Subscribe

Vodafone’s crowdsourcing app speeds up COVID-19 research

Sibahle Malinga
By Sibahle Malinga, ITWeb senior news journalist.
Johannesburg, 20 May 2020

The Vodafone Foundation has collaborated with scientists at UK-based research university, the Imperial College London, to develop the DreamLab app, aimed at helping speed up research into treatments for the novel coronavirus (COVID-19).

DreamLab is a specialist app, developed as part of the Corona-AI project, which harnesses artificial intelligence (AI) and the processing power of smartphones used by hundreds of people to speed up the discovery of novel anti-viral components in existing medicines and help in the hunt for anti-viral molecules in foods.

Since the outbreak of the deadly pandemic, technology has been placed at the centre of managing the spread of the virus, which has already infected almost five million people globally and claimed the lives of almost 325 000, with over 1.9 million recoveries.

The DreamLab app creates a network of smartphones to power a virtual supercomputer, capable of processing billions of calculations, without collecting or disclosing users’ location data.

Users download the DreamLab app and run it for six hours overnight as the phone charges.

During this time, the app downloads a 5MB packet of data and uses the phone’s processors to run millions of calculations, before uploading the results and clearing the data.

By using the crowd-based approach to work on publicly available data on human genes and drug interactions, the researchers hope to significantly speed up COVID-19 research, by identifying new combinations of drugs that may be more effective in fighting the virus.

According to the Vodafone Foundation, using this mobile cloud-based computing approach could drastically reduce the time taken to analyse such vast amounts of data. A desktop computer with an eight-core processor running 24 hours a day would take 100 years to process the data, but a network of 100 000 smartphones running six hours per night from various parts of the globe could do the job in just three months.

“We are pleased to offer our DreamLab technology to assist researchers at Imperial College in their work to fight the coronavirus,” says Joakim Reiter, Vodafone Foundation trustee and external affairs director, Vodafone Group.

“Vodafone Foundation’s award-winning DreamLab app has already supported discoveries through cancer research thanks to our customers’ participation, and we want to do our part now as society battles against COVID-19.”

Every time a person uses the DreamLab app, they are supporting vital scientific health studies, according to the foundation. The Corona-AI research project involves analysing billions of combinations of existing drugs and food molecules to identify how they can be potentially used for more effective treatments against COVID-19.

Researchers believe that in the long run, this work could speed up access to effective drugs and enable tailored treatments against the infectious disease.

Ultimately, the research will result in dietary recommendations with anti-viral properties and an open source database for clinicians around the world to test in labs.

Dr Kirill Veselkov from the Department of Surgery and Cancer at Imperial College London, who is leading the research, says: “We urgently need new treatments to tackle COVID-19. There are existing drugs out there that might work to treat it, but we need to do complex analyses using AI to find out which molecule or combinations of molecules might be able to disrupt the virus when it’s inside the body. All of this takes a huge amount of computing power and DreamLab enables us to do this important work in a much shorter timeframe.”

DreamLab is free to download and zero-rated for Vodafone customers, and is available in the app stores for iOS or Play Store for Android.

It is available to download now in SA, Australia, Italy, New Zealand, Spain, Romania, UK, Portugal, Ghana, Lesotho and Germany, and will be available in Ireland, Greece, Turkey and Albania from 1June.

Share