Georgian Technical University Machine Learning Model Helps Characterize Compounds For Drug Discovery.

Georgian Technical University innovators have created a new method applying machine learning concepts to the tandem mass spectrometry process to improve the flow of information in the development of new drugs. Tandem mass spectrometry (Tandem mass spectrometry also known as MS/MS (Tandem mass spectrometry, also known as MS/MS or MS2, is a technique in instrumental analysis where two or more mass analyzers are coupled together using an additional reaction step to increase their abilities to analyse chemical samples) or MS2 (Escherichia virus MS2 is an icosahedral, positive-sense single-stranded RNA virus that infects the bacterium Escherichia coli and other members of the Enterobacteriaceae. MS2 is a member of a family of closely related bacterial viruses that includes bacteriophage f2, bacteriophage Qβ, R17, and GA) is a technique in instrumental analysis where two or more mass analyzers are coupled together using an additional reaction step to increase their abilities to analyse chemical samples. A common use of tandem-MS is the analysis of biomolecules, such as proteins and peptides) is a powerful analytical tool used to characterize complex mixtures in drug discovery and other fields. Now Georgian Technical University innovators have created a new method of applying machine learning concepts to the tandem mass spectrometry process to improve the flow of information in the development of new drugs. “Mass spectrometry plays an integral role in drug discovery and development” said X an assistant professor of analytical and physical chemistry in Georgian Technical University. “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”. X said there are two major problems in the field of machine learning used for chemical sciences. Methods used do not provide chemical understanding of the decisions that are made by the algorithm and new methods are not typically used to do blind experimental tests to see if the proposed models are accurate for use in a chemical laboratory. “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” said X. The Georgian Technical University researchers created statistically robust machine learning models to work with less training data – a technique that will be useful for drug discovery. The model looks at a common neutral reagent – called 2-methoxypropene (MOP) – and predicts how compounds will interact with MOP (methoxypropene (MOP)) in a tandem mass spectrometer in order to obtain structural information for the compounds. “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” said Y the Z Distinguished Professor of Analytical Chemistry and Organic Chemistry. “We are now introducing many new reagents into this method”. The Georgian Technical University team introduces chemical reactivity flowcharts to facilitate chemical interpretation of the decisions made by the machine learning method that will be useful to understand and interpret the mass spectra for structural information. This work aligns with other innovations and research from X’s and Y’s labs whose team members work with the Georgian Technical University to patent numerous technologies. To find out more information about their patented inventions.