I am a computational biologist and data scientist with nearly two decades of experience using genomic data to inform drug discovery, target identification, target validation, and model selection.
I’ve worked on a wide range of diseases including cancer, cardiovascular disease and rare diseases. Most recently, I founded Diamond Age Data Science, a bioinformatics startup that offers both strategic and analytical services to innovative biotech and small pharmaceutical companies in the Boston area.
My past work includes:
- Bulk and single-cell RNA-Seq analysis (including QC/Normalization, differential expression and pathway analysis) for compound mechanism-of-action studies, discovery biology, and biomarker discovery
- Data analysis for functional assays and dropout screens (e.g., Project Achilles)
- Analysis of large public datasets including GTEx, CCLE, TCGA, ExAC, COSMIC, LINCs/CMAP, and GEO
- Use of survival modeling to assess the impact of clinical data and genetic variants on severity of rare disease
- Data visualization, including building interactive tools for exploring large datasets or the results of a complex analysis
Skills include:
- Programming: R (8 years’ experience), Java (7 years)
- Machine learning: clustering, classification, cross-validation
- Statistics: survival modeling, feature selection, enrichment, marker detection
- Cloud computing: running analyses in EC2/S3 using AWS api
- Informatics: evaluation of data storage needs for lab experiments; user experience assessment for information systems
- Reproducible research: systematic use of self-documenting Rmarkdown to produce analysis reports that can be re-created later
In addition to my scientific work, I have a passion for mentoring at all levels, from high school through PhD and up.
The best way to reach me is through Diamond Age. You can do that here.