Scientists have successfully used artificial intelligence to create a new drug regime for children with a deadly form of brain cancer that has not seen survival rates improve for more than half a century.

The breakthrough, revealed in the journal Cancer Discovery, is set to usher in an “exciting” new era where AI can be harnessed to invent and develop new treatments for all types of cancer, experts say.

“The use of AI promises to have a transformative effect on drug discovery,” said Prof Kristian Helin, chief executive of The Institute of Cancer Research (ICR), London, where a team of scientists, doctors and data analysts made the discovery.

“In this study, use of AI has identified a drug combination which appears to have promise as a future treatment for some children with incurable brain cancer. It’s exciting to think that it could become one of the first examples of a treatment proposed by AI going on to benefit patients.”

Computer scientists and cancer specialists at the ICR and the Royal Marsden NHS Foundation Trust used AI to work out that combining the drug everolimus with another called vandetanib could treat diffuse intrinsic pontine glioma (DIPG), a rare and fast-growing type of brain tumour in children.

Currently, DIPG and other similar types of tumours are incredibly difficult to remove surgically from children because they are diffuse, which means they do not have well-defined borders suitable for operations.

But after crunching data on existing drugs, the team found everolimus could enhance vandetanib’s capacity to “sneak” through the blood-brain barrier and treat the cancer.

The combination has proved effective in mice and has now been tested in children. Experts now hope to test it on a much larger group of children in major clinical trials.

The research found that combining the two drugs extended survival in mice by 14% compared with those receiving a standard control treatment.

Both the drugs in the research, which was funded by Brain Research UK, the DIPG Collaborative, Children with Cancer UK and the Royal Marsden Cancer Charity, among others, are already approved to treat other types of cancer.

“DIPG is a rare and aggressive childhood brain cancer, and survival rates have not changed over the past 50 years so we desperately need to find new treatments for this disease,” said Chris Jones, professor of paediatric brain tumour biology at the ICR.

“Our study demonstrates just how much AI can bring to drug discovery for cancers like DIPG, in proposing new treatment combinations that would not have been obvious to people.

“The AI system suggested using a combination of two existing drugs to treat some children with DIPG – one to target the ACVR1 mutation, and the other to sneak the first past the blood brain barrier. The treatment extended survival when we tested it in a mouse model, and we have already started testing it out in a small number of children.

“We still need a full-scale clinical trial to assess whether the treatment can benefit children, but we’ve moved to this stage much more quickly than would ever have been possible without the help of AI.”

Dr Fernando Carceller, consultant in paediatric and adolescent neuro-oncology at the Royal Marsden NHS Foundation Trust, and leader of the paediatric and adolescent neuro-oncology and drug development team at the ICR, said the breakthrough was “encouraging” and highlighted the possibilities of “harnessing artificial intelligence” to find “cures” for cancer.

The initial idea for the research came from BenevolentAI – a company that has built an AI drug discovery platform. Researchers at the ICR worked with those from BenevolentAI to use its platform to identify drugs that could be used to treat DIPG.

Prof Peter Richardson, vice-president for pharmacology at BenevolentAI, said the early results were “promising”.

He added: “AI-enhanced approaches are already proving their value in expanding researchers’ capabilities to find innovative new treatment approaches – be it through uncovering new therapeutics or repurposing existing ones – not only in DIPG, but also other diseases in the future.”