Unfolding The Mystery of Proteins Using Deepmind’s AI Tools

Proteins are large, complex but essential molecules for life, which perform vital functions in our bodies. Proteins spontaneously fold into unique three-dimensional (3D) structures; their structures play a crucial role in determining their biological function. In fact, the recipes for each protein are encoded in a string of letters that we owe to our DNA. Any error in the code results in either the complete absence of a protein or the formation of dysfunctional proteins which ultimately lead to disease conditions.

(photo: Getty/Science Photo Library RF)

What’s the matter?

Traditionally, 3D structures of proteins were determined with the help of techniques like Cryo-Electron MicroscopyNuclear Magnetic Resonance, and X-Ray Crystallography, which are extremely expensive as well as time-consuming. With a view to increasing efficiency as well as reducing time and costs involved, researchers are resorting to Artificial Intelligence (AI)-based tools which are capable of predicting the 3D structures of proteins based solely on their genetic sequences. 

The breakthrough occurred when DeepMind Technologies, London, a Google’s subsidiary, launched an AI- based software named ALPHAFOLD that predicted the structure of nearly the entire human proteome, covering 98.5% of known human proteins (https://www.deepmind.com). ALPHAFOLD works on the principle of deep neural networks which can predict the properties of a protein just from its genetic sequence. The AI-based tool predicted the complete proteomes of 20 model organisms, ranging from mice and maize to the malarial parasite.

Why its important?

This new technology led to solving structures of more than 350,000 proteins; these structures were made publicly available by the company for the benefit of the scientific fraternity. The project has yet to be completed; the company aspires to enrich the database with 130 million additional structures, with highest possible accuracy, by the end of 2021. This is a revolutionary news for biologists who can now “predict” targeted protein structures within a time span of a few minutes to hours, which will help them understand the unique properties of the proteins, and perhaps provide ideas on their potential role within cells.

This advancement can a be total game-changer, especially in drug discovery, accelerating the drug development process. It can also play a crucial role in managing the global issue of pollution, by identifying key biodegradable enzymes for engineering bacteria to manage plastic and oil pollutants. These are just some of the applications; this breakthrough advancement can prove to be a torchbearer in managing several other prevalent issues.

AUTHOR : Priya Mehta, Ph.D.

REVIEWER : Manasi Apte, Ph.D.

COPY EDITOR : Liza Changkakoti, M.Sc.

GRAPHICS DESIGN : Tausif Ahmed Sayed, B.E. (Chem.) & REVIEWED BY : Isha Parlikar & Pawan Upadhyay, Ph.D.

PUBLICATION SUPPORT : Karthick Raj S M K, B.Tech.(Food Technology)

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

Create a website or blog at WordPress.com

Up ↑

%d bloggers like this: