A company based in the UK, for example, has created algorithms that search through research papers, clinical trial results and other sources of biomedical information to look for relationships between genes, drugs and diseases. This machine learning technology is able to systematically analyse and understand connections between data, and then uses AI to extrapolate the connections (more information here). On top of this, deep learning is emerging as an aspect of machine learning that goes one step further. It uses a multi-layered analysis to simulate the way a human mind processes data. In contrast to machine learning, deep learning algorithms determine for themselves whether their prognosis is right or wrong (see more detail here).

Machine learning and deep learning are already an indispensable part of the scientific process, as this article explains. And this trend is widely predicted to gather pace as the technology improves, with exciting potential for the pharmaceutical industry. Many pioneering companies and start-ups are already working on AI-driven solutions to optimise the drug discovery process. Grünenthal, for example, is cooperating with a specialised vendor to create algorithms that can generate and optimise molecules based on data from the company’s research projects. This is particularly exciting because drug development is such an elaborate process. Machine learning and deep learning have the potential to increase the success of research and development in the pharmaceutical industry – and contribute to the development of new medicines that improve quality of life for patients worldwide.