Image: Neural network graphic. Source: Rawpixel (edited)
Scientists have created a dynamic database driven by artificial intelligence which is collecting together the world’s research on coronavirus in a single online space.
The new resource will make freely available vast amounts of data on the biology and treatment of COVID-19 – accelerating the search for new drugs and ensuring we learn rapidly from international efforts to understand and overcome the disease.
A team at The Institute of Cancer Research, London, has fast-tracked development of the powerful database by adapting an existing system called canSAR which already pulls together data from across cancer research and drug discovery.
One-stop shop for COVID-19 research
The new ‘knowledgebase’, called Coronavirus canSAR, draws in data published across the world on viral proteins, interactions of viral proteins with human proteins, drugs and drug mechanisms, and clinical trials.
It is believed to be the world’s first one-stop shop for research on COVID-19 and related diseases such as SARS and MERS.
Coronavirus-CanSAR has been developed by a team of researchers funded by Cancer Research UK and the Wellcome Trust – and will help power the interactions between scientists across the globe with a wide range of expertise and disease interests who are working together to beat COVID-19.
It is the first phase of an ambitious push to capture the rapidly changing information on coronaviruses, and should help researchers rapidly repurpose drugs from across the whole of medicine, including cancer.
Unique AI technology
The online knowledgebase, which is updated weekly, pulls in every 3D structure of all biological molecules published in the international Protein Databank – 450,000 so far. This information includes more than 830 3D structure snapshots of 47 proteins made by the novel coronavirus, MERS and SARS.
Using canSAR’s unique AI technology, the team at The Institute of Cancer Research (ICR) analysed more than 4 million sites across all proteins in its database, including more than 8,000 from coronavirus protein structures.
The researchers identified several ‘druggable cavities’ – suitable sites for novel antiviral drugs targeted at the contact points between human and virus proteins.
Coronavirus-CanSAR uses AI to generate complex three-dimensional maps of how virus proteins interact with human proteins that look like visualisations of space. These maps are based on data on almost 1 million interactions – and highlight those that could potentially be disrupted with new drugs.
The team will also assess the quality of data published on how viral proteins interact with human proteins or existing drugs – so that the system can point users to the most promising leads for new treatments.
We are building a new state-of-the-art drug discovery centre to develop a new generation of drugs that will make the difference to the lives of millions of people with cancer. Find out more about the challenge of cancer drug resistance and help fund research to help finish cancer.
Objectively assessing potential treatments
The researchers have already used Coronavirus-CanSAR to analyse the interactions between coronavirus and the critical proteins ACE2 and B(0)AT1 which it uses as a gateway to human cells – and identified new druggable sites at these interfaces.
This work is guiding the development of new antibodies at the ICR that could either amplify the signal from viral infection to improve testing, or act as treatments themselves by blocking the interactions between viral and human proteins.
The knowledgebase also pulls together data from more than 1,100 clinical trials of COVID-19 alongside existing findings on SARS and MERS, so researchers can objectively and transparently assess results on drugs that have been touted as potential treatments, such as chloroquine or remdesivir.
The ICR, with funding from Cancer Research UK and Wellcome, is making a team of around 10 researchers available for ongoing development of the database and curation of the data within it. The team plans to work with colleagues around the world to make the resource as valuable as possible in the battle against COVID-19.
‘More than just a database’
Project leader Professor Bissan Al-Lazikani, Head of Data Science at The Institute of Cancer Research, London, said:
“We are launching the initial phase of the world’s first one-stop shop for coronavirus research, designed to rapidly pull together data on COVID-19 as it becomes available. It is more than just a database – it’s an intelligent system which visualises vast amounts of complex data in a way that is easy for researchers to understand and act upon, predicts which approaches to treatment are most likely to work, and objectively assesses the information emerging from clinical trials.
“We hope that Coronavirus-CanSAR can play a big role in the search for new drug treatments for COVID-19, and can become a vital tool for future research into viral diseases too. Unfortunately, nothing like this existed during the past SARS and MERS outbreaks, and we need to ensure that it is maintained and developed as part of our rapid response to future pandemics.
"The faster we beat COVID-19, the faster we can get back to defeating cancer, and as we’ve demonstrated in this work, one field can benefit from knowledge generated by another. We will take the lessons from Coronavirus CanSAR back to benefit our cancer research."
Here at the ICR, we are leading in innovative cancer informatics. From mapping the paths of cancer evolution, to the design and discovery of novel drugs, to the precision tailoring of radiation therapy.
Global effort to tackle the coronavirus crisis
Project co-leader Professor Paul Workman, Chief Executive of the ICR, said:
“Scientists around the world, representing a wide range of research backgrounds and skills, are coming together in an unprecedented way to help tackle the coronavirus crisis. Our intelligent knowledgebase is a great example of this, created by our specialists in data science and AI, drawing also on our expertise from cancer research and structural biology, and intended to benefit virologists, drug discoverers and doctors treating patients with COVID-19.
“Our aim is to bring all the relevant data together in one place, helping researchers to cut through the noise and prioritise the best opportunities, and speeding up the pace of coronavirus research around the world. We want to make sure that patients everywhere benefit as soon as possible from the best of the treatments that have already reached the clinic, as well as identifying new opportunities for innovative drug discovery.
“With the support of Cancer Research UK and other funders, we have been using and continuously enhancing our canSAR knowledgebase over the last 10 years to empower ourselves and others to discover new cancer drugs. We have now rapidly adapted our resource for use by scientists worldwide in the battle against COVID-19.”