- Course overview
- Search within this course
- An introductory guide to AlphaFold’s strengths and limitations
- Validation and impact
- Inputs and outputs
- Accessing and predicting protein structures with AlphaFold 2
- Choosing how to access AlphaFold2
- Accessing predicted protein structures in the AlphaFold Database
- Predicting protein structures with ColabFold and AlphaFold2 Colab
- Predicting protein structures using the AlphaFold2 open-source code
- Other ways to access predicted protein structures
- How to cite AlphaFold
- Advanced modelling and applications of predicted protein structures
- Classifying the effects of missense variants using AlphaMissense
- Summary
- Course slides
- Your feedback
- Glossary of terms
- Acknowledgements
AlphaFold 3 and AlphaFold Server
AlphaFold 3 is a new version of AlphaFold. It has additional capabilities, especially the ability to predict the structures of complexes containing multiple non-protein molecules (e.g. DNA, RNA, ligands). For non-commercial projects, AlphaFold 3 is available as a service via AlphaFold Server and as source code via the AlphaFold 3 GitHub repository.
This section assumes familiarity with AlphaFold 2. This includes an understanding of the confidence scores, strengths, and limitations, as well as a grasp of the underlying technology. For those new to AlphaFold, it is highly recommended to read the first section, “What is AlphaFold?” as it covers essential principles that are foundational to understanding both AlphaFold 2 and AlphaFold 3.
By the end of this section you will be able to:
- Understand what AlphaFold 3 can and can’t do.
- Determine whether to use AlphaFold 2 or AlphaFold 3 to help with your research questions.
- Generate AlphaFold 3 structure predictions using AlphaFold Server for non-commercial projects.
- Interpret the structure predictions provided by AlphaFold 3.