Ellen D. Zhong
Department of Computer Science
Email: zhonge [at] princeton.edu
Office: Computer Science 314
Lab website: E.Z. Lab
Ellen Zhong is an Assistant Professor of Computer Science at Princeton University.
She is interested in problems at the intersection of AI and biology. Her research develops machine learning methods for computational and structural biology problems with a focus on protein structure determination with cryo-electron microscopy (cryo-EM).
She received her Ph.D. from MIT in 2022, advised by Bonnie Berger and Joey Davis,
where she developed deep learning algorithms for 3D reconstruction of dynamic
protein structures from cryo-EM images. She has interned with John Jumper and
Team at DeepMind
and previously worked on molecular dynamics algorithms
and infrastructure for drug discovery at
D. E. Shaw Research.
She obtained her B.S. from the University of Virginia where she worked with Michael Shirts on computational methods for studying protein folding.
For more information about her research and group, please visit her lab website: https://ezlab.princeton.edu/.
Department of Computer Science, Princeton University
Principal Investigator, E.Z. Lab
Co-affiliated faculty: Quantitative and Computational Biology Graduate Program, Bioengineering Initiative
July 2022 - Present
Research Scientist Intern
AlphaFold team, DeepMind
Host: John Jumper
Machine learning for protein structure prediction
May - Sept 2021
Graduate Student Researcher
MIT Computer Science and Artificial Intelligence Lab, Computational and Systems Biology Ph.D. Program
Advisors: Bonnie Berger (Math, EECS), Joey Davis (Biology)
Thesis: Machine learning for reconstructing dynamic protein
structures from cryo-EM images
Sept 2017 - May 2022
D. E. Shaw Research
Methods for estimating protein-ligand binding free energies
July 2014 - Sept 2017
Undergraduate Student Researcher
University of Virginia, Chemical Engineering
Advisor: Michael Shirts (ChemE)
Thesis: Thermodynamics of protein folding from Hamiltonian Monte Carlo simulations
Fall 2011 - Spring 2014
For more details, see Ellen's full CV.
See here for a full list of publications.
Latent space diffusion models of cryo-EM structures.
Karsten Kreis*, Tim Dockhorn*, Zihao Li, Ellen D. Zhong. (*Equal contribution)
Machine Learning for Structural Biology Workshop at NeurIPS, 2022. (Oral)
Amortized inference for heterogeneous reconstruction in cryo-EM.
Axel Levy, Gordon Wetzstein, Julien Martel, Frederic Poitevin, Ellen D. Zhong.
Neural Information Processing Systems (NeurIPS), 2022.
Deep Generative Modeling for Volume Reconstruction in Cryo-EM
Claire Donnat, Axel Levy, Fred Poitevin, Ellen D. Zhong, Nina Miolane
Journal of Structural Biology, 2022.
Uncovering structural ensembles from single-particle cryo-EM data using cryoDRGN
Kinman LF*, Powell BM*, Zhong ED*#, Berger B#, Davis JH# (*co-first, #co-corresponding)
Nature Protocols, 2022.
Machine Learning for Reconstructing Dynamic Protein Structures from Cryo-EM Images
Ellen D. Zhong
Ph.D. dissertation, 2022.
CryoDRGN2: Ab Initio Neural Reconstruction of 3D Protein Structures From Real Cryo-EM Images
Ellen D. Zhong, Adam Lerer, Joey Davis, and Bonnie Berger.
International Conference on Computer Vision (ICCV), 2021.
CryoDRGN: reconstruction of heterogeneous cryo-EM structures using neural networks
Ellen D. Zhong, Tristan Bepler, Bonnie Berger, and Joey Davis.
Nature Methods, February 2021.
Learning the language of viral evolution and escape
Brian Hie, Ellen D. Zhong, Bonnie Berger, and Bryan Bryson.
Science, January 2021.
2020 and earlier
Exploring generative atomic models in cryo-EM reconstruction
Ellen D. Zhong, Adam Lerer, Joey Davis, and Bonnie Berger
Machine Learning in Structural Biology Workshop at NeurIPS, December 2020.
