Researches have used machine learning approach to the task of medicinal plants identification
June 28, 2016

Researchers from Skoltech and MSU have showed that machine learning techniques can be used for medicinal plants identification based on High performance liquid chromatography – mass spectrometry (HPLC-MS) data.

Photo credit: hkpuipui99.

Photo credit: hkpuipui99.

Herbal remedies have become popular alternative to modern healthcare system. In recent years this market has been rapidly developing. But there are still no existing effective and holisitic methods of plant material quality control. Various tests sometimes show absence of the declared herbs in drugs.

HPLC-MS is an analytical chemistry laboratory technique for identification and quantitation of material’s constituents. In this work samples from 36 medicinal plant species have been analyzed, and collected data have been used to train classificator. Machine learning is a promising tool for automation of herbal remedies quality control. Nevertheless, authors are currently facing some challenges. One of them is lack of primary data. First, samples should be diverse to capture internal structure of data better. At the same time all experimental protocols require standardization since extraction procedure strictly affects resulting data.

The developing approach can be potentially used by drug control organizations.

The results were published in Chemometrics and Intelligent Laboratory Systems.

* The Skolkovo Institute of Science and Technology (Skoltech) is a private graduate research university in Skolkovo, Russia, a suburb of Moscow. Established in 2011 in collaboration with MIT, Skoltech educates global leaders in innovation, advances scientific knowledge, and fosters new technologies to address critical issues facing Russia and the world. Applying international research and educational models, the university integrates the best Russian scientific traditions with twenty-first century entrepreneurship and innovation.