Healx: Using AI to Discover New Treatments for Rare Diseases

The company aims to progress 100 rare disease treatments towards the clinic by 2025.

17.10.2019 | by Reve Fisher
Photo by Gerd Altmann from Pixabay
Photo by Gerd Altmann from Pixabay

Traditional drug discovery is a long, costly process. According to a study by the Tufts Center for the Study of Drug Development, the average cost to get a drug to market is $2.6 billion, and only 12 percent of medications even get approved to enter the clinical development process.

The team at Healx believes there’s a better way. The BioTech startup has developed an artificial intelligence-powered, patient-centred platform to bring drugs to market faster, with a focus on rare diseases.

According to the World Health Organisation, a disease is considered rare when it affects no more than five out of 10,000 people. Between 5,000 and 8,000 rare diseases currently affect a total of 400 million people worldwide.

Instead of developing completely novel treatments for rare diseases, Healnet, the company’s AI platform, maximises the value of drugs that are currently on the market, combining them to increase their therapeutic effects.

“By focusing on approved drugs and harnessing the power of AI we’ve been able to make the rare disease drug discovery process a faster and more efficient one,” Healx CEO Dr. Tim Guilliams told TechCrunch. “We’ve since made it our mission to progress 100 rare disease treatments towards the clinic by 2025.”

The programme uses natural language processing to extract information from already-published sources to complement biomedical databases as well as new, curated data generated through the platform. Healnet also uses machine learning techniques to examine clinical trials, medical literature, patents, chemical structures, symptoms, drug targets and other sources to gather the most comprehensive knowledge base possible.

“We use a variety of machine learning algorithms to solve the many tasks necessary to predict drug treatments and translate them in the clinic effectively,” Guilliams told VentureBeat. “We use deep learning AI algorithms that predict novel connections between, for instance, drugs and disease. This is known as ‘knowledge base completion’ and relies upon our comprehensive knowledge graph of rare disease data.”

Healnet’s data is then integrated into the company’s biomedical “Knowledge Graph.” The graph shows hidden and novel connections between drugs and diseases when explored by expert pharmacologists and biologists. As a result, the platform can prepare pre-formed, data-driven hypotheses, which speeds up the data interpretation process.

“We are able to predict drug combinations and translate them very fast in the clinic… ” the CEO said. “We work extremely closely with patient groups, as strategic partners and disease experts.”

Through these techniques, Healx aims to discover new treatments and move them toward clinic within two years—much shorter than the 12 to 14 years that a traditional drug needs to make it to market,

The startup raised $56 million in a Series B financing round led by Atomico with participation by Intel Capital, Global Brain, btov Partners, Balderton Capital, Amadeus Capital Partners and Jonathan Milner.

The funds will be used to launch Healx’s global Rare Treatment Accelerator and extend its pipeline. The accelerator is a collaborative effort among selected patient groups and teams of experts to review and validate the Healnet predictions for clinical trials.

Join the discussion

Leave a Reply

Related Shakers

Oluseun Onigbinde


Robert Scott Lazar

United Nuclear

Related Shakers