Learning mutational semantics
Brian Hie, Ellen D. Zhong, Bryan Bryson, and Bonnie Berger.
Neural Information Processing Systems (NeurIPS), December 2020.
Structures of radial spokes and associated complexes important for ciliary motility
Miao Gui, Meisheng Ma, Erica Sze-Tu, Xiangli Wang, Fujiet Koh, Ellen D. Zhong, Bonnie Berger, Joseph H.
K. Dutcher, Rui Zhang, and Alan Brown.
Nature Structural and Molecular Biology, December 2020.
RNA timestamps identify the age of single molecules in RNA sequencing
Sam Rodriques, Linlin Chen, Sonya Liu, Ellen D. Zhong, Joe Scherrer, Ed Boyden, and Fei Chen.
Nature Biotechnology, October 2020.
Reconstructing continuous distributions of 3D protein structure from cryo-EM images
Ellen D. Zhong, Tristan Bepler, Joey Davis, and Bonnie Berger.
International Conference on Learning Representations (ICLR), May 2020.
Spotlight Presentation at ICLR.
CryoDRGN (Deep Reconstructing Generative Networks) is a state-of-the-art machine learning system for 3D reconstruction of dynamic protein structures from cryo-EM data, developed and maintained by Ellen, her collaborators and research group. CryoDRGN is released as an open-source tool on Github:
For more information, see her group's software
Ellen is a co-organizer for the Machine Learning for Structural Biology Workshop
, held at
NeurIPS. The MLSB workshop website can be found here:
- Oct 2023: Keynote, CryoNet, Stockholm, Sweden
- Aug 2023: International Congress on Industrial and Applied Mathematics, Tokyo, Japan
- July 2023: American Crystallography Association Annual Meeting, Baltimore, MD
- July 2023: Symposium on Geometry Processing, Genoa, Italy
- June 2023: EMBL Heidelberg, Heidelberg, Germany
- June 2023: Google Research, Virtual
- June 2023: Poster at 3DEM Gordon Research Conference, Newry, ME
- June 2023: Flatiron Institute workshop on Cryo-EM methods, New York, NY
- May 2023: University of Pennsylvania Structural Biology Symposium, Philadelphia, PA
- May 2023: Princeton Catalysis Intiative, Princeton, NJ
- May 2023: University of Michigan Cryo-EM Data Processing Workshop, Ann Arbor, MI
- May 2023: ICLR Neural Fields Across Fields Workshop, Kigali, Rwanda
- Apr 2023: UC Davis Department of Molecular and Cellular Biology, Davis, CA
- Apr 2023: Stanford SCIEN Seminar Series, Palo Alto, CA
- Apr 2023: Caltech AI4Science Seminar Series, Pasadena, CA
- Mar 2023: University of Washington Institute of Protein Design, Seattle, WA
- Mar 2023: North Atlantic Microscopy Society Annual Meeting, Princeton, NJ
- Mar 2023: Columbia Physiology and Cellular Biophysics, New York, NY
- Feb 2023: Biophysical Society Annual Meeting, San Diego, CA
- Jan 2023: Brigham Young University Department of Chemistry and Biochemistry, Provo, UT
- Dec 2022: MIT 6.S980 Machine Learning for Inverse Graphics guest lecture, Cambridge, MA
- Nov 2022: Institute of Pure and Applied Mathematics (IPAM) workshop, Los Angeles, CA
- Nov 2022: Cold Springs Harbor Laboratory, Course on Cryo-EM, Long Island, NY
- Nov 2022: Flatiron Institute Workshop on Sampling, Diffusion, and Transport, New York, NY
- Nov 2022: Chan Zuckerberg Imaging Institute, Frontiers in Cryo-Electron Tomography, San Francisco, CA
- Oct 2022: Yale Department of Statistics and Data Science, New Haven, CT
- Oct 2022: Keynote, MIT Molecule Machine Learning Conference, Cambridge, MA
