- 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 AlphaFold2
- 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
- Classifying the effects of missense variants using AlphaMissense
- Future directions and summary
- 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.
Outputs from ColabFold
ColabFold generates PDB files containing the predicted 3D coordinates of the protein or protein complex. These can be analysed with standard molecular visualisation software packages, such as PyMOL or Chimera.
pLDDT values are stored in the B-factor field. This means you can use molecular graphics programs like PyMOL to colour-code the predicted structure according to the pLDDT scores (e.g. see ColabFold’s FAQ for the instructions).
For monomer structures, the predictions are ranked by pLDDT, where ‘rank_001’ represents the structure with the highest confidence. For protein complexes, the predictions are ranked by pTM (see section “Evaluating AlphaFold2’s predicted structures using confidence scores” for explanations of these confidence metrics).
ColabFold also provides a pLDDT plot (_plddt.png). This shows the pLDDT score for each amino acid position. Meanwhile, the PAEs for all models are stored as one png file (_PAE.png).
The MSA file (a3m format) contains the sequences used by ColabFold in the prediction. This file can be inspected using your favourite alignment viewer, e.g. JalView.
The MSA coverage and diversity can be examined by visualising the coverage plot (_coverage.png). This plot shows the number of sequences in the MSA and their identity to specific amino acid positions. This can provide insights into the sequence information used for the prediction.