Robot scientist Eva found a new cure for malaria
Researchers from Cambridge and Manchester universities have proven the ability of Eva, a robot scientist, to find a cure for malaria . To do this, Eva scanned ten thousand combinations of substances every day and tested them on genetically modified yeast to check for toxicity to human cells. As conceived by its creators, Eve will make the process of finding drugs faster and cheaper.
Artificial intelligence allows Eve to learn. She chooses compounds that are active in relation to the goal - in this case they were plasmodia, unicellular parasites, pathogens of malaria. The drug must meet another important requirement: it should not harm the person. Lack of toxicity is tested on genetically modified yeast.
Eva herself chooses from the library, in which about fifteen thousand compounds are suitable, and sets up experiments up to ten thousand times a day. She checks some substances several times to make sure that they are useless.
')
To choose drugs, Eva uses active learning - one of the ways of machine learning. The algorithm independently assigns the following situation to be studied. This approach will minimize the consumption of the material under study, that is, save the manufacturer of drugs.
From the start of drug development to its entry into the market, it takes ten years, the cost on average is about a billion dollars. And diseases that kill millions of people adapt to the drugs. Therefore, it is important to automate the search process and make it more efficient.
Eve at work
Artificial intelligence allows Eve to learn. She chooses compounds that are active in relation to the goal - in this case they were plasmodia, unicellular parasites, pathogens of malaria. The drug must meet another important requirement: it should not harm the person. Lack of toxicity is tested on genetically modified yeast.
Eva herself chooses from the library, in which about fifteen thousand compounds are suitable, and sets up experiments up to ten thousand times a day. She checks some substances several times to make sure that they are useless.
')
To choose drugs, Eva uses active learning - one of the ways of machine learning. The algorithm independently assigns the following situation to be studied. This approach will minimize the consumption of the material under study, that is, save the manufacturer of drugs.
From the start of drug development to its entry into the market, it takes ten years, the cost on average is about a billion dollars. And diseases that kill millions of people adapt to the drugs. Therefore, it is important to automate the search process and make it more efficient.
Eve at work
Source: https://habr.com/ru/post/376227/
All Articles