Engineering enzyme replacement therapies for lysosomal storage diseases using generative AI

Add to your list(s) Download to your calendar using vCal

• Dr Giovanni Stracquadanio, The University of Edinburgh
• Wednesday 11 October 2023, 16:00-17:00
• Lecture Theatre 2.

If you have a question about this talk, please contact Pietro Lio.

This talk has been canceled/deleted

Lysosomal storage diseases (LSDs) are rare inherited disorders caused by mutations in genes encoding lysosomal enzymes. Enzymatic deficiencies lead to the accumulation of substrates within the lysosome, ultimately cause progressive organ damage and death. The standard-of-care for many LSDs are enzyme replacement therapies (ERTs), which consist in injecting patients with a recombinant version of the defective enzyme to restore physiological enzymatic levels. However, current ERTs have limitations: they have poor catalytic activity, they are poorly uptake by the cell and usually trigger an immune response which limits their long-term use. We are addressing these issues by using an AI driven approach, where using a new class of variational auto-encoders based on discrete-like latent space modelling we can efficiently generate new ERTs with desirable sequence, structural and biochemical features. We are then linking our AI to our automated experimental platform, where we can rapidly build, test hundreds of ERTs in a matter of weeks and inform our AI to refine our ERT design. In this talk, I will show you our recent computational and experimental results of engineering new ERTs for Fabry disease, the most prevalent of all LSDs.

HYBRID https://cl-cam-ac-uk.zoom.us/j/99216883530?pwd=OFRHMkh1KzUzVm5EZzFLS0JLUTlMZz09

Biography. Giovanni Stracquadanio is an UKRI EPSRC fellow, Senior Lecturer (Associate Professor) in Synthetic Biology and co-director of the Edinburgh Genome Foundry (EGF). His group is interested in understanding the molecular mechanisms underpinning complex phenotypes and diseases using two of the most disruptive technologies available: synthetic biology and machine learning. His long-term goal is to reverse-engineer biological systems to develop generative algorithms to design, build and test biological agents for addressing healthcare problems, such as rare metabolic diseases and cancer, and industrial biotechnology challenges, like de-novo enzyme engineering. Dr Stracquadanio has authored more than 40 research articles published in international peer-reviewed journals, including Science, Nature Rev. Cancer, Cancer Research and PNAS . He also serves as Associate Editor for BMC Genomics and as reviewer and panel member for EPSRC , BBSRC, MRC and FLF . Since 2021, he is also a member of the EPSRC Peer Review Associate College

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

This talk is included in these lists:

This talk is not included in any other list

Note that ex-directory lists are not shown.