AI scientist Eve finds toothpaste ingredient may help fight malaria

The AI system, dubbed ‘Eve’ by the scientists at the Universities of Manchester, Aberystwyth and Cambridge responsible for developing and employing it, speeds up the drug discovery process by automating the established processes of high-throughput, hypothesis-led research.

As well as developing and testing hypotheses to explain observations, and running experiments using laboratory robotics, Eve is able to interpret the results, amend the hypotheses and repeat the cycle.

One series of experiments has discovered that triclosan, an ingredient found in many toothpastes, could help the fight against malaria, which  kills over half a million people each year, predominantly in Africa and south-east Asia. While a number of medicines are used to treat the disease, malaria parasites are growing increasingly resistant.

The trials involving Eve focused on triclosan, which is used in toothpaste to prevent the build-up of plaque bacteria by inhibiting the action of an enzyme known as enoyl reductase (ENR). Scientists have known for some time that triclosan also inhibits the growth in culture of the malaria parasite Plasmodium during the blood-stage, and assumed that this was because it was targeting ENR, which is found in the liver. However, subsequent work showed that improving triclosan's ability to target ENR had no effect on parasite growth in the blood.

With Eve’s help, the research team discovered that triclosan affects parasite growth by specifically inhibiting an entirely different enzyme of the malaria parasite, DHFR, which is the target of a well-established drug, pyrimethamine. They showed that triclosan was able to target and act on DHFR even in pyrimethamine-resistant parasites. Because triclosan inhibits both ENR and DHFR, they say it may be possible to develop a new drug that targets the parasite at both the liver stage and the later blood stage, making it harder for it to evolve resistance.

Professor Ross King from the Manchester Institute of Biotechnology at the University of Manchester, who led the development of Eve, believes AI-based approaches like this could greatly speed up the drug discovery process. "Artificial intelligence and machine learning enables us to create automated scientists that do not just take a 'brute force' approach, but rather take an intelligent approach to science,” he said.