UK (Commonwealth Union) – Drug discovery has generally been a time-consuming and costly endeavor. AI (artificial intelligence) is changing this landscape by significantly accelerating the identification of potential drug candidates. Machine learning algorithms can analyze vast datasets, including genetic information and chemical properties, to predict the most promising compounds. This not only saves time but also reduces the need for extensive laboratory experimentation.
Furthermore, AI-driven algorithms can simulate the behavior of molecules and predict their interactions with biological targets. This predictive modeling enables researchers to design drugs with higher specificity and efficacy, ultimately increasing the success rate of drug development.
Identifying the right biological target for a drug is critical. AI helps pharmaceutical researchers by mining biological data and identifying potential targets that were previously overlooked. These AI-powered insights lead to more precise drug targeting and, consequently, more effective treatments.
A collaborative effort between the UCL Global Business School for Health (GBSH) and the University College London (UCL) School of Pharmacy is harnessing data collected from an innovative “electric tongue” device to construct an AI model capable of forecasting the bitterness of pharmaceuticals.
The importance of taste cannot be understated, as it plays a crucial role in ensuring individuals adhere to their medication regimens and is a vital aspect of drug development. Taste aversion is particularly significant for children taking medications, where it serves as a major impediment to compliance. However, it is also a pertinent concern for adults, especially those on long-term medication regimens, such as individuals managing HIV.
Dr. Hend Abdelhakim, heading the research team at the UCL Global Business School for Health, employed an “e-tongue,” a device equipped with sensors that respond to taste, to assign bitterness scores to various medicines. This allowed the team to estimate the expected aversiveness associated with the intended clinical dosages of these drugs.
The e-tongue functions by gauging how strongly bitter molecules adhere to a plastic sensor, simulating the human tongue’s response, and subsequently comparing this measurement to a reference sample. The disparity between these measurements provides an approximation of a drug’s theoretical bitterness level.
Employing the e-tongue expedites and enhances drug testing when compared to the conventional method of conducting human trials. Furthermore, the research team is now collaborating with machine learning experts, including Dr. David Shorthouse from the UCL School of Pharmacy, to expedite drug development further through the utilization of an AI model.
The AI model, which utilizes data collected by the e-tongue, dissects a drug into a series of molecular descriptors (such as the number of atoms and total surface area of the molecule) that determine its taste. This enables the model to predict the levels of bitterness associated with the pharmaceutical compounds.
Crucially, the developed model is intended to be an open-access tool, facilitating global access to valuable data regarding the palatability of medicines, thereby benefiting pharmaceutical development efforts worldwide.
Dr Abdelhakim told the Telegraph, “We run a machine learning algorithm to basically see what’s the chemical structure, what’s the molecular structure, what are the other chemical physical parameters that make it bitter, and try to see if there’s a relationship.”
Dr Abdelhakim elaborated that taste in medicines was a particular issue for children that had a “heightened sense of taste”.
“It’s a problem for longer term diseases, so for example, HIV,” added Dr Abdelhakim. “Antiretroviral medicines don’t taste very well. So, if the patient has to take those pills every day for life, it’s a much bigger problem, especially if they start them very, very young. Even if it’s a wonder drug, if the patient doesn’t take it, it won’t work.”
The rapid utilization of AI in a wide variety of fields in medicine is likely to increase in the years ahead and with taste being a key in medicine consumption, the role of AI is likely to be further enhanced.
