Why we need to take AI in drug discovery seriously
The role AI can play in drug discovery and development is well documented, but the recent global pandemic has highlighted the growing importance this technology has in the fight against disease, writes Lu Rahman.
Never has the world been more aware of the time and cost involved in the development of new drugs and vaccines. The global hunt is on for a vaccine for Covid-19, a process that usually takes 10-15 years. And while the pharmaceutical sector seeks treatments for the virus, this comes at a cost – a huge one. According to a study by the Tufts Center for the Study of Drug Development, it costs around $2.6 billion to develop a new prescription drug.
When the race is on to find treatment and prevention, the need to do things differently is clear. The luxury of time doesn’t exist when hundreds of thousands are dying, and this is where AI and machine learning are coming into their own. Companies such as Sanofi, Pfizer and Genentech, have already shown their interest and support for this technology, but in 2020, its ability to accelerate drug discovery and development has never been more crucial.
Academics at UCL have partnered with AI specialist Causaly in the hope of speeding up coronavirus research. Causaly uses AI techniques to rapidly read and interpret databases of biomedical knowledge. It pulls together evidence from 30 million biomedical publications in seconds, enabling researchers to map epidemiology data, biomarker genes, molecular targets and identify potential treatment options.
Earlier this year, UCL Innovation & Enterprise and Causaly began exploring the potential of collaboration. With the escalation of Covid-19, they saw the opportunity to bring their expertise together. UCL has been working on a number of Covid-19 related research projects, including the development and delivery of a low-cost breathing aid, trials of a potential anti-viral, and rapid genome sequencing to better understand the spread of the disease.
Healx, is an AI-powered, patient-inspired biotech specialising in rare diseases. It is using its AI platform to develop drug combinations from approved drugs to find treatments for Covid-19. This requires analysis of the eight million possible pairs and 10.5 billion drug triples stemming from the 4,000 approved drugs already on the market. Healx’s AI platform, Healnet, overcomes this challenge by analysing data to predict combination therapies most likely to succeed in the clinic.
Dr David Brown, Healx chairman, said: “Healx's data-driven AI platform is able to predict, within weeks, which known drugs can be repurposed to treat other conditions such as Covid-19. This approach significantly shortens discovery-to-clinic timelines. Our AI is able to combine two to three existing drugs to formulate the most effective treatment. This approach ensures that any potential treatments we identify can be used by clinicians to help patients very quickly.”