Enzyme researchers partner with pioneering AI company, DeepMind, in developing green solutions to combat plastic waste
University of Portsmouth joins leading AI researchers at DeepMind to help engineer faster acting enzymes for recycling some of the worlds most polluting single use plastics
University of Portsmouth joins leading AI researchers at DeepMind to help engineer faster acting enzymes for recycling some of the worlds most polluting single use plastics
The University’s Centre for Enzyme Innovation (CEI) has used DeepMind’s ground-breaking AI system to make strides in their research on circular recycling.
Following the initial announcement of DeepMind’s AlphaFold system last year — an AI system that predicts highly-accurate 3D structure of proteins— researchers at CEI struck up an exciting new collaboration with the team. As a testing partner, the CEI team was able to investigate the ability of AlphaFold to accelerate the engineering and development of their plastic digesting enzymes, proteins that act as biological catalysts.
The AlphaFold system was put to immediate use on a joint project running between the CEI and Dr Gregg Beckham’s group at the National Renewable Energy Laboratory in Colorado, researching a new selection of plastic-digesting enzymes.
Being given access to AlphaFold has transformed our research strategy, and we are excited to be partnering with DeepMind to explore other ways in which AI can accelerate our scientific discoveries
Professor Andy Pickford, Operations Director of the CEI, said: “Structure-informed enzyme engineering is a core aspect of our work but obtaining those structures has, until now, always been the bottleneck in our research pipeline. Being given access to AlphaFold has transformed our research strategy, and we are excited to be partnering with DeepMind to explore other ways in which AI can accelerate our scientific discoveries.”
The CEI is focussed on the discovery and engineering of enhanced enzymes that can eventually be applied at scale to break down some of our most polluting single-use plastics. The team has already improved the natural enzymes significantly, with advances published in the journal PNAS in 2018 and 2020, but one of the key bottlenecks is solving the enzyme structures that provide the atomic coordinates required. Their latest project, as part of the BOTTLE consortium, involves screening around 100 enzymes from a variety of microorganisms, too many to generate 3D structures for. Until now. Using AlphaFold, DeepMind is able to provide the team with all 100 structures in a matter of days, which is already changing their approach to the problem of generating improved enzymes.
AlphaFold provides us with an exciting new library of templates to engineer faster, more stable and cheaper enzymes for plastic recycling
Professor John McGeehan, Director of the CEI said: “AlphaFold provides us with an exciting new library of templates to engineer faster, more stable and cheaper enzymes for plastic recycling.
“This doesn’t replace the experimental techniques, in fact given the huge number of new targets that we can now investigate, we are going to need to employ experimental facilities such as the Diamond Light Source even more. In fact, I believe the next biggest scientific discoveries will emerge from the synergistic combination of experimental and AI technologies.
“Their open access model is now going to open this technology to laboratories around the world, accelerating collaborative efforts to develop enzyme-based solutions for recycling and upcycling plastic bottles and polyester textiles.”
the next biggest scientific discoveries will emerge from the synergistic combination of experimental and AI technologies.
DeepMind, in collaboration with EMBL’s European Bioinformatics Institute (EMBL-EBI), are today launching the AlphaFold Protein Structure Database (AlphaFold DB), containing 350,000 structures, including those of 20 organisms that are key to science, such as E.coli, fruit fly, mouse, zebrafish, malaria parasite and tuberculosis bacteria. Their target over the coming months is to vastly expand the coverage of this database to almost every sequenced protein known to science - over 100 million structures. This opens up huge opportunities for further discoveries in medicine and health, and through new partnerships such as the CEI, provides a faster route to biobased solutions for some of our biggest environmental challenges.
A copy of the Nature paper can be found here. and read the Authors notes here.
