Preece-Baines growth model