Researchers find computational models that can help identify drug mechanisms of action
A new study by Massachusetts Institute of Technology (MIT) researchers invents a computational model that predicts molecular interactions that need improvement before they can help identify drug mechanisms. The MIT team found that the predictions of existing models, called molecular docking simulations, performed little better. The team studied the interactions of 296 essential proteins from Escherichia coli with 218 antibacterial compounds, using molecular docking simulations using protein structures generated by an artificial intelligence program called AlphaFold. The researchers found similar results when they used this modeling approach with protein structures that have been experimentally determined, instead of the structures predicted by AlphaFold. AlphaFold is exciting the science world. AlphaFold appears to do roughly as well as experimentally determined structures. It has been accessed by more than half a million researchers and is used to accelerate progress on important real-world problems ranging from plastic pollution to antibiotic resistance.
AlphaFold in drug discovery:
The MIT researchers explored whether existing models could accurately predict the interactions between bacterial proteins and antibacterial compounds. The researchers were able to improve the performance of the molecular docking simulations by running them through four additional machine learning models trained on data that describe how proteins and other molecules interact with each other. Molecular docking predicts how strongly two molecules will bind together based on their shapes and physical properties.
James Collins, Professor of Medical Engineering and Science at MIT’s Institute for Medical Engineering and Science (IMES) and Department of Biological Engineering, in his new study, proved that there is an improvement in the performance of these types of models, known as molecular docking simulations, by applying machine-learning techniques to refine the results. Their study speaks to both the current abilities and the current limitations of computational models for drug discovery.
This study is part of an effort recently launched by Collins’ lab called the Antibiotics-artificial Intelligence Project, which has the goal of using AI to discover and design new antibiotics. The antibiotics-artificial intelligence Project is supported by the Audacious Project, the Flu Lab, the Sea Grape Foundation, and the Wyss Foundation. With further advances, scientists may be able to harness the power of artificial intelligence-generated protein structures to discover not only new antibiotics but also drugs to treat a variety of diseases, including cancer.
AlphaFold is already having a significant, direct impact on human health. AlphaFold is a glimpse of the future, and what might be possible with computational and AI methods applied to biology. With improvements to the modeling approaches and expansion of computing power, these techniques will become increasingly important in drug discovery. AlphaFold has already shown its worth in drug discovery, with biotechs importing its predictions into their own computational models to explore how proteins will interact with potential medicines.
Source: analyticsinsight.net
