AI enhanced NMR sets record

Swiss scientists have created a method that can be combined with NMR spectroscopy to determine the exact location of atoms in complex organic compounds.

The team, from École Polytechnique Fédérale de Lausanne, have written a machine-learning program that can predict, in record time, how atoms will respond to an applied magnetic field. NMR spectroscopy probes the magnetic fields between atoms to determine how neighbouring atoms interact with each other. However, full crystal structure determination by NMR requires complicated, time-consuming calculations involving quantum chemistry – nearly impossible for molecules with very intricate structures. The team say their program can overcome these obstacles.

“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,” says Michele Ceriotti, head of the Laboratory of Computational Science and Modeling at EPFL’s School of Engineering and co-author of the study. “To predict the NMR signature of a crystal with nearly 1,600 atoms, our technique – ShiftML – requires about six minutes; the same feat would have taken 16 years with conventional techniques.”

This can be of huge benefit to pharmaceutical companies, which must carefully monitor their molecules’ structures to meet requirements for patient safety. To fully understand how the active ingredients will behave once inside the body, scientists need to know their exact atomic-level structure.

“This is really exciting because the massive acceleration in computation times will allow us to cover much larger conformational spaces and correctly determine structures where it was just not previously possible. This puts most of the complex contemporary drug molecules within reach,” says Lyndon Emsley, head of the Laboratory of Magnetic Resonance at EPFL.

The study is published in Nature Communications and the program is freely available online.