Belgium
Slideshow, Training materials
Prediction of protein structures and complexes with AlphaFold on the HPC
At the end of 2020, results for the CASP14 (Critical Assessment for protein Structure Prediction) were released. Just like in 2018, DeepMind Technologies won the competition with their deep (machine) learning based AlphaFold prediction models. However, the leap in prediction accuracy now raised the performance to a level that had several big names in the field consider the protein structure prediction task as ‘solved’.
Architectural details, code and trained AlphaFold models were released by DeepMind in 2021. Given the high computational cost of deep learning algorithms, specialized hardware and software are required. Online solutions are available but come with considerable disadvantages. Therefore, the Flemish Supercomputer Center (VSC) provides high performance computing facilities, on which AlphaFold is installed and fully operational. This course gives a solid introduction on how AlphaFold can be easily and swiftly accessed using the HPC.
Next to AlphaFold, RoseTTAFold has been published alongside in the summer of 2021. This tutorial will be extended with more background information on RoseTTAFold as well as a practical guide for the HPC.
This tutorial material was created by Jasper Zuallaert (VIB-UGent), with the help of Alexander Botzki (VIB) and Kenneth Hoste (UGent). For questions and remarks, feel free to contact [email protected] or [email protected].
This work is licensed under a Creative Commons Attribution 4.0 International License.
Licence: Creative Commons Attribution Non Commercial Share Alike 4.0 International
Contact: [email protected], [email protected]
Keywords: AlphaFold Database (13181), Structure prediction
Target audience: Life scientists with programming skills
Resource type: Slideshow, Training materials
Version: 1.0
Status: Active
Prerequisites:
You are encouraged to use your own laptop. For those who do not have a laptop, the YASARA software can be run in a remote Linux environment (access to cloud via web browser).
Knowledge of command line and basic Python skills are recommended.
Learning objectives:
Objectives
Day 1 Protein Structure Analysis
- Get to know the data generated from protein structure determination experiments (high-resolution NMR spectroscopy, X-ray crystallography, electron microscopy, ...) and where to get it.
- Display protein structure data and compare structures, through the use of Yasara.
- Create high-quality graphical representations of the structures.
- Calculate the effect of mutations on the stability of your protein.
Day 2 AlphaFold
- Introduction to AlphaFold2 and the technical setup at the Flemish SuperComputer
- Understand the technical methodology of AlphaFold2
- Understand the technical setup at the Flemish SuperComputer
- Predict three-dimensional protein models with AlphaFold2 using the HPC at the VSC UGhent
- Dive in your research question where structural prediction via AlphaFold will be used.
Date created: 2022-04-01
Date published: 2022-04-28
Contributors: Kenneth Hoste
Scientific topics: Protein structure analysis, Machine learning, Structure prediction
Operations: Structure visualisation, Multiple sequence alignment
Activity log
