Connect with us


Using AI to find the cure for COVID-19



The coronavirus pandemic is one of the most difficult challenges many of us have experienced in our lifetime – and AI may have an important role to play in overcoming it, writes Ananth Krishnan.

In the midst of the turmoil national health authorities, pharmaceutical companies, universities, and research institutes have been put under enormous strain and pressure to find a cure or a vaccine against COVID-19, with individuals working tirelessly around the clock.

This year has shown that solving problems during a crisis demands accelerating innovation by repurposing the knowledge, resources, and technology we already have at hand. As organisations and experts scramble to innovate therapies, they are also redefining innovation. The future of healthcare lies in working hand-in-hand with technology.

Reimagining the future of healthcare with AI

Over the last decade we have seen enormous innovation in healthcare technologies, such as VR/AR, 3D-printing, robotics and nanotechnology but perhaps most exciting, is the advancement in artificial intelligence (AI).

Before this outbreak, AI-based methods were emerging as promising tools with which to explore chemistry as they can learn feature representations based on existing drugs. In the normal research process, lots of researchers would have to spend hours going through databases and literature to find suitable drug candidates.

By using AI, scientists can use already existing data to find these candidates without deploying a full team, a team who can turn their attention more resourcefully elsewhere.

Recent studies have proven the efficiency of AI techniques in understanding the known chemical space and generating novel small molecules. These molecules need to satisfy several physicochemical properties to be able to be used as potential drug molecules.

With the advent of AI-based methods, it is possible to design these small molecules with the desired drug-like properties.

Most importantly, this AI-based approach can reduce the initial phase of the drug-discovery process from several years to a few days, in part thanks to its ability to streamline through rapid data processing. Typically, finding a new drug takes a decade or more with a very low success rate.

However, advances in data curation and management have meant that AI can massively reduce that. In a situation like COVID-19, this is very important as cases grow exponentially and can rapidly spiral out of control.

Putting AI to work against COVID-19

The scientific community’s priority is finding treatment and a vaccine as quickly as possible so we can return to our lives as normal. AI has proven critical in the fight against COVID-19, by helping scientists to identify and study the molecular setup of existing drugs that were developed to fight other diseases, but which could now be repurposed to combat the deadly virus.

One of these teams of scientists are those in Tata Consultancy Service’s (TCS) Innovation Lab in Hyderabad, India. They have discovered 31 molecular compounds that could potentially be used in the search to find a cure for COVID-19.

They have done this by using AI to focus on one of the well-studied protein targets for coronavirus, chymotrypsin-like (3CL) protease. This protease is responsible for the virus’ survival and replication in humans; essentially if you can find a way to stop this, you can stop the spread.

Ananth Krishnan, chief technology officer at TCS

TCS created an AI model which was initially trained on a dataset of 1.6 million drug-like molecules from the ChEMBL database, a public database which maintains the most comprehensive collection of drug-like small molecules.

The use of AI enabled scientists to rapidly evaluate multiple scenarios with a multitude of parameters while problem-solving, and so, allowed them to adapt and refine the model to produce molecules with the optimised physiochemical properties.

The trained generative model sampled 50,000 small molecules. After duplicates were removed, the molecules were streamlined based on their chemical properties, drug likeness, water content and other factors.

The resulting set of molecules were further filtered based on their affinity towards the SARS-CoV-2 3CL protease. A virtual screening revealed a total of 1,333 small molecules which could act as potential inhibitors.

The team also noticed that the generative model could produce small molecules that are similar to HIV-protease inhibitors, but with better binding to the SARS-CoV-2 3CL protease. This narrowed down the dataset to only 31 molecular compounds.

While we are still a way off from being able to develop drugs at scale using AI, this is a step in the right direction. The research is now available to the public (and can be found here) so that scientists around the world can use this data to aid the development of a treatment and a vaccine for COVID-19.

The start of a revolution

The potential for this goes far beyond finding a vaccine for COVID-19, By using these same tools and skills across the healthcare sector the possibilities are endless on what could be achieved. The future of healthcare is well and truly shaping up in front of our very eyes and it’s clear that AI has an important role to play in it.

From speeding up the vaccine process for coronavirus to driving innovations in clinical operations, drug development, surgery and data management to name but a few. With AI we can accelerate the speed and dramatically reduce the cost across the healthcare space.

It may also be possible topersonalise medical treatments by leveraging analytics to mine significant, previously untapped stores of non-codified clinical data.

The advancement in data curation and management have fuelled the emergence of an AI-driven revolution in drug discovery, and so it comes as no surprise to learn that the market value of AI in the global health care industry is projected to reach a staggering $31.02 billion in 2025! 

Ananth Krishnan is chief technology officer at in Tata Consultancy Services (TCS). 


Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Trending stories