Spearheaded computational biology division and led a team to support Cardiometabolic Disease Department (CMD) for portfolio and pipeline development. Oversaw end-to-end development of AI/ML approaches to support data analysis, target identification and validation in therapeutical areas of heart failure, MASH, obesity, inflammation, fibrosis, retinal disease, renal disease, vascular disease.• Acted as a key member of CMD Leadership Team (LT), contributing to strategic planning by providing actionable, data-driven insights. Proposed multiple strategic reviews that led to new initiatives: harnessing multi-omics technology to propel biological understanding; leveraging real-world evidence (RWE) to strengthen biomarker discovery; empowering human data by introducing >100 public human data in house.• Generated insightful biological outcome for multiple programs in different phases of drug discovery, ranging from POC to clinical trial.• Accelerated target identification and drove biomarker discovery by leveraging multi-omics approaches in obesity (RNAseq, scRNAseq, Proteomics, UKB), retinal disease (RNAseq, EyeIntegration), MASH (lipidomics), IPF (cell surface biomarker).• Enhanced research capabilities by introducing and evaluating new technology (single cell HT/standard/LT, single nuclear, spatial transcriptomic), with discoveries help to standardize protocols across organization. • Oversaw computational related project portfolio, ensuring analysis activities are properly prioritized to align with organization goal. Responsible for resources allocation, budget management and delivery expedition (significantly reduced delivery time to 2 weeks in average).• Fostered biopharma ecosystem in Bay Area and led several Scientific Engagement and Emerging Discovery Science (SEEDS) programs with Stanford University, UCSF, UC Berkeley, which led to target/biomarker/animal model implemented in house to hasten scientific discoveries.

Computational Biology Lead for Comparative Biology and Safety Sciences (CBSS) department, drove various pipeline development and safety related issue resolution in the therapeutic areas of oncology, cardiometabolic disease, inflammation, neuroscience.• Solely responsible for executing toxicogenomics assay, generated actionable insights to investigate drug induced toxicity for both GLP and non GLP studies, streamlined the process and reduced delivery to 2 weeks.• Established a novel somatic structure variants analysis pipeline, which was applied in house for genome instability test to support carcinogenesis risk assessment.• Engaged in FDA CiPA initiative, evaluated multiple in silico cardiac action potential models, implemented the selected model internally to assess pro-arrhythmic risk and addressed regulatory concerns.• Built internal translational and predictive safety knowledgebase, single-handed led the successful integration of multiple data sources including historical ~3M FAERS report, millions of drug-target-downstream interactions, and >800 drug 2D descriptors.• Developed a compound attributes based in silico model for prediction of DILI, which resulted in a publication and in-house practice to complement in vitro/in vivo models.• Collaborated with UCSF Immunoprofiler, specifically contributed to immune-phenotyping image analysis and spatial statistics.

Specialized in cancer genomics; designed and built multiple mathematical models independently, applied them to identify driver mutations/genes/pathways in various types of cancer; published multiple high impact journal papers. • Developed algorithms to identify driver pathway collaborations in breast cancer by using NGS mutation data.• Identified and ranked plausible drivers in TCGA pan-cancer by evaluating and integrating current cancer gene methodologies.• Discovered different mechanisms of breast cancer therapy and suggested optimized drug option by analyzing driver mutations/genes/pathways.• Identified pathway crosstalk based on a functional linkage network with VisANT integration.• Designed algorithms to identify cancer driver modules in a functional linkage network by using gene expression and mutation data.

- Integrated pathway enrichment analysis based on both GWAS and gene expression data.