Artificial intelligence has been taught to accurately predict a person’s response to a new drug

(ORDO NEWS) — Work on new drugs is ongoing, and one of the main problems is the need for long-term studies that stretch over years and cost billions. A new neural network can facilitate and speed up this stage.

Scientists at the Center for Graduate Studies at the City University of New York have introduced an algorithm called CODE-AE. It can test new drug compounds and accurately predict their effectiveness in humans.

During the trials, it was theoretically possible to find personalized medicines for more than 9,000 specific patients. In the future, this can significantly improve accuracy, reduce the time and cost of drug development.

What is known about CODE-AE

In the work, data on the cells of patients were analyzed. An array of real characteristics of their condition was loaded into the system, which then analyzed how they work.

Then drugs were “added” there and they observed how the initial virtual cells reacted to this or that composition.

Using CODE-AE, we tested 59 drugs in 9808 cancer patients.

Our results are consistent with existing clinical observations, the scientists write in the report.

Accurate and reliable prediction of a patient’s response to a new chemical compound is critical to the discovery of a new drug and the selection of an already available drug for a particular patient.

However, early testing directly on humans is unethical and legally impossible. This is the main factor in the high cost of research and its duration.

Our new machine learning model can handle the problem.

CODE-AE takes advantage of biology-inspired design and takes advantage of the latest advances in machine learning,” said Lei Xie, Professor of Computer Science, Biology and Biochemistry.

The next challenge for the research team is to develop a way to reliably predict the effects of new drug concentrations and their metabolism on the human body.

The researchers also noted that the neural network can be configured to accurately predict the side effects of a drug in a particular person.

It should be noted that in recent years, personalized medicine has been gaining popularity, when drugs and treatment approaches are selected for a specific patient, sometimes at the cellular level.

Therefore, such technology will help move in this direction.


Contact us: [email protected]

Our Standards, Terms of Use: Standard Terms And Conditions.