AI-based structural modelling of host-pathogen protein interactions

AlphaFold and related Artificial Intelligence (AI) methods now predict the structures of many protein complexes with near-experimental accuracy, and they are increasingly used to model how pathogen proteins interact with host proteins. However, for host-pathogen interactions, the success rate remains low. In this webinar, we will explain how AlphaFold-style methods predict protein complexes, and why they depend on evolutionary information that host and pathogen protein pairs largely do not provide. We will then go through what recent large-scale studies have achieved, where the predictions worked and where they failed, and how the reported success rates should be read. Finally, we will describe strategies that can improve the results, including extensive sampling, modified sequence alignments, and the use of experimental data such as crosslinking mass spectrometry, illustrated with our work on influenza A virus.

This event is part of the webinar series “Integrating structural biology and bioinformatics to study infection”. You can follow the link for more information about the series and its webinars.

Who is this course for?

This webinar is suitable for students and researchers interested in host-pathogen interactions, protein structure prediction and structural bioinformatics. No prior experience with AlphaFold is required, although a basic understanding of protein structure and of multiple sequence alignments will make the methodological parts easier to follow.

Outcomes

By the end of the webinar, participants will be able to:

• Describe how AlphaFold-style methods predict the structures of protein complexes, and what their input data and confidence scores do and do not tell you.
• Explain why host-pathogen protein interactions are harder to predict than interactions within one species, and interpret published success rates in that light.
• Identify strategies for improving predictions, including extensive sampling, alignment and pairing options, biological context, and integration of experimental restraints such as crosslinking mass spectrometry.
   

This webinar, hosted on Zoom Webinar, is free to attend, but you need to register for a place beforehand, using the 'Register' button. Once registered, you will receive a confirmation email with a link to join the webinar.

The webinar will be recorded, and the recording will be made available on this page one day after the event. Please note that we do not issue certificates of attendance for our webinars. However, you will receive an email from our Zoom account confirming your participation a day after the event