The development of new drugs or more effective drugs to treat medical conditions can revolutionize healthcare, and drug discovery is an important part of the business of pharmaceutical companies. However, it is difficult to find which drugs are effective in treating which conditions. Identifying and screening candidate drugs is usually time-consuming, making the search for new drugs slow, uncertain and very expensive.

In modern science, it is not for lack of data. Much data exists on how small molecules interact with biological systems such as proteins. However, sifting through all this data to find promising combinations of molecules and biological pathways to treat particular conditions is very slow. Machine learning offers a way to overcome this problem.

We recently reported on Alphafold, a machine learning tool capable of predicting protein structures with much greater reliability than previous tools. Other programs already exist that can predict the structures of small molecules, which are much easier to determine from their chemical composition than the structures of proteins. Based on the predicted structures of proteins and small molecules, machine learning can predict their interactions and work through libraries of molecules to identify drug candidates much faster than would be possible with human effort alone.

This type of processing can identify entirely new drugs, but can also be used to identify new applications of existing drugs. Identifying new uses for existing drugs can be particularly valuable, as manufacturing capacity and detailed side effect data may already exist, which may allow the drug to be repurposed more quickly to treat a new condition.

Machine learning can not only identify molecules that may interact with a target protein, but may also be able to extrapolate properties such as toxicity and bioabsorption using data from other similar molecules. In this way, machine learning algorithms could also efficiently perform some of the first steps in in silico drug testing, reducing the need for expensive and time-consuming laboratory tests.

Other applications of machine learning in drug discovery include personalized medicine. A major problem with some drugs is the varying response of different individuals to the drug, both in terms of effectiveness and side effects. Some patients with chronic conditions such as high blood pressure may spend months or years sifting through alternative medications to find one that is effective and has acceptable side effects. This can represent a huge waste of time for the doctor and create significant inconvenience for the patient. Using data on the responses of thousands of other patients to different drugs, machine learning can be used to predict the effectiveness of those drugs for specific individuals based on genetic profiling or other biological markers.

Identification of drug candidates as discussed above relies on knowing the biological target it is desirable to affect, so that molecules can be tested for their interaction with relevant proteins. However, at an even higher level, machine learning techniques can enable the identification of entirely new mechanisms for the treatment of medical conditions.

There are many studies in which participants have their genetic data sequenced and correlated with data on a wide variety of different phenotypes. These studies are often used to try to identify genetic factors that affect an individual’s risk of developing a disease. However, machine learning techniques can also identify correlations between medical conditions and other measurable parameters, such as the expression of certain proteins or levels of particular hormones. If plausible biological pathways can be determined using these correlations, it could even lead to the identification of entirely new mechanisms by which certain conditions could be treated.

Examples of AI-based drug discovery already exist in the real world, with molecules identified using AI methods having undergone clinical trials. Many companies are using AI technology to identify potential new drugs and predict their effectiveness for individual patients. Some estimates suggest that more than USD 2 billion in investment funds were raised by companies in this technology field in the first half of 2021 alone. As with any technology, the patents held by these companies allow them to protect their intellectual property. and to ensure their safety and that of their business partners.

Machine learning excels at identifying patterns and correlations in huge datasets. Harnessing this capacity for drug discovery has the potential to dramatically improve healthcare outcomes for patients and streamline the cumbersome and costly process of developing new treatments. We may be on the threshold of a new era of personalized medicine and rapid drug development.

The content of this article is intended to provide a general guide on the subject. Specialist advice should be sought regarding your particular situation.