A novel machine learning scheme for classification of medicinal herbs based on 2D-FTIR fingerprints.

A proof-of-concept medicinal herbs identification scheme using machine learning classifiers is proposed in the form of an automated computational package. The scheme makes use of two-dimensional correlation Fourier Transformed Infrared (FTIR) fingerprinting maps derived from the FTIR of raw herb spectra as digital input. The prototype package admits a collection of 11 machine learning classifiers to form a voting pool. A common set of oversampled dataset containing 5 different herbal classes is used to train the pool of classifiers on a one-verses-others manner. The collections of trained models, dubbed the voting classifiers, are deployed in a collective manner to cast their votes to support or against a given inference fingerprint whether it belongs to a particular class. By collecting the votes casted by all voting classifiers, a logically designed scoring system will select out the most probable guess of the identity of the inference fingerprint. The same scoring system is also capable of discriminating an inference fingerprint that does not belong to any of the classes the voting classifiers are trained for as the 'others' type. The proposed classification scheme is stress-tested to evaluate its performance and expected consistency. Our experimental runs show that, by and large, a satisfactory performance of the classification scheme of up to 90 % accuracy is achieved, providing a proof-of-concept viability that the proposed scheme is a feasible, practical, and convenient tool for herbal classification. The scheme is implemented in the form of a packaged Python code, dubbed the "Collective Voting" (CV) package, which is easily scalable, maintained and used in practice.

Mechanisms of action of Panax notoginseng ethanolic extract for its vasodilatory effects and partial characterization of vasoactive compounds.

Panax notoginseng is the most valuable medicinal plant and has been used clinically for more than two thousand years to treat various diseases, including hypertension. Previous studies claimed that different isolated compounds from P. notoginseng are involved in different pathways for vasodilation. It is strongly believed that these vasodilating compounds might act synergistically in contributing vasodilatory effects via holistic signaling pathways. The present study aims to evaluate the vasodilatory effect and mechanism of action employed by the crude extract of P. notoginseng. The fingerprint of P. notoginseng was developed using tri-step FTIR and HPTLC. The contents of Rg1 and Rb1 in the active extract (PN95) were further quantified via HPTLC. The vasodilatory effect of PN95 was evaluated using an in vitro aortic ring model. The results showed that PN95 contains a high amount of Rg1 and Rb1, 25.9 and 13.6%, respectively. The vasodilatory effect of PN95 was elicited via the NO/sGC/cGMP and ß2-adrenergic receptors pathways. Furthermore, PN95 could manage vascular tone by regulating action potentials via potassium and both VOCC and IP3R pathways. The results obtained fulfilled the expected outcome where the PN95 employed more signaling pathways than any of the single active compounds; hence, the holistic therapeutic effect could be achieved and would more easily translate to applications for the treatment of human diseases.

Vasorelaxant and chemical fingerprint studies of Citrus reticulatae pericarpium extracts.

ETHNOPHARMACOLOGICAL RELEVANCE: Citrus reticulatae Pericarpium (Chen pi) was widely used as an important ingredient in the prescription of TCM to treat phlegm fluid retention type hypertension. Since Chen pi is involved in treatment as antihypertensive TCM formula, we have reasonable expectation in believing that it might possess vasorelaxant activity. AIM OF THE STUDY: This study is designed to investigate the vasorelaxant effect of Chen pi and to study its pharmacology effects. MATERIALS AND METHODS: The vasorelaxant effect of water extract of Chen pi (CRW) were evaluated on thoracic aortic rings isolated from Sprague Dawley rats. The fingerprint of Chen pi and the extracts were developed with quantification of hesperidin content by HPTLC. RESULTS: CRW exhibited the strongest vasorelaxant activity. CRW caused the relaxation of the phenylephrine pre-contracted aortic rings in the presence and absence of endothelium as well as in potassium chloride pre-contracted endothelium-intact aortic ring. The incubation of propranolol (ß-adrenergic receptor blocker), atropine (muscarinic receptor blocker), Nω-nitro-L-arginine methyl ester (NO synthase inhibitor), ODQ (sGC inhibitor), indomethacin (COX inhibitor), 4-aminopyridine (KV blocker), barium chloride (Kir blocker), and glibenclamide (KATP blocker) significantly reduced the vasorelaxant effects of CRW. CRW was also found to be active in reducing Ca2+ releases from the sarcoplasmic reticulum and suppressing the voltage-operated calcium channels. CONCLUSION: The vasorelaxant effect of CRW on rat aorta involves NO/sGC, calcium and potassium channels, muscarinic and ß-adrenergic receptors.

Rapid authentication and identification of different types of A. roxburghii by Tri-step FT-IR spectroscopy.

Anoectochilus roxburghii (Wall.) Lindl. (Orchidaceae) is a precious traditional Chinese medicinal herb and has been perennially used to treat various illness. However, there were unethical sellers who adulterated wild A. roxburghii with tissue cultured and cultivated ones. Therefore, there is an urgent need for an effective authentication method to differentiate between these different types of A. roxburghii. In this research, the infrared spectroscopic tri-step identification approach including Fourier transform infrared spectroscopy (FT-IR), Second derivative infrared spectra (SD-IR) and two-dimensional correlation infrared spectra (2D-IR) was used to develop a simple and rapid method to discriminate between wild, cultivated and tissue cultivated A. roxburghii plant. Through this study, all three types of A. roxburghii plant were successfully identified and discriminated through the infrared spectroscopic tri-step identification method. Besides that, all the samples of wild, cultivated and tissue cultivated A. roxburghii plant were analysed with the Soft Independent Modelling of Class Analogy (SIMCA) pattern recognition technique to test and verify the experimental results. The results showed that the three types of A. roxburghii can be discriminated clearly as the recognition rate was 100% for all three types and the rejection rate was more than 60%. 70% of the validated samples were also identified correctly by the SIMCA model. The SIMCA model was also validated by comparing 70 standard herbs to the model. As a result, it was demonstrated that the macroscopic IR fingerprint method and the classification analysis could discriminate not only between the A. roxburghi samples and the standard herbs, it could also distinguish between the three different types of A. roxburghi plant in a direct, rapid and holistic manner.