AI harnessed in fight against deadly childhood cancer

Scientists used the technology to come up with a combination of drugs to treat diffuse intrinsic pontine glioma

There are currently no treatments approved to target the ACVR1 mutation. Alamy
Beta V.1.0 - Powered by automated translation

Artificial intelligence can be used in the fight against a deadly form of brain cancer in children after work done by a leading London hospital.

There has been no improvement in the survival rate of children suffering from diffuse intrinsic pontine glioma (DIPG) tumours for half a century. The growths have proven difficult for surgeons to extract because they do not have clearly defined borders suitable for operations.

A quarter of children with DIPG have a mutation in a gene known as ACVR1, for which no treatments are approved.

Scientists at the Institute of Cancer Research, London (ICR) and the Royal Marsden NHS Foundation Trust were able to use AI to discover that combining the drug everolimus with another called vandetanib could enhance the latter's capacity to pass through the blood-brain barrier and attack the cancer.

The combination has proved effective in mice, where the drugs increased the animals' vandetanib levels by 56 per cent and their survival rates by 14 per cent.

The process has been tested on four children and experts hope to involve a wider group in clinical trials. Both drugs in the study have approval to treat other types of cancer.

The breakthrough comes days after the results of a major clinical trial showed that a simple blood test can detect 50 types of cancer.

AI-enhanced approaches are already proving their value in expanding researchers' capabilities to find innovative new treatment approaches
Prof Peter Richardson, BenevolentAI

"This encouraging research highlights the possibilities of harnessing artificial intelligence to find better cures for childhood cancers," said Dr Fernando Carceller, consultant in paediatric and adolescent neuro-oncology at the Royal Marsden NHS Foundation Trust.

"Close collaboration between scientists at the ICR and clinicians at the Royal Marsden made possible this bench-to-bedside approach."

The initial plan for the study came from BenevolentAI – a company that has built an AI drug-discovery platform.

Researchers at the ICR worked with those from BenevolentAI to use the platform to identify drugs that could be used on ACVR1 mutations in DIPG.

"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," said Prof Peter Richardson, vice president for pharmacology at BenevolentAI.

Updated: September 23, 2021, 9:49 AM