Scientists use machine learning to improve drug research




Scientists have succeeded in finding potential medicines faster with machine learning. After training, the technology can better predict which molecules have desirable properties compared to conventional systems.

The machine learning technology was developed by scientists from the authoritative institute MIT. According to the researchers, a model was developed that was subsequently trained with a dataset with data of approximately 250,000 molecules, with different properties. The intention was that the system would use the data to predict how molecules can best be optimized to serve as potential drugs.

From MIT’s experiments it appears that the machine learning model is better able to optimize molecules than existing systems after training; via machine learning, properties such as synthetizability and solubility were better achieved. Even if the system was asked to find the best ‘basic molecule’, it performed better than conventional systems.

In drug development, a basic molecule is usually chosen in the lab that contains desired properties, such as binding to a particular receptor in the body. Subsequently, with a so-called lead optimization process, the basic molecule is further improved, so that it acquires properties that are important for medication, including the ability to easily manufacture it, or to dissolve it properly in liquids. The optimized molecule is then, after the necessary tests, tested for laboratory animals before being tested on humans.


In: A Technology & Gadgets Asked By: [22618 Red Star Level]

Answer this Question

You must be Logged In to post an Answer.

Not a member yet? Sign Up Now »