AI method predicts retention times of small molecules more reliably
Whether in drug discovery, environmental analysis or metabolomics: anyone analyzing complex biological samples often needs to identify the small molecules they contain. Researchers at Friedrich Schiller University Jena, in collaboration with partners from the Helmholtz Zentrum München and the Technical University of Munich, have developed a method that addresses a problem in analytical chemistry…
Researchers at Friedrich Schiller University Jena have developed a new method to predict the retention times of small molecules in liquid chromatography more reliably. This advance could have wide-ranging applications in drug discovery, environmental analysis, and metabolomics. Liquid chromatography separates complex biological samples by passing them through a column, allowing individual molecules to elute at different times—a key indicator of their identity.
Retention times are affected by numerous experimental conditions, making predictions challenging. Previous models relied heavily on data from the same measurement system, limiting their applicability. The new two-step method developed by bioinformatician Prof. Dr. Sebastian Böcker and his team addresses this issue. It focuses on reversed-phase liquid chromatography and operates by first calculating a retention order index for a molecule, then converting this index into specific retention times using reference points.
This approach does not require extensive training on the target system, enabling accurate predictions even for new systems and unknown molecules. The method, called "2-step," is available as a software package and web application, potentially integrating into many analytical programs to automatically assist laboratories using liquid chromatography and mass spectrometry.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
