Artificial intelligence created a new medicine in just 21 days

Artificial Intelligence has succeeded already in manyareas of our lives. And basically AI finds its application in the field of complex computing, building mathematical models, and so on. However, in the medical field, artificial intelligence can be no less useful (do you follow the progress of AI? We regularly talk about them in our Telegram channel). For example, recently the Hong Kong-based company Insilico Medicine published the results of a study showing that its system based on AI and deep learning can create new drugs against certain pathologies in just 3 weeks. And this is several tens of times faster than traditional methods.

The use of AI in drug development is an extremely promising technology

How Artificial Intelligence Creates Medicines

AI from Insilico Medicine is calledGENTRL. Moreover, it is noteworthy that our compatriot Alex Zhavoronkov is at the helm of the company. Mr. Zhavoronkov in the mid-2000s received a master's degree at Johns Hopkins University, and then a doctorate at Moscow State University, where his research focused on the use of machine learning to study the physics of molecular interactions in biological systems. In 2006, he managed to work for ATI until it was acquired by AMD chip maker. In 2014, Alex founded the already mentioned Insilico Medicine, having behind him experience in the high-tech industry and becoming interested in pharmacy issues.

Interesting: How Artificial Intelligence Works

If you go back to AI, then the developers themselvesthey call the basic technology of artificial intelligence “generative tensor training”. It allows AI, if not to go into details, to learn the required skills more efficiently and quickly.

We thought: can we make machines invent new molecules with certain properties from scratch instead of forcing them to sort through dozens of available options, says Alex Zhavoronkov.

Insilico used GENTRL in order tocreate several (and to be precise, 6) drug options for the treatment of muscle fibrosis. The developed drugs inhibit the DDR1 receptor, which is involved in the development of the disease. For this, AI took 21 days, after which scientists chose the most suitable drug options and tested them on laboratory animals. It took another 25 days. Thus, it took only 46 days to select a potential medicine. For comparison, the traditional process of developing drug candidates takes about 8 years and costs companies several million US dollars. While the creation of AI took only 150 thousand dollars.

On the left is normal muscle tissue. Right - tissue with the development of fibrosis

However, Insilico emphasize that they are not yetproved that the new drug is more effective than existing drugs. However, the time and cost that scientists took to create potential drugs is much less than traditional pharmacy methods. Their work was to demonstrate the huge potential of artificial intelligence based systems in the development of new drugs. Now, scientists are focused on improving the technology and, naturally, on testing the effectiveness of new drugs developed by AI.