- Course overview
- Search within this course
- An introductory guide to AlphaFold’s strengths and limitations
- Validation and impact
- Inputs and outputs
- Advanced modelling and applications of predicted protein structures
- Classifying the effects of missense variants using AlphaMissense
- AlphaFold 3 and AlphaFold Server
- Summary
- Course slides
- Your feedback
- Glossary of terms
- Acknowledgements
All materials are free cultural works licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) license, except where further licensing details are provided.
Accessing and predicting protein structures with AlphaFold 2
AlphaFold2 is a powerful tool for protein structure prediction. However, the best way to access it depends on your specific needs and resources. The main options are:
- Using the AlphaFold2 source code for protein structure prediction.
- A cloud-based approach via ColabFold.
- Accessing the free AlphaFold Protein Structure Database. Developed by Google DeepMind in collaboration with EMBL-EBI, it offers a user-friendly interface and over 200 million predicted protein structures.
- Using specialised software that incorporates AlphaFold algorithm and/or data.
By the end of this section you will be able to:
- Describe the key differences between using the AlphaFold source code, Google Colab notebooks or the AlphaFold Protein Structure Database to predict protein structures.
- Determine the best approach to using AlphaFold, based on your computational resources, coding experience and need for customisation.
- Recall the ways to access the pre-computed predictions from the AlphaFold Protein Structure Database.
- Identify other resources for accessing and predicting structures of proteins and macromolecules.