AstraZeneca joins with BenevolentAI for drug discovery

Strategic partnership between AstraZeneca and BenevolentAI to use artificial intelligence and machine learning to identify new kidney and lung drugs.

Pharma giant AstraZeneca has announced a new long-term collaboration with artificial intelligence experts BenevolentAI. The collaboration aims to combine AstraZeneca’s world-leading clinical data with BenevolentAI’s machine learning capabilities and artificial intelligence to discover new drugs for chronic kidney disease (CKD) and idiopathic pulmonary fibrosis (IPF).

As a recent study in Respiration shows, CKD and IPF are two of the most fatal and prevalent age-associated diseases [1]. However, they are both notoriously complex and not much is yet known about their underlying biology. This makes the process of researching and developing new treatments much more difficult.

Longevity.Technology: Big pharma have large data sets that can be mined to understand the prevalence, cause and treatment of certain diseases. When companies work together it’s a cases of smarter, not harder, and it’s to their benefit as well as to the benefit of the patients who will reap the extended lifespan rewards.

The TRL score for this Longevity.Technology domain is currently set at: ‘Early proof of concept demonstrated in the laboratory.’
TRL score 3 orange
The TRL score for the technology addressed in this article is: ‘Principles are demonstrated through experimentation.’

To discover viable new treatment options for CKD and IPF, BenevolentAI will use machine learning to systematically mine and analyse AstaZeneca’s datasets to discover commonalities. AI-based reasoning will then be used to infer previously unknown connections. Scientists from the two organisations will then be able to interpret these results to better understand how these diseases work and potentially identify new treatments.

“By combining AstraZeneca’s disease area expertise and large, diverse datasets with BenevolentAI’s leading AI and machine learning capabilities, we can unlock the potential of this wealth of data to improve our understanding of complex disease biology and identify new targets that could treat debilitating diseases” Mene Pangalos, AstraZeneca’s executive vice-president of biopharmaceuticals R&D, said in a press release announcing the collaboration [2].

Pharmaceutical companies have been increasingly using AI to optimise the drug discovery process. The global healthcare AI market is expected to surpass $10 billion by 2024, according to new research by Global Market Insights [3].

Currently, developing a new drug can cost up to $2.6 billion because 95% of new treatments fail [4]. Furthermore, despite being an evidence based field, there is so much research being published that is impossible for researchers to take it all into consideration. AI has the potential to reveloutionise the drug discovery sector by making the process more efficient, cheaper, and more accurate through predictive modelling and processing unprecedented amounts of data.

BenevolentAI has previsouly been successful in working with charities to identify possible treatments for age-related sight loss and motor neurone disease. CKD and IPF mark the next phase in their development, representing a degree of complexity which requires the interrogation of much larger data-sets.

However, prominent pharmaceutical insider Derek Lowe dampens the optimism surrounding AI by arguing that the primary issue halting innovation is not our inability to process large amounts of data. Rather, he writes for the the Scientific Journal of Translational Medicine that the “bigger problem is that we just don’t know enough about cells, about organisms, and about disease” [5].

The long-term usefulness of AI within the drug discovery process will ultimately be determined through the results collaborations between companies such as AstraZeneca and BenevolentAI produce. Nevertheless, AI is enjoying a moment in the sun, with AstraZeneca only the latest pharma giant to invest heavily into the new technology.

[1] https://www.ncbi.nlm.nih.gov/pubmed/28728146
[2] https://www.astrazeneca.com/media-centre/press-releases/2019/
[3] https://www.globenewswire.com/news-release/2017/05/11/982356/0/
[4] http://phrma-docs.phrma.org/sites/default/files/pdf/rd_brochure_022307.pdf
[5] https://blogs.sciencemag.org/pipeline/archives/2018/04/23/benevolentai-worth-two-billion
Image: Piotr Swat / Shutterstock.com