Skip to main content

Artificial Intelligence predicts the frequencies of drug side effects

Dr Diego Galeano and Prof Alberto Paccanaro develop the first Machine Learning method for the prediction of the frequencies of drug side effects

  • Date11 September 2020

Dr Diego Galeano, who recently completed his PhD in the Department of Computer Science at Royal Holloway, together with his supervisor Prof Alberto Paccanaro, have published their work in Nature Communications.

Picture 1.jpg

A central issue in drug development is the identification of the frequencies with which side effects will appear in the population. Currently, these frequencies can only be experimentally determined by pharmaceutical companies through clinical trials before a drug enters the market. Unfortunately, this process has several limitations and numerous side effects are only discovered after the drug is already on the market. For this reason, drug side effects remain a leading cause of illness and mortality in healthcare.

We have developed the first method for computationally predicting the frequencies of drug side effects in the population. Our machine learning algorithm, based on matrix decomposition, learns a small set of components (latent features) that encode the biological interplay between drugs and side effects. In our paper, we show the usefulness of our approach for drugs from multiple therapeutic classes (e.g. nervous system drugs) and side effects belonging to all physiological systems (e.g. psychiatric disorders)

A very important aspect of our machine learning model is that its predictions are explainable, and its individual components can be interpreted in terms of drug effects on specific physiological systems (e.g. cardiovascular or nervous systems). We also show that these components capture shared drug clinical activity, drug targets and anatomy/physiology of side effects. Thus, our model is informative of the biology underlying drug activity. 

Dr Shantao Li and Prof Mark Gerstein from Yale University contributed to the evaluation of the biological relevance of the results and are also authors of the paper.

The journal: Nature Communications (Impact Factor > 12) is an open access, multidisciplinary journal dedicated to publishing high-quality research in all areas of the biological, health, physical, chemical and Earth sciences. Papers published by the journal aim to represent important advances of significance to specialists within each field.


Explore Royal Holloway

Get help paying for your studies at Royal Holloway through a range of scholarships and bursaries.

There are lots of exciting ways to get involved at Royal Holloway. Discover new interests and enjoy existing ones

Heading to university is exciting. Finding the right place to live will get you off to a good start

Whether you need support with your health or practical advice on budgeting or finding part-time work, we can help

Discover more about our 21 departments and schools

Find out why Royal Holloway is in the top 25% of UK universities for research rated ‘world-leading’ or ‘internationally excellent’

Royal Holloway is a research intensive university and our academics collaborate across disciplines to achieve excellence.

Discover world-class research at Royal Holloway

Discover more about who we are today, and our vision for the future

Royal Holloway began as two pioneering colleges for the education of women in the 19th century, and their spirit lives on today

We’ve played a role in thousands of careers, some of them particularly remarkable

Find about our decision-making processes and the people who lead and manage Royal Holloway today