A Bengaluru-based Artificial Intelligence (AI) firm has come up with “designs” of several chemical molecules that may help stop SARS-CoV2 virus, which causes Covid-19 infection from multiplying in an infected person.
The firm, which used deep learning technology to identify structures of molecules that would inhibit a critical enzyme of the virus – called 3CLpro, is already in talks with an Indian pharma company, which could synthesise the molecules for testing, if the deal materialises.
“We are not in a position to disclose the name of the pharma firm yet,” said Vikram Jha, CEO of Pucho Technology Information Limited, the five-year-old firm. The firm, which has office in Bengaluru has been involved in developing an AI platform that offers search and information services to people who have otherwise access to the Internet in languages they are comfortable with when the lockdown happened.
“We were ready with our platform but could not launch because of the lockdown. So, we decided to direct our energies towards the Covid-19 fight in a meaningful way using our expertise in AI. That was when two of our engineers specialising in deep learning suggested they could use neural network technology to look for generating potential lead compounds that can target the viral enzyme, 3CLpro,” said Jha.
Over the next few weeks working from their respective homes, Pucho engineers – Madhusudan Verma and Deepanshu Bansal – generated nearly 200 chemical structures and out of them, ten were found to have “drug-likeness properties” similar to existing 3CLpro inhibitors. One of them, in fact, is very similar in functionality to Remdesivir, the drug recently approved by US Food and Drug Administration for Covid-19. Verma and Bansal made the pre-print (not peer-reviewed yet) of the paper available online on ChemRxiv. The team is already in talks with a few journals for publishing the paper, Jha said.
Once the structure and functionalities are known, chemists would be able to synthesise the molecules using active pharmaceutical ingredients as feedstock. Subsequently, these novel molecules pass through a series of tests and trials – just as any new drug – before submitted for approval from drug regulatory authorities.
Using machine learning in drug design – for generating novel molecules with optimised properties – is a new thing in pharmaceutical research. Many pharma and IT companies – including TCS – have been involved in creating such molecules using what they called reinforcement neural networks. While TCS has used this technique to generate nearly 2,500 inhibitors, IBM generated about 3,000 novel molecules against three different targets.
"Unlike other companies where the average generation of molecules is in thousands or lakhs, we generated only 200 molecules and got ten novel molecules which have been potential inhibitors for Covid-19, Jha told BusinessLine.