Tandem mass spectrometry is nearly the most powerful tool that can be used to analyze compounds for drug discovery.

Purdue University Researchers have have a brand-new method that utilizes concepts of machine learning and has applied them to the field of tandem mass spectrometry. This technique improves the flow of information in drug development. Chemical Science has published the work produced by these researchers.

Mass Spectrometry

Mass spectrometry plays an integral role in drug discovery and development. The specific implementation of bootstrapped machine learning with a small amount of positive and negative training data presented here will pave the way for becoming mainstream in day-to-day activities of automating characterization of compounds by chemists.

Gaurav Chopra – Purdue’s Assistant professor of physical and analytical chemistry

The Two Main Issues

Gaurav Chopra explained that there are two issues when it comes to using machine learning for chemical sciences. First, a it doesn’t provide a chemical understanding of the algorithm’s decisions. Then, a model cant be determined to be accurate enough to use in a chemical laboratory using conventional methods.

We have addressed both of these items for a methodology that is isomer selective and extremely useful in chemical sciences to characterize complex mixtures, identify chemical reactions and drug metabolites, and in fields such as proteomics and metabolomics.

Chopra

The researchers created an all-inclusive machine learning algorithm that require far less training data than usual to function. They were able to do so by using a new method that’s useful for drug discovery. So, their program looks at MOP (2-methoxypropene), which happens to be a common neutral reagent. It predicts exactly how certain chemicals will interact with MOP in a tandem mass spectrometer. Doing this provides a compounds structural information.

This is the first time that machine learning has been coupled with diagnostic gas-phase ion-molecule reactions, and it is a very powerful combination, leading the way to completely automated mass spectrometric identification of organic compounds. We are now introducing many new reagents into this method.

Hilkka Kenttämaa – Frank Brown Distinguished Professor of Analytical Chemistry and Organic Chemistry

The team of Purdue researchers brought in flowcharts of chemical reactivity so that a chemical interpretation of the algorithm’s choices could be provided. This is very helpful in the understanding and interpretation of the structural information’s mass spectra.

If you liked this article, then maybe you should check this one out.

Joseph Everett