Scientists at Cambridge University and the University of Manchester have demonstrated that their robot scientist Eve is capable of speeding up the search for new drugs and could transform the global pharmaceutical industry.
Eve is a robotic scientist developed by researchers from the Universities of Aberystwyth and Cambridge, the same team who created the robot Adam back in 2009. Robot scientist Eve cost about $1 million to build and is able to be left on her own for days to design experiments, carry them out, analyze samples, take down results from the experiments and then move on to the next experiment. Eve was created specifically to automate the early stages of drug design, she’s capable of scanning over 10,000 compounds a days, whereas human obviously wouldn’t be able to process as many in the same timeframe.
Eve uses a smart screening system based on genetically engineered yeast, whereby one strain of the yeast is dependent on a parasite in order to grow, while another strain is dependent on an enzyme similar to human proteins. “Eve is much more robust and better at multitasking,” Cambridge University’s Professor Steve Oliver, who directs the Systems Biology Center says. “ In the case of drug screening, she can search her library and select compounds that have a high probability of being active against the chosen drug target and she will prioritise screening them.” By doing this, Eve offers significant savings in both time and money as scientists normally need to manually screen a whole library in order to find compounds that match the samples.
Professor Ross King, from the Manchester Institute of Biotechnology at the University of Manchester, says: “Every industry now benefits from automation and science is no exception. Bringing in machine learning to make this process intelligent, rather than just a ‘brute force’ approach could greatly speed up scientific progress and potentially reap huge rewards.”
To test the viability of the approach, scientists describe how Eve has been able to identify promising new candidates for malaria and neglected tropical diseases such as African sleeping sickness and Chagas’ disease. Eve compared assays targeting key molecules in parasites responsible for these diseases with library of approximately 1,500 clinically approved compounds. The robot discovered a compound previously investigated as an anti-cancer drug is able to stop DHFR, a key molecule in the malaria parasite. Although there are already drugs that resist this molecule and are currently given to over a million children to protect them from malaria, new strains of parasites continue to emerge that are resistant to existing drugs, so new drugs are urgently needed to combat this.
The AI is still young, and she’s bound to go through more upgrades before she gets to help out more scientists and companies. Professor King believes her recent findings might end up being ‘more significant than just demonstrating a new approach to drug discovery,’ though. “Despite extensive efforts no one has been able to find a new antimalarial that targets DHFR and is able to pass clinical trials.