About Me
I am a Bioinformatics Scientist (II) at Somalogic in the Production Bioinformatics group. My work is focused on full stack development of a data analytics pipeline to enable statistical process control of the SomaScan Assay. Applications include:
- ML-based anomaly detection of highly dimensional data with lead generation utilizing graph networks of process and material data followed by downstream impact analysis
- Scalable quality reporting powered by seamless traversal between abstractions of data from experiment summary statistics to individual SOMAmer stability
- Creation of proteomic data lakes wherein data provenance is fully maintained for model development in R and neural network training
The tech stack includes:
- Python with heavy utilization of the data science libraries
- Django with Django Rest Framework
- Celery and RabbitMQ
- Docker
- Kubernetes
- AWS
- PostgreSQL
- Neo4j
- Node.js
- D3.js and Plotly.js
- Vue.js with Bootstrap
Before SomaLogic I received my PhD from Colorado State University (CSU) with Dr. Anthony Rappé in computational chemistry where I developed and applied methodologies to elicit enthalpic global minima and reaction pathways. This work was primarily programmed in Fortran 66 and executed on the CRAY at CSU.
I then acquired a bioinformatics post-doctoral position in the Microbiology, Immunology, and Pathology Department with Dr. Mark Stenglein where I focused on the development of metagenomic analysis tools as well as supporting the NGS Core Facility at CSU.
In my spare time I moonlight as an iOS app developer with my father where we have created an organic chemistry reference app called TapOChem. I like to think of it as the best one out there but that might just be my bias talking.