A new machine learning process enables faster analysis of nuclear magnetic resonance (NMR) data than conventional methods, with comparable accuracy.
Developed by Ohio State University scientists, the technique trains computers to scan NMR spectrometer images and decipher complex data about atomic-scale characteristics of proteins.
The process entails generating an artificial deep neural network that the computer employs to parse and analyze data.
The researchers fed the network previously analyzed NMR images or spectra of gradually increasing complexity.
Once trained, the computer could separate peaks in samples with the same accuracy as human experts, and at higher speed and reproducibility.
From Ohio State News
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found