- Oct 2022: Purdue Department of Computer Science, Virtual
- Oct 2022: Rutgers Institute for Quantitative Biomedicine and RCSB Protein Data Bank, Virtual
- Sept 2022: Nature Conferences, Frontiers in Electron Microscopy for Physical and Life Sciences, Princeton, NJ
- Sept 2022: Van Andel Institute, Virtual
- Aug 2022: Microscopy & Microanalysis, Portland, OR
- Jun 2022: CVPR, Neural Fields in Computer Vision Tutorial, New Orleans, LA
- Apr 2022: ICLR Deep Generative Models for Highly Structured Data Workshop, Virtual
- Apr 2022: VIB-VUB Center of Structural Biology, Virtual
- Apr 2022: CCP-EM/CCPBioSim Cryo-EM Dynamics Discussion Meeting, Virtual
- Mar 2022: Vienna Biocenter IMBA/IMP Young Investigator Symposium, Virtual
- Mar 2022:Society for Industrial and Applied Mathematics (SIAM) Conference on Imaging Science, Cryo-EM
- Mar 2022: SLAC/Stanford University, Palo Alto, CA
- Mar 2022: John Hopkins University Cryo-EM Seminar Series, Virtual
- Mar 2022: Brookhaven National Lab Applied Mathematics Seminar Series, Virtual
- Mar 2022: International Conference on Image Analysis in Three-dimensional Cryo-EM, Lake Tahoe, CA
- Mar 2022: OpenEye CUP Conference, Santa Fe, NM
- Feb 2022: Princeton Department of Computer Science, Princeton, NJ
- Feb 2022: Columbia Department of Computer Science, Virtual
- Nov 2021: MRC Laboratory of Molecular Biology, Cambridge, UK
- Nov 2021: The Francis Crick Institute, London, UK
- Oct 2021: Introductory remarks and discussion leader: Gordon Research Conference, Visualizing Biological
Complexity Across Scales, Waterville Valley, NH
Cryo-EM and AlphaFold in translational research
- Nov 2021: Microsoft Research New England, Virtual
- Sept 2021: Scientific Computing in Structural Biology Workshop, Stanford SLAC Users Meeting, Virtual
- Aug 2021: RosettaCon, Virtual
- Aug 2021: American Crystallographic Association Annual Meeting, Virtual
- Apr 2021: CCP-EM Spring Symposium, Virtual
- Apr 2021: GlaxoSmithKline (GSK), Virtual
- Feb 2021: Princeton University Applied Mathematics IDeAS Seminar, Virtual
- Feb 2021: UIUC Coordinated Science Laboratory Student Conference (CSLSC), Virtual
2020 and earlier:
- Nov 2020: Vienna BioCenter, Research Institute of Molecular Pathology (IMP) Seminar Series, Virtual
- Sept 2020: SciLifeLab Advanced Cryo-EM Seminar Series, Virtual
- Aug 2020: Microscopy & Microanalysis, Virtual
- May 2020: SBGrid Annual Symposium, Virtual
- Feb 2020: Relay therapeutics, Cambridge, MA
- Dec 2019: Machine learning in Computational Biology (MLCB) meeting, Vancouver, BC
- Dec 2019: Poster: NeurIPS Learning Meaningful Representations of Life (LMRL) workshop, Vancouver, BC
- Dec 2019: Harvard Cryo-EM Club, Cambridge, MA
- Nov 2019: Poster: Janelia Women in Computational Biology Meeting, Ashburn, VA
- Oct 2019: New England CryoEM symposium, Worchester, MA
- Aug 2019: Poster: Flatiron Institute Computational Cryo-EM Workshop, New York, NY
- Nov 2015: Out in STEM National Conference, Pittsburgh, PA
From silicon to medicine: Core challenges of
using molecular dynamics for early-stage drug discovery.
- Oct 2015: Grace Hopper Annual Conference, Houston, TX
Optimizing molecular visualization for drug
- Nov 2013: AIChE Annual Meeting, San Francisco, CA
Efficient simulation of protein stability on surfaces
using a Hamiltonian Monte Carlo approach.
Last updated May 2023.