Discovering active compounds from mixture of natural products by data mining approach

Impact of dietary supplementation with chokeberry (Aronia melanocarpa, Michx.) on tetrachloride-induced liver injury in Wistar rats: Hematological and biochemical implication

In the current study, we assessed the hematological/biochemical alterations, histopathological changes in the liver, and blood cell disorders in Wistar rats exposed to a toxic concentration of carbon tetrachloride (CCl4 ) and the potential protective effect of a 30-day oral extract of chokeberry (Aronia melanocarpa, AM). The concentration of AM (3.38 mg/kg) obtained by quantitative purification from AM fruit showed the highest antioxidant activity (AOA) in vitro and was used for oral ingestion. In addition to high AOA, high values of total phenols (85.334 mg/g), total phenolic acid (606.95 mg/g), total flavonids (22.10 mg/g), and total anthocyanins (11.01 mg/g) were recorded in chokeberry extract. CCl4 treatment caused serious liver injury, hepatocyte and blood cell impairment. AM extract given to rats before CCl4 application had a moderate hepatoprotective effect in comparison to after CCl4 application. White blood count and leukocytes were significantly altered by CCl4, however, the protective role of AM in leukocyte disorders was not established. A high number of microcytes, stomatocytes, anisocytes, and hemolyzed erythrocytes during CCl4 exposure was reduced by AM extract. Flower erythrocytes in the AM + CCl4 group were recorded. Supplementation with chokeberry extract without CCl4 caused hyperproteinemia and hyperalbuminemia. Although the results indicate a weak protective role for AM, it is nevertheless important for improved erythropoiesis and regulation of the development of anemia. The hepatoprotective role of AM was moderate, and the immune response was not proven. Daily consumption of chokeberry extract can improve health. However, the results of our study showed that the ingestion of AM extract at this dose with the highest AOA would have more effective effects if the supplementation were significantly increased.

Machine Learning-Enabled Genome Mining and Bioactivity Prediction of Natural Products

Natural products (NPs) produced by microorganisms and plants are a major source of drugs, herbicides, and fungicides. Thanks to recent advances in DNA sequencing, bioinformatics, and genome mining tools, a vast amount of data on NP biosynthesis has been generated over the years, which has been increasingly exploited to develop machine learning (ML) tools for NP discovery. In this review, we discuss the latest advances in developing and applying ML tools for exploring the potential NPs that can be encoded by genomic language and predicting the types of bioactivities of NPs. We also examine the technical challenges associated with the development and application of ML tools for NP research.

Machine learning approaches for elucidating the biological effects of natural products

Covering: 2000 to 2020 Machine learning (ML) is an efficient tool for the prediction of bioactivity and the study of structure-activity relationships. Over the past decade, an emerging trend for combining these approaches with the study of natural products (NPs) has developed in order to manage the challenge of the discovery of bioactive NPs. In the present review, we will introduce the basic principles and protocols for using the ML approach to investigate the bioactivity of NPs, citing a series of practical examples regarding the study of anti-microbial, anti-cancer, and anti-inflammatory NPs, etc. ML algorithms manage a variety of classification and regression problems associated with bioactive NPs, from those that are linear to non-linear and from pure compounds to plant extracts. Inspired by cases reported in the literature and our own experience, a number of key points have been emphasized for reducing modeling errors, including dataset preparation and applicability domain analysis.

A systematic literature review and classification of knowledge discovery in traditional medicine

INTRODUCTION AND OBJECTIVE

Despite the importance of machine learning methods application in traditional medicine there is a no systematic literature review and a classification for this field. This is the first comprehensive literature review of the application of data mining methods in traditional medicine.

METHOD

We reviewed 5 database between 2000 to 2017 based on the Kitchenham systematic review methodology. 502 articles were identified and reviewed for their relevance to application of machine learning methods in traditional medicine, 42 selected papers were classified and categorized on four dimension; 1) application domain of data mining techniques in traditional medicine; 2) the data mining methods most frequently used in traditional medicine; 3) main strength and limitation of data mining techniques in traditional medicine; 4) the performance evaluation methods in data mining methods in traditional medicine.

RESULT

The result obtained showed that main application domain of data mining techniques in traditional medicine was related to syndrome differentiation. Bayesian Networks (BNs), Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs) were recognized as being the methods most frequently applied in traditional medicine. Furthermore, each data mining techniques has its own strength and limitations when applied in traditional medicine. Single scaler methods were frequently used for performance evaluation of data mining methods.

CONCLUSION

Machine learning methods have become an important research field in traditional medicine. Our research provides information about this methods by examining the related articles.

Anticancer effects of ginsenoside Rg3 (Review)

Cancer is a life-threatening disease with an alarmingly increased annual mortality rate globally. Although various therapies are employed for cancer, the final effect is not satisfactory. Chemotherapy is currently the most commonly used treatment option. However, the unsatisfactory efficacy, severe side-effects and drug resistance hinder the therapeutic efficacy of chemotherapeutic drugs. There is increasing evidence indicating that ginsenoside Rg3, a naturally occurring phytochemical, plays an important role in the prevention and treatment of cancer. The suggested mechanisms mainly include the induction of apoptosis, and the inhibition of proliferation, metastasis and angiogenesis, as well as the promotion of immunity. In addition, ginsenoside Rg3 can be used as an adjuvant to conventional cancer therapies, improving the efficacy and/or reducing adverse effects via synergistic activities. Ginsenoside Rg3 may be a widely applied natural medicine against cancer. To date however, there is no systematic summary available of the anticancer effects of ginsenoside Rg3. Therefore, in this review, all available literature over the past 10 years was reviewed and discussed in order to facilitate further research of ginsenoside Rg3.

