top of page
Search
Muneeza Maqsood

AlphaFold: A Miraculous Advance to Solve 50-Year Old Biological Problem

For more than 5 decades, researchers have been struggling with the great biological challenge of “Protein Folding” to map the 3-dimensional structures and conformations of the proteins that are responsible for diseases from cancer to COVID-19. DeepMind - an artificial intelligence (AI) company and research laboratory acquired by Google - claims to solve such biological problems regarding the structure determination of proteins as a matter of days, via a tool known as “AlphaFold” created by the researchers of the DeepMind using the AI algorithms.





In essence to the results of the latest experiment, DeepMind claimed AlphaFold to have the potential to determine the shape of about two-third of proteins with accuracy comparable to wet lab techniques and also published the results online for other scientists to further inspect these results.


According to the experts, if it works, the solution has come “decades” before it was expected and can have transformative effects in the way diseases are treated. Professor Venki Ramakrishnan, a nobel laureate and the President of the Royal Society said:


“This computational work represents a stunning advance on the protein-folding problem, a 50-year-old grand challenge in biology. It has occurred decades before many people in the field would have predicted. It will be exciting to see the many ways in which it will fundamentally change biological research.”


Why is it important to determine the 3D structure of proteins?

A protein’s shape is closely linked with its function, and by predicting this structure unlatches a greater understanding of what it does and how it works. A lot of the world’s greatest challenges, like developing treatments for diseases or finding enzymes that break down industrial waste, are fundamentally associated with proteins and the function they perform.


The “Protein Folding Problem”

For many years, it has been a focus of intensive scientific research to use a variety of experimental techniques to examine and determine protein structures, such as nuclear magnetic resonance (NMR) and X-ray crystallography. These techniques, as well as newer approaches like cryo-electron microscopy, depend on extensive trial and error, which can take years of conscientious and laborious work per structure, which require the use of multi-million dollar specialised equipment and apparatus.


At present about 200 million proteins are known to exist in nature but only a fraction have actually been unfolded to fully understand what is their function and how they perform it. Even those that have been understood completely and successfully often depend on costly and time-intensive techniques, with scientists devoting years to unfold each structure and relying on pretty expensive equipment.


AI to solve the problem

DeepMind has been working on the AI project along with the 14th Community Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction (CASP14), a group of scientists who have been looking into the matter since 1994.


This major breakthrough illustrates the impact AI can have on scientific discoveries and its potential which can dramatically accelerate progress in some of the most fundamental fields of science that elucidate and shape our world.


According to Arthur D. Levinson, founder & CEO of Calico, Former Chairman & CEO of Genentech:

“AlphaFold is a once in a generation advance, predicting protein structures with incredible speed and precision. This leap forward demonstrates how computational methods are poised to transform research in biology and hold much promise for accelerating the drug discovery process.”


The researchers and scientists behind the project say that there is still more work that needs to be done, which involves figuring out how multiple proteins form complexes in order to form huge and complicated networks and how they interact with DNA.


276 views0 comments

Recent Posts

See All

Comments


bottom of page