Summary
This Free EBI/EMBL on-line course “AlphaFold, A practical guide” provides an understanding of the fundamental concepts behind AlphaFold2, how users can run protein predictions and integrate these predictions into their projects, and how AlphaFold2 has been used to enhance research.
Course info
Cost: Free
Time to complete: 3 hours
Resources required: Google Account (computation occurs on Google Colab)
This free course is suitable for all levels from undergraduate upwards. It helps researchers, clinicians and data experts everywhere integrate AlphaFold protein structure predictions into workflows efficiently and responsibly. Delve into the fundamentals of AlphaFold, explore its strengths and limitations, and gain practical skills through hands-on exercises.
Course overview and goals
Proteins are essential components of life, predicting their 3D structure enables researchers to get an insight into its function and role. AlphaFold is an artificial intelligence (AI) system, developed by Google DeepMind, that predicts a protein’s 3D structure based on its primary amino acid sequence. It regularly achieves accuracy competitive with experiment.
This training module on AlphaFold2 has been developed in collaboration with Google DeepMind.
By the end of the course you will be able to:
– Explain how AlphaFold2 works and its strengths and limitations
– Describe how AlphaFold2 predictions were validated experimentally
– Discuss the fundamental concepts behind AlphaFold2 and why it is considered a significant breakthrough in protein structure prediction
– Assess the best way to predict protein structures
– Identify the best way to access pre-computed predictions from the AlphaFold2 Protein Structure Database
– Evaluate predicted structures from AlphaFold2 by integrating the different confidence metrics
What resources do I need?
To access some of the resources listed in this course, you will need a Google Account which can be created at accounts.google.com.
Course Contents – Chapter Titles
– An introductory guide to AlphaFold’s strengths and limitations
– Validation and impact
– Inputs and outputs
– Accessing and predicting protein structures with AlphaFold2
– Advanced modelling and applications of predicted protein structures
– Future directions and summary
– Glossary of terms
– References
Course Disclaimer
The course is subject to the disclaimer presented on the main page as predictions have varying levels of confidence and should be acknowledge by the users of the service.
DOI
A course DOI is provided: DOI: 10.6019/TOL.AlphaFold–w.2024.00001.1
Additional references
Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).
Yang, Z., Zeng, X., Zhao, Y. et al. AlphaFold2 and its applications in the fields of biology and medicine. Sig Transduct Target Ther 8, 115 (2023). https://doi.org/10.1038/s41392-023-01381-z