Development of liposomal Ginsenoside Rg3: formulation optimization and evaluation of its anticancer effects

The Ginsenoside Rg3 has been shown to possess antiangiogenic and anticancer properties. Because of its limited water solubility, we decided to design and synthesize liposomal Rg3 (L-Rg3), to optimize preparation conditions, and to investigate further whether liposome could enhance the anticancer activity of Rg3. L-Rg3 was prepared using a film-dispersion method and the preparation conditions were optimized with response surface methodology (RSM). The mean encapsulation efficiency (EE) of 82.47% was close to the predicted value of 89.69%. Therefore, the optimized preparation condition was predicted correctly. We evaluated the cytotoxicity, pharmacokinetics, biodistribution and antitumor activities of L-Rg3. HepG2 and A549 cells were treated with Rg3 or L-Rg3 at different concentrations in vitro. Pharmacokinetics and biodistribution studies were carried out in Wistar rats. Tumor model was established by inoculating a suspension of A549 cells into BALB/c nude mice. The mice were divided into Saline, Rg3 solution, and L-Rg3 groups with the drug given by i.p. injection. Survival of the mice and tumor volume were monitored. In addition, CD34 immunohistochemical analysis was used for measuring microvessel density (MVD) of the tumor tissues. The cytotoxicity and ratio of tumor inhibition of L-Rg3 group were significantly higher than the Rg3 solution group. MVD values in the Rg3 solution and L-Rg3 groups decreased, especially in the L-Rg3 group. Compared to Rg3 solution, the L-Rg3 showed increased Cmax and AUC of Rg3 by 1.19- and 1.52-fold, respectively. This liposomal formulation could potentially produce a viable clinical agent for improving the anticancer activity of Rg3.

Chemometrics-based approach to feature selection of chromatographic profiles and its application to search active fraction of herbal medicine

In our previous report (J Pharmaceut Biomed 56 (2011) 443-447), a support vector machine (SVM)-based pharmacodynamic model was established for predicting active fractions of herbal medicines (HMs), where information contents embedded in the chromatograms of the fractions were represented with the peak areas. However, in this representation the global characteristics of the chromatograms were completely missed, which is definitely contrary to the global and holistic views in theories of HMs and undoubtedly reduce the success rate of this model. To deal with the challenge, two chemometrics methods, that is, minimum redundancy maximum relevance (mRMR) and particle swarm optimizer (PSO), were applied in this article for feature selection of the whole chromatograms, and the PSO was also used to tune the SVM parameters. As a case, a sample HM, that is, Xiangdan injection, was investigated. The predictive accuracy was fully evaluated and compared with those by other popular and reported methods. Furthermore, the confirmation on the independent predicting set exhibited that the predicted bioactivities were well consistent with the experimental values. The important potential application of the present model is to be extended to help search active fractions of other HMs.

21st century natural product research and drug development and traditional medicines

Natural products and related structures are essential sources of new pharmaceuticals, because of the immense variety of functionally relevant secondary metabolites of microbial and plant species. Furthermore, the development of powerful analytical tools based upon genomics, proteomics, metabolomics, bioinformatics and other 21st century technologies are greatly expediting identification and characterization of these natural products. Here we discuss the synergistic and reciprocal benefits of linking these 'omics technologies with robust ethnobotanical and ethnomedical studies of traditional medicines, to provide critically needed improved medicines and treatments that are inexpensive, accessible, safe and reliable. However, careless application of modern technologies can challenge traditional knowledge and biodiversity that are the foundation of traditional medicines. To address such challenges while fulfilling the need for improved (and new) medicines, we encourage the development of Regional Centres of 'omics Technologies functionally linked with Regional Centres of Genetic Resources, especially in regions of the world where use of traditional medicines is prevalent and essential for health.

Assessment of herbal medicinal products: challenges, and opportunities to increase the knowledge base for safety assessment

Although herbal medicinal products (HMP) have been perceived by the public as relatively low risk, there has been more recognition of the potential risks associated with this type of product as the use of HMPs increases. Potential harm can occur via inherent toxicity of herbs, as well as from contamination, adulteration, plant misidentification, and interactions with other herbal products or pharmaceutical drugs. Regulatory safety assessment for HMPs relies on both the assessment of cases of adverse reactions and the review of published toxicity information. However, the conduct of such an integrated investigation has many challenges in terms of the quantity and quality of information. Adverse reactions are under-reported, product quality may be less than ideal, herbs have a complex composition and there is lack of information on the toxicity of medicinal herbs or their constituents. Nevertheless, opportunities exist to capitalise on newer information to increase the current body of scientific evidence. Novel sources of information are reviewed, such as the use of poison control data to augment adverse reaction information from national pharmacovigilance databases, and the use of more recent toxicological assessment techniques such as predictive toxicology and omics. The integration of all available information can reduce the uncertainty in decision making with respect to herbal medicinal products. The example of Aristolochia and aristolochic acids is used to highlight the challenges related to safety assessment, and the opportunities that exist to more accurately elucidate the toxicity of herbal medicines.