- 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.
Other tools to check quality of the predicted structures
Users who wish to further evaluate the quality of predicted protein structures from AlphaFold2 can use a variety of open-source tools.
Open-source tools for evaluating predicted structures
One option is a general structural biology validation tool like MolProbity. These are used for diagnosing “correctness” in 3D models of proteins, nucleic acids or complexes. AlphaFold2 models generally have excellent geometrical quality in high-confidence regions. Nevertheless, if MolProbity flags part of the structure, you should examine it carefully.
For protein-protein complexes, tools like PISA can be used to further assess the quality of the predicted interface. The software allows you to check details like the total buried surface area and the number of cross-interface hydrogen bonds, which in turn give an indication of whether the predicted interface corresponds to reality or is artefactual. Note that PISA validation criteria may have some exceptions, e.g. strongly bound antibody-antigen complexes could be reported as weakly bound by PISA.
The PAE viewer is a web server designed to facilitate the interpretation of PAE scores for multimeric predictions. The visualisation highlights the violations and/or satisfactions of crosslinker length restraints.