I'm an Assistant Professor of Genetics in the Computational Medicine Program and Lineberger Cancer Center
at the University of North Carolina - Chapel Hill.
I help run the Personalized Immunotherapy Research Lab at UNC where we work on T-cell epitope discovery, cancer genomics, machine learning for immunology, and making personalized cancer vaccines which actually do something useful.
Previously: researcher in Mount Sinai's OpenVax group and Hammer Lab.
I help run the Personalized Immunotherapy Research Lab at UNC where we work on T-cell epitope discovery, cancer genomics, machine learning for immunology, and making personalized cancer vaccines which actually do something useful.
Previously: researcher in Mount Sinai's OpenVax group and Hammer Lab.
Blogs
- Personalized Immunotherapy Research Lab
- My research lab at UNC Chapel Hill with posts about computational immunology, genomics, and machine learning
- OpenVax Blog
- Open source software for personalized cancer vaccines
- Hammer Lab Blog
- Former research lab: cancer genomics, immunotheray, machine learning, and bioinformatics
- explain my data
- Machine learning and data analysis
- φ-node
- My previous research life: translating programs into faster programs.
Writing & Presentations
-
Neoantigens beyond SNVs: embracing the full spectrum of antigenic dark matter in tumors
Presented at CIMT 2021 (May 12th, 2021) -
Precision vaccine design from cancer to SARS-CoV-2 and back
Presented at the Lineberger Cancer Center faculty lunch (September 14th, 2020) -
Personalized Cancer Vaccines: Literature Review
Written for Epivax Oncology (January 2018) -
Machine Learning for Personalized Cancer Vaccines
Presented at Data Science Salon - Miami (February 9th, 2018) -
Personalized Cancer Vaccines: History, Preclinical Evidence, and Ongoing Trials
Presented at Neoantigens & Cancer Immunotherapy Symposium (March 27th, 2017) -
Computational Tools for Cancer Neoantigens and Mount Sinai's Personalized Vaccine Trial
Presented at the University of Miami's Center for Computational Science (February 27th, 2017) -
Python Libraries for Deep Learning with Sequences
Video from PyData NYC 2015 -
Personalized Cancer Vaccine Pipeline (pdf)
Poster for Systems Biology of Cancer Therapeutics Symposium (October 27th, 2014) -
CudaTree: Training Random Forests on the GPU
GPU Technology Conference (March 25th, 2014) -
Python on the GPU with Parakeet
Slides for PyData NYC (November 10th, 2013) -
Parakeet: A Runtime Compiler for Numerical Python (pdf)
Slides for PyData Boston (July 27th, 2013) -
Programming Languages Recitation
Links and resources for a programming languages course (Fall 2011) - Resources for Learning OCaml (October 6th, 2011)
- Tips for Solving the Dating Game (or, a machine learning primer) (Nov. 12th, 2008)
- C++ Template Metaprogramming Insanity (Nov. 10th, 2007)
Clinical Trials
I helped start and run the PGV (personalized genomic vaccine) series of therapeutic cancer vaccine at Mount Sinai:- Safety and Immunogenicity of Personalized Genomic Vaccine to Treat Malignancies
- Safety and Immunogenicity of Personalized Genomic Vaccine and Tumor Treating Fields (TTFields) to Treat Glioblastoma
- Atezolizumab Given in Combination With a Personalized Vaccine in Patients With Urothelial Cancer
Art
- punch.card.collective
- Ongoing collaboration working on generative fiber arts and proto-computational pattern crafts
- Weave
- Early experiments in generating textile patterns and weaving drafts
Projects
- Vaxrank
- Computational prediction and ranking of synthetic long peptides for personalized therapeutic cancer vaccines
- Isovar
- Python library for determining mutant protein sequences from somatic variants and tumor RNA sequencing
- Topiary
- Python library and commandline tool for predicting cancer epitopes from mutation and RNA expression data
- MHCflurry
- Neural network Class I MHC binding predictors
- MHCdouble
- Convolutional neural network Class II MHC binding predictors
- MHCtools
- Python API which wraps messy commandline peptide-MHC binding tools like NetMHC
- PyEnsembl
- Python interface to the Ensembl gene annotation database
- Varcode
- Library for analyzing and inferring effects of genomic variants in Python
- PepData
- Python interface to immunology and bioinformatics datasets
- Parakeet
- An optimizing just-in-time compiler for an array-oriented subset of Python
- CudaTree
- GPU Random Forest library for Python
- GenePool
- A basic framework for implementing genetic algorithms in OCaml.
- ocaml_llvm
- A toy compiler for a mini-language implemented with OCaml and LLVM
- Falcon
- A faster register-based virtual machine for Python (primarily by Russell Power)
- TreeLearn
- Decision tree learning algorithms for Python.
- Yasper
- simple single-header reference counting smart pointer for C++
- Parsnip
- packrat parser combinator library for C++