- Course overview
- Search within this course
- An introductory guide to AlphaFold’s strengths and limitations
- Validation and impact
- 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
- AlphaFold 3 and AlphaFold Server
- Summary
- Course slides
- Your feedback
- Glossary of terms
- References
- 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.
Evaluating AlphaFold2’s predicted structures using confidence scores
In order to hold practical significance, predicted protein structures must be accompanied by reliable measures of confidence. AlphaFold2 returns two confidence measures called pLDDT and PAE. These metrics can be used to identify regions of the predicted structure, and relative positions of different regions, that are more or less reliable. All predicted structures should be interpreted critically and in the light of these confidence scores.
Continue through the next subsections to learn more about these metrics.