Artificial intelligence halves development time for cancer drug

The time a new cancer drug spent in development was halved by scientists using artificial intelligence

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.

Advertisement - Article continues below
Advertisement - Article continues below

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."

Featured Resources

Digitally perfecting the supply chain

How new technologies are being leveraged to transform the manufacturing supply chain

Download now

Three keys to maximise application migration and modernisation success

Harness the benefits that modernised applications can offer

Download now

Your enterprise cloud solutions guide

Infrastructure designed to meet your company's IT needs for next-generation cloud applications

Download now

The 3 approaches of Breach and Attack Simulation technologies

A guide to the nuances of BAS, helping you stay one step ahead of cyber criminals

Download now


Careers & training

The UK should follow Finland's lead with it comes to AI training

19 Dec 2019
Business strategy

What is machine learning?

27 Sep 2019
Marketing & comms

AI is just clever marketing, and I’m not buying

20 Sep 2019

AI can play poker, but I’m neither shaken nor stirred

16 Jul 2019

Most Popular

Microsoft Windows

What to do if you're still running Windows 7

14 Jan 2020
operating systems

17 Windows 10 problems - and how to fix them

13 Jan 2020
Microsoft Windows

Memes and Viking funerals: The internet reacts to the death of Windows 7

14 Jan 2020

Dell XPS 13 (New 9300) hands-on review: Chasing perfection

14 Jan 2020