Professional Experience
Quantitative systems biologist, model simulation and drug discovery
As Graduate Research Assistant
University of Notre Dame
Dec 2019 – Current
-
Integrated quantitative systems pharmacology (QSP) and model-informed drug development (MIDD) modeling software for mechanistic modeling of oncology resulting in 2 collaborations.
-
Explored multimodal single-cell omics cancer data with the Seurat and ScanPy genomics toolkits resulting in attainment of 3 bioinformatics analysis approaches in oncology and disease biology.
-
Responsible for collaborative relationship building by leading 4 cross-functional teams spanning drug discovery, machine learning, computational biology, simulation, and mathematical modeling.
-
Developed a Gaussian process surrogate model (PyTorch) for prediction and simulation of therapeutic viability of 1,498 compounds to 172 kinase targets for cancer research.
-
Implemented 2 machine learning approaches for de novo therapeutic design as a scientific approach for identification and simulation of new therapeutics using generative models.
-
Utilized machine learning, mathematical modeling, and cloud computing for rapid simulation and data classification of 4 unique calcium signatures in developmental biology.
-
Operated mechanistic modeling tools to discover 2 distinct cell populations in developing epithelial tissue via simulation and analytic techniques.
Computational biologist, data management and data science
As Graduate Research Assistant
University of Notre Dame
Jul 2018 – Dec 2019
-
Participated in cross-function teams to collaborate with other scientists that led to development of a cloud computing project to manage datasets consisting of 13,324 images.
-
Executed innovation in data democratization as demonstrated by generating 2 open-source repositories for biotechnology software (simulation and biostatistics) for non-technical users.
-
Performed in vivo gene expression of 425 human disease related genes in Drosophila Melanogaster.
-
Spearheaded design and innovation of a more efficient coverslip plating protocol for in vivo calcium signaling imaging that increased throughput by a factor of 2.
-
Deployed bioinformatics, data processing, and data science methods for analysis of phenomic datasets to identify 4 lead therapeutic candidates using Python and MATLAB.