Artificial intelligence (AI) can help identify molecules that could become new medicines for psychiatric disorders. AI can be used to predict the three-dimensional structure of important receptors, thereby accelerating the development of potential drugs. This is the result of a new study from Uppsala University published in Science Advances.
In drug development, experimental methods are often used to determine the three-dimensional structure of target proteins and understand how molecules bind to them. This information is necessary to efficiently design drug molecules. However, the process of determining the structure is demanding, so this strategy is not always possible.
Advances in AI methods have made it possible to predict protein structures with greater accuracy than ever before.
In this study, researchers from Uppsala University used AI to create a model of the unknown three-dimensional structure of a receptor. In this case, the TAAR1 receptor is an interesting target protein for the development of drugs for psychiatric disorders. Drug molecules that activate TAAR1 have shown promising results in the treatment of schizophrenia and depression.
The researchers used supercomputers to search a chemical library containing millions of molecules for those that best matched the model. Those predicted to bind to the receptor were then tested in experiments by researchers at the Karolinska Institutet. Unexpectedly, many of the molecules activated TAAR1, and one of the most potent molecules even showed promising effects in animal studies.
At the final stage of the study, the experimental structure of TAAR1 suddenly became available, allowing the researchers to compare it with the AI model.
“The accuracy of the AI-generated structures was astonishing – we couldn't believe it! The results also show that AI-based modelling is significantly better than traditional methods. We can now apply the same strategy to receptors that we could only dream of before,” explains Jens Karlsson, who led the study from Uppsala University.
sauce:
Journal References:
Díaz-Holguín, A., et al. (2024). AlphaFold Accelerates Psychotropic Drug Discovery Targeting Trace Amine Associated Receptor 1. Science Advances. doi.org/10.1126/sciadv.adn1524.
