Projects

CryoLens is a 3D variational autoencoder for learning interpretable representations of cellular structures from cryo-electron tomography data (available on the CZI Virtual Cell Platform). The model learns compressed representations of 3D subtomograms that capture structural variation in an interpretable latent space—useful for visualization, classification, and understanding structural diversity. Trained on a large synthetic dataset composed of 100+ diverse structures, CryoLens can produce high-fidelity single-angle 3D densities. Tools are available for napari and the Virtual Cell Platform.

Nov 5, 2025

The CZII CryoET Object Identification Challenge, hosted on Kaggle from November 2024 to February 2025, was a machine learning competition focused on automating the detection of protein complexes in cryo-electron tomography (cryoET) data. Published in Nature Methods (Peck et al., 2025), this competition addressed a critical bottleneck in structural biology research by developing algorithms to accurately identify and annotate multiple types of protein complexes in 3D tomographic volumes. More on the Kaggle page

Nov 6, 2024

CellCanvas is a software tool for creating and working with geometric models of cellular architectures.

Jan 6, 2024

copick is a cross-platform API for collaborative work on cryo-electron tomography datasets. It provides standardized access to tomograms, picks, and segmentations across different storage backends—whether your data is local, on S3, or from the CZ CryoET Data Portal. Built to support the CZII CryoET ML competition on Kaggle, copick enables you to write data handling code once and have it work across diverse storage systems. This makes it easier to share annotations and build ML pipelines that scale across distributed data sources. Code: github.com/copick/copick

Jan 1, 2024

napari is a Python viewer for multi-dimensional images. I joined CZI’s napari team in 2022, where I made code contributions and served as tech lead. I’ve been on napari’s steering council since 2023. napari has become central infrastructure in the scientific Python ecosystem for microscopy—used for everything from basic image visualization to interactive ML annotation workflows. My contributions have focused on large-data handling, ML integration, and helping coordinate the project’s technical direction.

Jul 1, 2022

Album is a software tool for sharing scientific code and software early in the development process. The goal is accelerating the iterative development of scientific software between developers and users. Check out the repository here.

Jul 8, 2020

SciView is an ImageJ/FIJI plugin for 3D visualization of images and meshes. It uses scenery as a rendering backend and supports rendering to VR headsets via OpenVR.

Jul 8, 2016

Brevis is an open-source platform for agent-based biological modeling and synthetic biology simulation. Built with Clojure, it enables researchers to design and test complex multi-agent biological systems with interactive 3D visualization.

Jan 28, 2013