Artificial intelligence halves development time for cancer drug

Pharmaceutical lab

A new cancer drug is being brought to market following testing by a pharmaceutical start-up using artificial intelligence that halved the usual time in development.

Berg Health expects the drug to be available within three years, seven years after it was put into development. This is half of the usual timeframe of 14 years and has been achieved using a specialised form of artificial intelligence that compares patient samples.

Niven Narain, president, chief technology officer and co-founder of Berg, said: "What the AI platform has done is helped us to develop this drug by understanding that the key hallmark of cancer is the cancer metabolism."

Cancer cell metabolism has been an area of interest for the National Institutes of Health (NIH) in recent times, and Berg's drug will undergo preclinical trials as it goes through development. Berg's drug is designed to find differences between the biological profiles of non-cancer sufferers and those with aggressive strains of the disease.

Of the artificial intelligence platform being used to match the right drug to the right type of tumour, Narain said: "It's helping us clinically develop the drug and define more lean and efficient clinical trials. It's not a one size fits all approach, it's the definition of precision medicine."

"We're looking at 14 trillion data points in a single tissue sample. We can't humanly process that," he told The Telegraph. "Because we're taking this data-driven approach we need a supercomputer capability."

It is expected that Phase 2 clinical trials will begin in the first quarter of 2016 with the help of the NIH. While kidney cancer is the NIH's area of focus, Berg believes the drug could help treat many types of cancer including brain, breast, gastric, oesophageal, pancreatic, liver and bladder.

Narain continued: "We use them for mathematics in a big data analytic platform, so it can collate that data into various categories There's a lot of trial and error in the old model so a lot of those costs are due to the failure of really expensive clinical trials. We're able to be more predictive and effective and that's going to cut hundreds of millions of dollars off the cost."

"We're [developing this drug] with world leaders, and that's a point of credibility but is good overall. Our passion is driving this tech to patients as quickly as possible."

Caroline Preece

Caroline has been writing about technology for more than a decade, switching between consumer smart home news and reviews and in-depth B2B industry coverage. In addition to her work for IT Pro and Cloud Pro, she has contributed to a number of titles including Expert Reviews, TechRadar, The Week and many more. She is currently the smart home editor across Future Publishing's homes titles.

You can get in touch with Caroline via email at