The Potential of Artificial Intelligence in Pharmaceutical Drug Development

By Lukas Dittrich

Cutting-edge technologies are increasingly entering pharma’s Research & Development (R&D) processes as the use of Artificial Intelligence (AI) and machine learning in the early stages of drug discovery and development has the potential for various research needs.

Currently, AI and machine learning are two of the most-used buzzwords that are linked to digitization. Almost every industry has involved AI and machine learning technologies in their businesses as they seem to be applicable to every use-case. The possibilities seem limitless, and it looks like we just need to train machines to learn and evolve to enhance production and cost efficiency.
One of the key topics in 2018 is how AI can transform the current pharmaceutical industry. In fact, over the last years, pharma companies have been looking to Artificial Intelligence as a potential tool to help facilitate drug research, reduce development costs and enhance efficiency.
A high number of articles about the impact of these new technologies on the pharma industry have been written. However, there is the need to explore AI and machine learning’s impact on drug R&D processes.

The Returns on Pharma R&D Investments are Falling

Over the last years, the global pharmaceutical industry has been facing several challenges, with most of them originating from the increasingly long and complex process of drug development. The entire industry is experiencing a steady decay, and many studies suggest that it is on the brink of terminal decline.

The Tufts Center for the Study of Drug Development estimates that the average development time of a new drug exceeds 12 years and costs between 2.0 and 2.6 billion USD, including costs for failed projects and opportunity costs in R&D projects. Statistically, only one every five to ten thousand initial drug candidates is eventually approved and brought to the market. In the face of such pressure, pharma companies are eager to reduce the cost of drug development, so that consumer prices can be lowered without sacrificing profits.

How AI can Revolutionize the Pharmaceutical R&D

Pharmaceutical giants such as Merck & Co, Johnson & Johnson and Sanofi are exploring the potential of AI to help streamline their drug discovery process.

The chart below shows exemplary application fields where Artificial Intelligence could enable a faster and more efficient completion of time-intensive and repetitive tasks compared to the traditional process.

Source: CLR Analysis

Start-ups are Driving Pharma Innovation

Recently, also many newborn start-ups are offering some unique solutions using machine learning and AI in the pharmaceutical industry. In this booming market, which spans from diagnostics to drug discovery, our research identified close to 30 different start-ups that are actively trying to bring Artificial Intelligence to the drug development process, using different stages and approaches to do so.
The chart below illustrates our shortlist of the most established and promising start-ups based on their value proposition and targeted process stage.

Source: CLR Analysis

Two of the more prominent start-ups in this growing field are Exscientia and Benevolent AI, with the former getting funded by Evotec and collaborating with GSK, while the latter has been raising over 200 million USD in funding over the last five years.  The potential for cost-reduction these start-ups present is exemplified by the amount of funding that they are receiving, as well as the high number of partnerships big pharma corporations are proposing to them.

There are Still a Lot of Challenges Ahead

Even if without question the implementation of AI in the pharma industry is experiencing great developments, there are still big challenges limiting its potential in the R&D process. For instance, the biggest challenge is that most of the above mentioned and identified start-ups focus only on the preclinical stages of drug development. Their goal is, in fact, to identify better drug candidates and speed up the overall development while using resources more efficiently, which is naturally the area where AI can play out its strengths.

However, an acceleration of the preclinical development does not influence the number and length of clinical trials required, which today make up more than 50% of the total costs and face increasing regulatory changes and requirements. This problem is based on the fact that even promising test results in an in-vitro environment often show undesirable effects when transferred to in-vivo testing in mice and later human patients due to the sheer complexity of the interaction between drug and body.

Of course, there are also companies that are working on improving the transferability of in-vitro or in-silico results to in-vivo tests. But the regulatory approval or a potential substitution in the future for actual clinical trials has still a long way ahead.

The Future of AI in the Drug R&D Process

There is still a lot of scepticism around whether AI can actually improve drug development efficiency. The application of AI in pharma is just at its initial stage, and it could take decades to reach its full potential. However, the current activities in the area hint towards a strong potential of AI that could relieve big pharmaceutical companies of a lot of pressure. Pressure that is a result of increasing regulatory requirements and shrinking margins, of competitive pressure due to generics and biosimilars as well as drugs losing patent protection.

Therefore, while AI has great potential to speed up the preclinical drug development, reduce costs and lead to more and better drug candidates, there are still some core issues that limit its impact on the overall process.

Feel free to contact CLEVIS RESEARCH at info@clevis-research.de to get to know more about our services.