AI Drug Discovery: A Key-Player in Finding Cure for COVID-19

Drug discovery

Drug discovery

Using Artificial Inteeligence For Accelerating Drug Discovery

Artificial Intelligence (AI) has transformed the healthcare industry in recent years. It has been influential in improving diagnostics tools, developing bots that can interact with patients recovering from surgery or with mental illness or transport medical samples and medicines. And now it is proving its mettle in drug discovery too. This is not surprising since AI innovations has become a regular dose for tech enthusiasts. Today, AI has potential to improve drug discovery and medical research which may reduce drug prices in the long-term—including COVID-19 vaccine.

The COVID-19 pandemic has wreaked havoc in human lives. Despite strict lockdown measures, social distancing protocols, at the time of writing this article, the number of positive cases was 41,171,093 worldwide with 1,130,597 deaths. Due to such alarming and unprecedented circumstances, researchers are more focused in leveraging technology to help them find potential cure to this nightmarish of a disease. Generally, discovery of any new drug to cure a disease is like finding a needle in a haystack. Further, it is an incredibly expensive, laborious, and time-consuming solution. Moreover, using the current conventional pipeline for discovering new drugs can take between five and ten years from the concept stage to being released to the market and could cost billions in the process. Next challenge is traditional protein drug discovery methods like high-throughput screening involve a lot of unsuccessful trial and error. Thus consuming a lot of time of researchers who are looking for new drug volunteer candidates.

Therefore, thanks to high-performance computing of supercomputers and artificial intelligence researchers can accelerate this process by screening billions of chemical compounds quickly to find relevant drug candidates. They also help scientists track the virus’s genetic mutations over time, information that will determine any vaccine’s value in the years to come. Earlier this year, a team of researchers from Penn State University had unearthed a solution that has the potential to expedite the process of discovering a novel coronavirus treatment i.e. quantum machine learning. This technology promises to yield quicker results and is more economical than any current methods used for drug discovery. Even a team of scientists lead by Russ Altman and Binbin Chen, at the Stanford Institute for Human-Centered Artificial Intelligence (HAI) used neural-network algorithms NetMHCpan-4.0 and MARIA, and a linear-regression model called DiscoTope, to come up with a list of targets on the novel coronavirus that were most likely to provoke an immune response.

Recently on September 10 Generate Biomedicines from Cambridge, Massachusetts announced to be leveraging machine learning algorithms and big data to design biological compounds to combat 50 of the top targets associated with a disease. The company is gathering volunteers for therapies that would fight SARS-CoV-2, caused by COVID-19.

All these instances of utilizing AI for rapid drug discovery against COVID-19, has helped in quicker transition to drug trials on humans—an achievement which would have sounded impossible a year ago. As per official data by WHO, as of early September, there were 34 vaccine candidates being tested in humans, and another 145 candidates were being tested in animals or in the lab. Laboratories are currently pursuing at least eight different types of vaccine. These include traditional ones based on inactivated viruses, as well as new, more experimental ones involving the use of genetic material—so-called DNA and RNA vaccines—as well as others based on special proteins or other biological agents.

It is important to note that while AI can speed up the process of molecule identification, sift through enormous database of known proteins and help in the synthesis of new custom proteins with therapeutic potential, it cannot hurry the trials phase. Jacob Glanville, founding partner at Distributed Bio says though computation helps to optimize the chances of success, ultimately one has to roll up his sleeves and do it in the lab.

However, despite this, one cannot simply rule out the role played by AI in the quest to find medical cure to the deadly COVID-19. In future, we may witness innovative and explicit uses of AI by leading pharmaceutical organizations in the drug discovery process.