How AI Will Disrupt Drug Development

For almost 30 years, life science companies have been using computational methods to discover drugs. However, latest technological advancements make drug design process quicker and more effective. In this article, Egor Kobelev discussed how breakthroughs in AI and ML are revolutionizing drug discovery.
All articles
By Egor Kobelev
VP of Healthcare Technology, USA
How AI Will Disrupt Drug Development

In the last four to six years, companies have been experimenting with new approaches that utilize the latest in artificial intelligence and machine learning technologies to identify new molecules and validate new drugs faster and more efficiently. This article will focus on some of the ways these breakthroughs are transforming drug discovery.

Companies like Schrodinger have been using computational methods to discover novel targets and drugs for almost 30 years. Schrodinger’s approach focuses mainly on proteins. Using a database of protein structures, they develop compounds based on biophysics, machine learning, and the binding properties of molecular docking.

For a while, this was the only model that worked. Schrodinger has built a successful business over the last three decades, offering software and services meant to help discover small molecules and optimize them for potential targets. But times have changed. Schrodinger has had to adjust its business model to include the development of therapeutics, along with its more traditional molecule discovery services.

This move signals a broader industry shift over the last four to six years. The community has been wondering how far we can push the drug design process—how much faster and more efficiently we can identify new molecules and validate new drugs.

Below are just a few of the ways breakthroughs in artificial intelligence (AI) and machine learning (ML) are revolutionizing drug discovery.

Advancing Approaches to Molecule Discovery

With AI’s growing influence in the tech world, industry experts and researchers have been trying to use this burgeoning tech to solve practically any issue they come across. This approach makes sense for some industries more than others, especially those with large amounts of data. The drug industry fits that bill in spades.

Some companies, like Atomwise and Exscientia, are using AI to revolutionize tried-and-true approaches. Essentially, they are using pattern recognition to discover small molecules that can lead to the creation of drugs. While their approach is similar to Schrodinger’s, the math used to drive their discoveries is very different, and they lean heavily on ML.

Younger companies like Cyclica, Cloud Pharmaceuticals, and E-Therapeutics have waded into the field more recently, and new start-ups are popping up every year. The market for this new approach to some older concepts and ideas is growing because these new methods are finally producing practical results.

Shortening Discovery Time

Researchers at Johns Hopkins University and In-Silico Medicine recently published a paper in the journal Nature Biotechnology claiming they were able to identify a new compound for a particular target within three weeks using neural networks. 

While the merit of these claims was debated, the idea of drastically cutting down the five to eight-year drug discovery process is incredibly attractive. 

Taking Advantage of Existing Data

Over the last few decades, drug companies and academics have been collecting data. In the course of their research, they have accumulated more information on molecules and compounds than any team of humans could ever sift through with a reasonable level of efficiency. And as measuring capabilities increase, data collection is only getting more sophisticated and complex. For AI researchers, that is a potential goldmine.

With the newer deep learning AI techniques developed over the past few years, analyzing this information could take a few days rather than years.

Potentially, companies could look at publicly available databases of compound binding, like drug databases, and then, with an understanding of the patterns of safety and efficacy for millions of such compounds, create their own predictive algorithms using neural networks or other machine learning tools.

The beauty of this approach is that it is not terribly complicated. With access to large databases that have been built over the years through academic research, and combining those databases with machine learning approaches to match patterns with the desired outcome, a company could ultimately deliver a new and interesting molecular lead. As long as the right database exists to train the machine learning models, putting this method into action could be both simple and fruitful.

Linking compounds in databases to typical outcome metrics, or measures of how compounds perform in relation to a specific disease like cancer, could also result in more targeted drug design and discovery.

In this technique’s infancy, the scope may be restricted to one disease, which, due to the sheer volume of research, would likely be cancer. But it doesn’t have to stop there.

Only around 1,500 drugs have been approved by the FDA, but hundreds of thousands, if not millions, of compounds have been tested in clinical trials and pre-clinical experiments. This abundance of data, which may have previously been seen as not very useful, will now be more important than ever. This data has yet to be repurposed, but with the power of AI, it could potentially contain the key to the next generation of pharmaceuticals.

Removing Human Inefficiencies

Generally, a large amount of the pushback against using machine learning to discover new drugs or novel compounds stems from a romanticized idea of human expertise–or to put a finer point on it, that no collection of code could match the expertise that comes from decades of medical research experience. The point has some validity, but it only goes so far.

Yes, AI systems have yet to match the sophisticated ability of a team of human experts. These systems are fallible, and they can make mistakes or miss things.

But, so do humans. We are inherently imperfect, and mistakes will inevitably be made. At the end of the day, a compound is either useful or not, and whether that compound was discovered by a team of human experts or a sophisticated computational model is irrelevant. The question is which method is more efficient?

While both humans and machines make mistakes, human mistakes are random while machine mistakes are systematic. The beauty of systematic mistakes is that they can potentially be fixed, and the system could become more efficient over time. Measures can be put in place to reduce human error, but that is not the same as changing a line of code or honing an algorithm. 

Ultimately, what matters is the method that discovers the most usable compounds. 

Linking Discoveries with Outcomes

In this new AI-driven future, the ideal drug discovery and design team can be relatively small. Currently, some teams are as small as several people, but they are extremely focused and specialized.

Such small teams could work from a large data set, and they would not necessarily need a software development team. Instead, they would need two main components–experts in training and building statistical models through machine learning, regression, or any other method, and experts in structural biology and biochemistry. The former may seem obvious, but the latter, while equally, if not more important, is often overlooked or undervalued.

Biological experts are needed to help connect the discoveries made by the algorithms with actionable results, blending the pros of both machine and human expertise and demonstrating that the discovery methodology is uncovering meaningful outcomes.

Weighing the Pros and Cons

If the integration of AI into the drug discovery and design process works, it could have incredibly disruptive effects, both positive and negative.

On the one hand, it could disrupt entire segments of the industry, putting many chemoinformatics employees out of jobs.

On the other hand, cutting down discovery from years to months would have an almost incalculable effect on big pharma. An industry that justifies the high prices of its products by pointing to the lengthy and costly research and development phase would be empowered to make more drugs quickly and affordably, resulting in lower drug prices. Even with the possibilities for negative disruption, it seems like a gamble worth taking.

Along with healthcare and life sciences industry knowledge, DataArt has a vast expertise in AI and ML, training and building statistical models through machine learning, regression, or any other method. Contact us today if you’re looking for a technical partner to bring this expertise to your project.

Sign Up for Updates!

Subscribe now to receive industry-related articles and updates

Choose industries of interest
Thank You for Joining!

You will receive regular updates based on your interests. No spam guaranteed

Add another email address
Sign Up for Updates!
Choose industries of interest
Thank You for Joining!

You will receive regular updates based on your interests. No spam guaranteed

Add another email address
We are glad you found us
Please explore our services and find out how we can support your business goals.
Get in Touch Envelope