The importance of AI-enabled drug research to develop effective therapies

Many of us interact with artificial intelligence (AI) in our everyday lives, from online searches and receiving personalized shopping recommendations to booking travel, making reservations and asking questions of digital assistants in our homes. The use of AI has been growing significantly because of its ability to carry out complex tasks rapidly and solve problems without human intervention.

AI’s ability to quickly scan and synthesize huge volumes of information is also being adopted for numerous healthcare initiatives, including use in pharmaceutical drug discovery and development.

The traditional process of drug discovery and development of just one new drug can take more than a decade and cost billions of dollars. Most drug candidates eventually fail to show effectiveness in clinical trials and large pharmaceutical companies often abandon investments in early development of drug candidates even before the clinical trial stage because of cost. As we learn more about human diseases and the complexity of human biology, it is clear that we need more sophisticated tools.

AI advantages in drug development

There are many benefits to using AI in drug development, including the ability to speed the rate of discovery while reducing the need for extensive lab work and shortening the clinical trial phase.

AI is also used to search for and find existing drugs that may be effective for newly discovered diseases. During the rapidly escalating and deadly Covid-19 pandemic, researchers applied AI to evaluate existing drugs that could be repurposed to treat Covid-19, alone or in combination with other drugs, without causing serious complications.

In spite of recent interest, the use of computational and data sciences has not evolved as fast in basic science research and clinical trials as it has in other sectors; however, evidence of its benefits has been growing.

Here are some of the potential advantages of using AI in drug development:

• Target identification: AI can be used to screen through vast amounts of structured and unstructured data to enhance understanding of a disease and identify relevant drug targets more accurately.
• Lead compound generation: AI can help screen through trillions of molecules to identify the most promising ones; or predict protein structures and interactions to increase the likelihood that the compounds will be effective.
• Predicting efficacy and safety: AI can be used to predict absorption, distribution, metabolism and excretion (ADME) properties in silico or to evaluate whether a drug compound that works in animal models would work in humans and also predict safety issues.
• Patient selection: AI can help determine which populations would most likely respond to a therapy to develop right inclusion and exclusion criteria and biomarkers.
• Preventing patient drop-out in clinical trials: AI can be used to develop “patient companions”—digital personalized messaging to support patients during the trial to encourage their continued participation and ask for feedback. AI can also give tailored responses to participant questions.
• Finding ideal sites to perform clinical trials: Since some sites have difficulty recruiting or enrolling patients in trials, AI can be used to understand those demographic variables and see what trials competitors are running at those same sites.

AI use in clinical trials

Importantly, AI, in combination with computational biology and modeling, can be used to form a synthetic control arm of a study to compare experimental drugs to the standard of care, other drugs or drug combinations. This is a relatively new and growing area known as ‘in silico’ clinical trials, where disease-specific computer models form virtual cohorts for testing the safety and/or effectiveness of new drugs.

By using in silico trials, we can incorporate different parameters of disease, age and sex, for example, one at a time and in different combinations, to test the potential effectiveness of a drug among thousands of virtual patients. We have the potential to look at thousands of variations. We can test multiple compounds, which cannot be done in the traditional clinical trial setting. Therefore, we can obtain statistically significant results with fewer unsuccessful trials.

AI may also alleviate the need for animal testing on some levels. In silico, modeling of translational medicine gives drug developers a better idea of how a drug will react in the human body rather than seeing how animals react and hoping the same effect will translate in humans. Almost 90% of drugs that show promise in animal research fail to be safe or effective for humans.

AI’s ability to reduce the cost of drug development 

Finally, there is the cost factor. We know the expense involved in developing new and better therapies. By being able to design drugs faster with better efficacy and fewer side effects, pharmaceutical manufacturers can develop and eventually sell drugs in a more affordable way.

I believe that in five to 10 years of increased use of AI in drug development and testing, we will see a completely changed structure of economics in pharmaceutical development. This is especially important for narrowly targeted therapies and therapies for orphan diseases—those affecting a smaller number of patients, where making the investment in drug development may not be in balance with the rate of return.

The increasing use of AI will also create opportunities for new, smaller companies to succeed in the drug development field.

The further refinement and use of AI in drug development will be essential in order to continue a patient-centric approach to care, improving and extending the lives of people – even those with rare but serious disorders for whom there is not a large financial incentive to devote the time and resources it takes to develop effective new therapies in a traditional way.

Photo: metamorworks, Getty Images

This post appears through the MedCity Influencers program. Anyone can publish their perspective on business and innovation in healthcare on MedCity News through MedCity Influencers. Click here to find out how.