AlphaFold: 3D Structure of proteins

DeepMind, a company based in London and owned by Google, announced this week that it had predicted the three-dimensional structures of more than 200 million proteins using AlphaFold.
This is the entire protein universe known to scientists today.

How proteins fold has puzzled scientists for nearly 50 years.
Protein folding or denaturation is the physical process by which a protein chain achieves its native three-dimensional structure, usually biologically functional, rapid and reproducible.
AlphaFold gives the solution to a 50-year-old grand challenge in biology

AlphaFold is an AI-based protein structure prediction tool.
It is based on a computer system called a deep neural network.
Inspired by the human brain, neural networks consume large amounts of input data and produce the desired output, just like the human brain.
The real work is done by the black box between the input and the output layers, called the hidden networks.
AlphaFold is fed with protein sequences as input.
As protein sequences enter through one end, predicted three-dimensional structures emerge through the other.
It is like a magician pulling a rabbit out of a hat.

RoseTTaFold, developed by David Baker at the University of Washington in Seattle, U.S., is another tool.
Although less accurate than AlphaFold, it can predict the structure of protein complexes.

It uses processes based on “training, learning, retraining and relearning.”
The first step uses the available structures of 1,70,000 proteins in the Protein Data Bank (PDB) to train the computer model.
Then, the training results are used to learn structural predictions of proteins not in the PDB.
Once it does, it uses the high-accuracy predictions from the first stage to retrain and relearn to achieve higher accuracy than the previous predictions.
By using this method, AlphaFold has now predicted the structures of the entire 214 million unique protein sequences deposited in the Universal Protein Resource (UniProt) database.

Proteins are the business ends of biology, meaning that proteins perform all functions within a living cell.
Therefore, knowledge of protein structure and function is essential to understanding human disease.
Scientists predict protein structures using x-ray crystallography, nuclear magnetic resonance spectroscopy, or cryogenic electron microscopy.
- These techniques are not only time-consuming. They often take years and are largely based on trial-and-error methods.
AlphaFold’s development changes all that.
AlphaFold has already helped hundreds of scientists accelerate their discoveries in vaccine and drug development since the first public release of the database nearly a year back.

From the seminal contribution of G. N. Ramachandran in understanding protein structures, India is no stranger to the field and has produced some outstanding structural biologists.
The Indian community of structural biology is strong and skilled.
- It needs to quickly take advantage of the AlphaFold database and learn how to use the structures to design better vaccines and drugs.

Understanding the accurate structures of COVID-19 virus proteins in days rather than years will accelerate vaccine and drug development against the virus.
India will also need to speed up its implementation public-private partnerships in the sciences.
The public-private partnership between the European Molecular Biology Laboratory’s European Bioinformatics Institute and DeepMind made the 25-terabyte AlphaFold dataset accessible to everyone in the scientific community at no cost.
- From this, India could facilitate collaborations with the prevalent hardware muscle and data science talent in the private sector and specialists in academic institutions to pave the way for innovations in data science.

Pic Courtesy: The Hindu

Content Source: The Hindu