CryoET Data Annotation Machine Learning Competition

Develop a ML model for annotating subcellular structures and proteins in CryoET data

Starts

Fall 2024

Prizes

$50k Total

About the Competition

Cryogenic Electron Tomography (CryoET) is an advanced imaging technique for visualizing cellular structures at near-atomic resolution. CryoET has led to significant scientific advances in our understanding of protein structure, cellular function, and disease. These insights come from analyzing annotated CryoET data where different parts of the cell and even individual proteins are segmented.

However, annotating CryoET data by hand is very time-consuming, taking weeks or months for a single dataset. In addition, particle picking, the annotation process of identifying particles of interest within tomograms, is challenging, especially for particles smaller than ribosomes since CryoET data has a low signal-to-noise ratio compared to other imaging modalities. Particle picking is generally done by template matching, which compares a predefined template to potential regions containing the particles of interest in the tomograms. Once particles are picked, they are aligned and averaged to reconstruct structures at near-atomic resolutions, providing insights into cellular mechanisms.

Our machine learning competition focuses on enhancing particle picking for a range of particle sizes through the development of machine learning models to generate semantic segmentation masks within 3D CryoET tomograms. The primary aim is to refine the template matching process by identifying areas of interest where template matching should be concentrated. This method narrows down the search space, thereby boosting the accuracy and efficiency of the CryoET computational workflow. Participants are tasked with crafting models that produce masks highlighting the precise locations for template matching, facilitating the identification of specific particles across various tomograms.

Competition Details

More info coming soon

How to Participate

More info coming soon

Competition Data

Competition Dataset:

Coming in Fall 2024

The competition dataset will be published on the Portal when the Competition starts Fall 2024.

In the meantime, you can explore other CryoET datasets in the Data Portal.

About CryoET Data

More info coming soon

Tutorials

Example notebooks for existing models, such as TomoTwin and DeepFinder, are provided to serve as onboarding materials and baseline solutions. These examples include preliminary results to set performance benchmarks for the competition.

Coming in Fall 2024

About the Organizers

Headshot of Bridget Carragher

Bridget Carragher

Chan Zuckerberg Imaging Institute (CZII)

Headshot of Anchi Cheng

Anchi Cheng

Chan Zuckerberg Imaging Institute (CZII)

Headshot of Utz Ermel

Utz Ermel

Chan Zuckerberg Imaging Institute (CZII)

Headshot of Kyle Harrington

Kyle Harrington

Chan Zuckerberg Imaging Institute (CZII)

Headshot of Reza Paraan

Reza Paraan

Chan Zuckerberg Imaging Institute (CZII)

Headshot of Jonathan Schwartz

Jonathan Schwartz

Chan Zuckerberg Imaging Institute (CZII)

Headshot of Daniel Serwas

Daniel Serwas

Chan Zuckerberg Imaging Institute (CZII)

Headshot of Hannah Siems

Hannah Siems

Chan Zuckerberg Imaging Institute (CZII)

Headshot of Yue Yu

Yue Yu

Chan Zuckerberg Imaging Institute (CZII)

Headshot of Kevin Zhao

Kevin Zhao

Chan Zuckerberg Imaging Institute (CZII)

Sponsored By:

Chan Zuckerberg Imaging Institute Logo
Chan Zuckerberg Imaging Program Logo

FAQ

More info coming soon

Contact

Have more questions? Reach out to Dannielle McCarthy at dmccarthy@chanzuckerberg.com