Swiss researchers use AI to determine atoms configuration

GENEVA. KAZINFORM - Swiss researchers have developed a machine-learning approach to determine, in record time, the location of atoms in powdered solids, which, when applied to complex molecules containing thousands of atoms, could be of particular interest to the pharmaceutical industry, said a press release of Swiss Federal Institute of Technology Lausanne (EPFL) on Monday, Xinhua reports.

Many drugs today are produced as powdered solids, but to fully understand how the active ingredients will behave once inside the body, scientists need to know their exact atomic-level structure.

For instance, the way molecules are arranged inside a crystal has a direct impact on a compound's properties, such as its solubility. Researchers are therefore working hard to develop technologies that can easily identify the exact crystal structures of microcrystalline powders.

In a latest study published in Nature Communications, a team of EPFL scientists has written a machine-learning program that can predict, in record time, how atoms will respond to an applied magnetic field.

This can be combined with nuclear magnetic resonance (NMR) spectroscopy to determine the exact location of atoms in complex organic compounds, which can be of huge benefit to pharmaceutical companies, as they must carefully monitor their molecules' structures to meet requirements for patient safety.

NMR spectroscopy is a well-known and highly efficient method for probing the magnetic fields between atoms and determining how neighboring atoms interact with each other. However, full crystal structure determination by NMR spectroscopy requires extremely complicated, time-consuming calculations involving quantum chemistry, which is nearly impossible for molecules with very intricate structures.

To overcome these obstacles, the scientists trained their AI model on molecular structures taken from structural databases. Even for relatively simple molecules, this model is almost 10,000 times faster than existing methods, and the advantage grows tremendously when considering more complex compounds, according to the study.

This new program will make it possible to use completely different approaches that will be faster and allow access to larger molecules. It will allow for covering much larger conformational spaces and correctly determining structures where it was just not previously possible, the researchers said, adding that it will put most of the complex contemporary drug molecules within reach.

The team said that the program is now freely available online, and that anyone can upload a molecule and get its NMR signature in just a few minutes.