Biomedical Engineer turned Statistician / Data Scientist
Master of Science in Statistical Science (Duke University)
Expertise in Data Science, Applied Bayesian Statistics, Machine Learning and Deep Learning in Healthcare
Experience with Distributed/Cloud Computing, MLOps, ML/AI Algorithms (e.g., Decision Trees / Forests, SVM, Neural Networks, Hierarchical Models,
Bayesian Inference, Multi-armed Bandits), Agile Product Development, Go-to-Market Strategy, and more
Here's a couple of projects I've worked on recently, ranging from
Advanced Stochastic Modeling to Machine Learning and Neural Networks
(click on images to see)
Obtained my M.S. in Statistical Science from Duke University, and here's a bit of what I've done over the last 5+ years
Taught introductory statistics and statistical computing courses to undergraduates and graduates
(STA 101, STA 110, STA 523)
Created computer vision course materials for an Advanced Data Analytics and Applications course at the Fuqua School of Business
Collaborated with team to analyze and synthesize historical customer data via a clustering algorithm to provide client with customer-segmentation recommendations
Developed a ML algorithm in R with a Python wrapper to enhanced the classification capabilities of a financial fraud detection tool
Co-led the successful launch of Galileo AMR , an antimicrobial resistance detection and classification software
Personally built and co-designed the company’s first BizOps infrastructure & web-store within a tight deadline (two months) linking over four sales/marketing platforms
Created and managed product requirements for
Galileo Virome , a genomics infectious disease diagnostic based on market research and KOL interviews
Actively worked with bi-coastal development team to ensure the product met customer, medical, and regulatory needs
Developed Python scripts to showcase core technology’s value to classify antimicrobrial DNA, prompting leadership to strategically shift outside the initial cancer target market
Integrated and automated the company’s first product which streamlined four data analysis algorithms in C++, R, and Python to analyze a whole Human genome (>600 Gb) in less than 1.5 days
Built a Python-based modular algorithm capable of comparing over 100,000 of genetic predictions via partial alignments across the Human genome in less than 1.5 hours
Developed Python scripts to tune a proprietary machine learning model's parameters via ROC curves to ensure greater than 95% precision in predictions
Automated data collection and tidying processes of 1000s of genomic records (file sizes >50Gb) with workflows in a high performance computing environment to generate train/test sets 5x faster
for an ML algorithm
Developed a predictive model in MATLAB to classify novel protein-encoding regions (95% C.I.) in the Human genome
Co-led a student-run program that helped develop over 20 early-stage ideas feasible prototypes, some of which were successfully funded by larger incubator programs such as MassChallenge
Relevant courses -
Predictive and Hierarchical Modeling,
Advanced Stochastic Modeling, Machine Learning, Probabilistic Machine Learning, Statistical Computation, Bayesian and Modern Statistics, High Dimensional Data Analysis
Relevant courses -
Signals and Systems, Control Systems,
Molecular Bioengineering, Systems Biology of Disease, Systems Physiology, Product Innovation & Design, Business Innovation, Nanomaterials/-technology, Nanomedicine
Quiroz Zárate, Alejandro. Olivares-Amaya, Roberto.
Watson Jr., Thomas J. van Aggelen, Helen C.
Coronado Sroka, Eduardo. Angulo Sermeño, Carlos A. Fimbres Jurado, Fernando. Solis Garcia-Inda, Abraham. Fontove Herrera, Fernando. 2016. Systems and methods for genomic analysis.
Competed and won the 2020 Big Data Health Science Case Competition hosted by the University of South Carolina. Our team developed an analytic tool focused on mitigating the human and financial cost of chemical spill related accidents
