Projects

SEAM (Systematic Explanation of Attribution-based Mechanisms) is a Python suite to interpret sequence-based deep learning models for regulatory genomics data. SEAM systematically mutates sequences and clusters their attribution maps to reveal diverse regulatory mechanisms and genomic background effects that shape DNN behavior in local regions of sequence space.

SQUID (Surrogate Quantitative Interpretability for Deepnets) is a Python suite to interpret sequence-based deep learning models for regulatory genomics data with domain-specific surrogate models. This software was developed in the Kinney lab and Koo lab at Cold Spring Harbor Laboratory.

Public release of ManifoldEM Python suite (Beta version) for determination of conformational continua of biomolecules from single-particle cryo-EM data. This software was developed in the Frank research group at Columbia University in collaboration with members from UWM.

Georgia Institute of Technology MOOC (massive online open courses) for introductory Physics education. I served as Creative Director on this project for the Department of Physics under advisement of Dr. Michael Schatz to oversee design and animation of educational content ranging from Introductory Mechanics to Electromagnetism.

An animated segment I created for Dr. Jennifer Aaker detailing her research in Social Psychology with colleagues at Stanford University on happiness and purpose. This work was featured at the 2015 Future of Storytelling Summit in New York City.

An animated segment I created for Dr. Jennifer Aaker detailing her research in Social Psychology with colleagues at Stanford University on persuasion and the power of story. This work was featured at the 2013 Future of Storytelling Summit in New York City.