Meet Eve, the first robot scientist that could make discovering new drugs both faster and cheaper.
Eve is the brainchild of researchers at the Universities of Aberystwyth and Cambridge, who previously gave us Adam, the first robot ever capable of making scientific discoveries.
Eve's purpose, though, is more specific than her predecessor's. Eve's job is to search through chemical compounds, test them and determine which ones are potential candidates for future drugs that can target diseases like malaria, African sleeping sickness and Chagas disease.
Eve targets these diseases because the drug discovery process for these illnesses is currently too expensive and time-consuming. However, these diseases are still deadly, meaning that new drug discovery targeting these illnesses is vital. This is where Eve comes in: it makes the process fast and cheap, so it's more economically viable than human-operated drug discovery methods.
Eve works a lot like a human scientist. It generates data and records knowledge, which allows it to develop and test hypotheses and even change them, if needed. It can repeat experiments and continue through with the scientific method until it finds a solution. Most impressively, though, is that Eve can do all this faster than any human: it can screen over 10,000 potential compounds per day.
"Eve exploits its artificial intelligence to learn from early successes in her screens and select compounds that have a high probability of being active against the chosen drug target," says Professor Steve Oliver from the Cambridge Systems Biology Centre and the Department of Biochemistry at the University of Cambridge.
Eve also has algorithms that allow it to randomly select which compounds to start testing first, with those drugs with potential getting re-tested multiple times, preventing false positives. Machine learning, along with statistical data, allows Eve to choose which compounds are most likely to give positive results.
In Eve's first tests, the robot looked for compounds that would target parasites responsible for malaria. Eve discovered one particular compound, previously considered as an anti-cancer drug, that inhibits the parasite responsible for malaria. Considering that these parasites have built up a resistance to current treatment methods, Eve's first experiment possibly discovered a new drug in the fight against the disease.
The only thing Eve can't do in the drug discovery process is synthesize compounds, but researchers want to add that feature next. That would make Eve a one-stop shop drug discovery and delivery factory.
"Every industry now benefits from automation and science is no exception," says Professor Ross King, from the Manchester Institute of Biotechnology at the University of Manchester. "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."
