COVID19 has caused thousands of deaths worldwide within a few months. The rapid spread of this virus has been helped by the lack of effective vaccines and treatments. In response to this threat, and to support the efforts in the search for a treatment for this existential threat, we directed our efforts to find a treatment for COVID19.  

Through a joint initiative with Youcef Mehellou at Cardiff University, we employed our artificial intelligence for drug discovery platform, Rosalind, to design compounds that could become viable drugs for the treatment of the COVID-19 coronavirus.

Rosalind has been injected with medicinal chemistry insights provided by our collaborator as well as knowledge from reported inhibitors of SARS-CoV and SARS-CoV-2. Through a unique set of generative and predictive models, Rosalind explored a wide and diverse chemical space. We finally prioritised a list of five compounds for further synthesis and testing. Rosalind will now form the basis of endeavours aimed at rapidly discovering effective treatments for COVID19 that could make a significant impact on the management of this infection. 

The data is made publicly available and we are continuing our work in a collaborative manner to identify lead SARS CoV2 Mpro compounds with excellent drug-like properties that could be developed in a timely manner to address the urgent need for new and effective COVID19 treatments. 


The approach followed is published in our preprint here.

Computational Docking

Docking and calculation of binding energy are a big part of Rosalind’s prioritisation phase. We know setting up a scalable process can take time and requires considerable computing resources. We are therefore offering the use of our computational docking pipeline to the wider community. Design your compounds,  we will dock them and get you the results in 48 hours. More details here.