Deep Learning — it is the artificial intelligence (AI) that powers today’s self driving cars, chatbots, personal assistants (such as Alexa, Cortana, Siri etc.), facial recognition in social media and law enforcement agencies. The collaboration between Prof Angshul Majumdar of IIIT Delhi and Prof Emilie Chouzenoux of INRIA, Saclay, Paris, harnesses the power of deep learning to screen drugs that have the potential to treat COVID-19 infections. “This is the first of a kind AI powered study for antiviral selection”, says Prof Majumdar.

In scientific literature this is called ‘drug repositioning’. Current approaches are based on rudimentary models like network diffusion, similarity matching, matrix factorisation, classification etc. In contrast, our approach (DeepVir), integrates the power of deep representation learning with biological insights via graphical regularisation. Furthermore, Prof. Chouzenoux boosted DeepVir with a state-of-the-art optimisation approach based on hybrid proximal alternating minimization (HyPALM); in short “it is Deep Learning on steroids,” she explains.   

Our deep learning AI model, DeepVir, selects Chloroquine, Remdesivir, Umifenovir, Favipiravir and Ribavarin. All of them are undergoing clinical trials for treating COVID-19 infections.

The use of chloroquine and hydroxychloroquine for COVID-19, both as a prophyalactic and as a treatment, is common knowledge today. Major pharma companies (Zydus Cadilla, Cipla, Jubilant) in India have already launched Remdesivir for treating COVID-19 infections. The Russian drug Umifenovir has received DGCI nod for phase III trials in the country a while back. Several big Pharma companies have launched the Japanese drug Favipiravir for treating novel coronavirus infections.