Connect with us

Healthcare

Drug Developed With AI Set To Start Clinical Trials

mm

Updated

 on

The AI startup Exscientia created a new drug compound that will soon start undergoing clinical trials in Japan. This is one of just a few instances of AI developed drugs being used in a clinical setting, potentially bringing the world closer to the widespread use of AI in drug development and deployment. The new compound was developed in association with Sumitomo Dainippon Pharma and in contrast, to traditionally develope drugs, the AI-developed compound will be starting clinical trials in just under a year from the inception of the project. Typical drug development takes around four and a half years.

Exscientia developed the drug with the use of an AI platform that utilized various algorithms to generate millions of potential molecule combinations. The AI then filtered through the generated molecules to narrow the field down to the best candidates that should be synthesized and tested.

The clinical trial comes as investments in AI-driven drug development is ramping up. AI has the potential to make drug discovery quicker and cheaper, with the average drug development cost being about 2.6 billion dollars. This means that new treatments for illnesses like heart disease and cancer could be produced more quickly. The drug that is to be tested in known as DSP-1181. Andrew Hopkins, molecular biologist, and chief executive of Exscientia, explained to Financial Times that the researchers only had to test approximately 350 compounds, which was about one-fifth of the normal number of compounds that are typically tested during drug development.

John Bell, the Regius professor of medicine at Oxford University was not involved with the research but explained the impact of the recent development to Financial Times:

“The design and development of molecules through medicinal chemistry has always been a slow and laborious process. Exscientia can do this in many fewer steps, which is really impressive, and it comes from very sound scientific principles.”

Exscientia will be working alongside other pharmaceutical corporations like Sanofi and Bayer in an attempt to find new treatments for diseases. While it has been claimed that the DSP-1181 is the first drug designed with an AI to be used in a clinical trial, ScienceMag reported that many other compounds have already seen human trials, including some drugs that have been tested to treat conditions like Parkinson’s and stroke.

As impressive as the achievements of Exscientia are, there are some problems that lie on the road to AI-enhanced drug development.

While AI can assist in the discovery and development of drugs, there’s no guarantee that the drugs discovered by the AI will be of particular use. It could be that the drugs discovered are extremely similar to molecules that humans have already studied. Hen combined with the fact that effective utilization of a drug depends on scientists understanding the nature of the illness they are trying to treat, AI drug development strategies may not transform the landscape of medicine as radically as some people hope.  Another issue that AI drug companies will have to deal with is the question regulation. The FDA is still attempting to decide the best way to regulate drugs discovered by AI systems, considering how the process differs from traditional drug research while trying to come up with regulatory strategies.

According to Vox, FDA spokesperson Jeremy Khan explained that any drugs developed with the assistance of AI should be held to the same standards as the current drug models, even though there may be differences in how the drug is discovered. Khan explained:

“The full role of AI in drug development is still being elucidated, and stakeholders understand AI in different ways considering the spectrum of tools and techniques covered under this umbrella term. Importantly, the evidentiary standards needed to support drug approvals remain the same regardless of the technological advances involved.”

Spread the love

Blogger and programmer with specialties in Machine Learning and Deep Learning topics. Daniel hopes to help others use the power of AI for social good.