MOSCOW, 30 June. /TASS/. Chemists and mathematicians from the Skolkovo Institute of Science and Technology (Skoltech) and Moscow State Universite (MSU) have suggested checking the composition of medical plants by means of machine learning technologies, the Skoltech press service said.
They have come up with automatizing computer assisted data analysis based on high-performance liquid chromatography and mass spectrometry.
"Machine learning is when a computer can be taught to analyze the chemical composition of herbal medicine based on the previously known data on chemical analysis," Skoltech said.
According to the researchers, the market of herbal remedies has been rapidly developing in the recent years, as it provides an alternative to synthetic drugs. But there are still no existing effective methods of plant material quality control. In some cases, various tests show the complete absence of the declared herbs in drugs.
Samples from 36 medicinal plant species have been analyzed, and collected data have been used as a training set for machine learning. As a result of chemical analysis of samples, the scientists have collected the chromatographic data in a digitized form which contain information on the components of samples. In different samples from the extracts of the same type, one could detect signals from the same chemical substances, which are typical for the particular type of plant and which build the picture or "fingerprints" of that species. Afterward, the "fingerprints" of substances have been analyzed with an algorithm introduced by Russian researchers.
The authors suppose that the automatizing chromatographic analysis could be used by organizations controlling the drugs before releasing them on the market.
The research was published in Chemometrics and Intelligent Laboratory Systems.