Frequently Asked Questions

This platform is designed to accelerate biological research by providing biologists and machine learning researchers with easy access to curated AI models and the datasets they were built on. Developed by CZI, our AI residents, collaborators, and the wider scientific community, the initial set of models included here focuses on simplifying complex tasks in subcellular imaging and single-cell transcriptomics. Researchers can see how to use these models by running our hosted tutorials, which demonstrate applications such as predicting protein localization, annotating cell types, and integrating multiple batches of data. Furthermore, the platform provides centralized access to ML-ready datasets in imaging and transcriptomics, enabling researchers to more easily train, fine-tune, test, and evaluate models with minimal data preparation.

Researchers can register by visiting the platform website and clicking on the "Register" button in the top right corner of the screen or by following this link. To create your account, we'll ask for some basic information, including your name, email address, and organization affiliation. We also have a few quick questions to help us better understand our users and their research needs.

To ensure that our platform is used to support the scientific community and foster collaboration among researchers, we require all users to have an email address associated with a recognized research institution. Research Organization Registry (ROR) is a global database of research organizations that we use to streamline the registration process and verify affiliations. If your organization is listed in ROR, your account will be created automatically, with some exceptions.

No problem! If your organization isn't listed, you can still register by manually entering your organization’s information. Our team will then review your registration to confirm your affiliation with the scientific community. You'll receive an email notification once your registration is approved.

The platform provides easy access for researchers to an initial set of models in the scientific domains of subcellular imaging and single-cell transcriptomics, built by CZI, our AI residents, collaborators, and the wider scientific community. Researchers can use these initial models to simplify time-consuming and complex biological tasks, such as predicting protein localization, annotating cell types, and integrating multiple batches of data. You can browse the available models and datasets through the platform's Model and Dataset Collection pages.

We've created helpful resources to get you started with the models. Those with accounts can head over to the model cards to find tutorials and quick start guides that provide clear instructions and real-world examples. You'll be up and running in no time!

You can access datasets through links to existing external data repositories or through AWS S3 on each datacard. For some datasets, processed data or data processing scripts are also available for download for those with accounts, making it easier to train and validate your own models.

Yes, you can suggest your own models and datasets for consideration to be included on the platform. This allows you to share your work with a broader audience and receive valuable feedback from the scientific community. Please use the provided model or dataset feedback form and follow the outlined guidelines for model and dataset submissions. We are currently prioritizing models and datasets that support imaging and transcriptomic research, but we are also interested in models and datasets in other research domains.

We encourage you to share feedback on the platform and its resources through the provided feedback form. Your input is valuable in helping us improve the platform and its offerings. If the provided forms do not capture all of your feedback, you can also reach out to our team at virtualcellmodels@chanzuckerberg.com.

If you encounter any issues or have specific questions, you can contact our support team at virtualcellmodels@chanzuckerberg.com or submit a bug report or feature request using this form. Your responses will be collected and processed in accordance with our privacy policy. Should you have any security or privacy issues, please reach out to our teams at security@chanzuckerberg.com or privacy@chanzuckerberg.com, respectively.

Yes, we use cookies and similar technologies to help improve the website, personalize content, and provide a better experience while using the platform. View our cookie policy for more information: cookie policy.