scholarly journals A Deep Learning-Based Approach for Identifying the Medicinal Uses of Plant-Derived Natural Compounds

2020 ◽  
Vol 11 ◽  
Author(s):  
Sunyong Yoo ◽  
Hyung Chae Yang ◽  
Seongyeong Lee ◽  
Jaewook Shin ◽  
Seyoung Min ◽  
...  

Medicinal plants and their extracts have been used as important sources for drug discovery. In particular, plant-derived natural compounds, including phytochemicals, antioxidants, vitamins, and minerals, are gaining attention as they promote health and prevent disease. Although several in vitro methods have been developed to confirm the biological activities of natural compounds, there is still considerable room to reduce time and cost. To overcome these limitations, several in silico methods have been proposed for conducting large-scale analysis, but they are still limited in terms of dealing with incomplete and heterogeneous natural compound data. Here, we propose a deep learning-based approach to identify the medicinal uses of natural compounds by exploiting massive and heterogeneous drug and natural compound data. The rationale behind this approach is that deep learning can effectively utilize heterogeneous features to alleviate incomplete information. Based on latent knowledge, molecular interactions, and chemical property features, we generated 686 dimensional features for 4,507 natural compounds and 2,882 approved and investigational drugs. The deep learning model was trained using the generated features and verified drug indication information. When the features of natural compounds were applied as input to the trained model, potential efficacies were successfully predicted with high accuracy, sensitivity, and specificity.

Author(s):  
Makoto Ogata

Abstract Carbohydrates play important and diverse roles in the fundamental processes of life. We have established a method for accurately and a large scale synthesis of functional carbohydrates with diverse properties using a unique enzymatic method. Furthermore, various artificial glycan-conjugated molecules have been developed by adding these synthetic carbohydrates to macromolecules and to middle and low molecular weight molecules with different properties. These glycan-conjugated molecules have biological activities comparable to or higher than those of natural compounds, and present unique functions. In this review, several synthetic glycan-conjugated molecules are taken as examples to show design, synthesis and function.


2019 ◽  
Vol 60 (12) ◽  
pp. 2758-2768 ◽  
Author(s):  
Shinnosuke Ishikawa ◽  
Jos� M Barrero ◽  
Fuminori Takahashi ◽  
Hirofumi Nakagami ◽  
Scott C Peck ◽  
...  

Abstract Abscisic acid (ABA) is a phytohormone and a major determinant of seed dormancy in plants. Seed dormancy is gradually lost during dry storage, a process known as ‘after-ripening’, and this dormancy decay is related to a decline in ABA content and sensitivity in seeds after imbibition. In this study, we aimed at investigating the effect of after-ripening on ABA signaling in barley, our cereal model species. Phosphosignaling networks in barley grains were investigated by a large-scale analysis of phosphopeptides to examine potential changes in response pathways to after-ripening. We used freshly harvested (FH) and after-ripened (AR) barley grains which showed different ABA sensitivity. A total of 1,730 phosphopeptides were identified in barley embryos isolated from half-cut grains. A comparative analysis showed that 329 and 235 phosphopeptides were upregulated or downregulated, respectively after ABA treatment, and phosphopeptides profiles were quite different between FH and AR embryos. These results were supported by peptide motif analysis which suggested that different sets of protein kinases are active in FH and AR grains. Furthermore, in vitro phosphorylation assays confirmed that some phosphopeptides were phosphorylated by SnRK2s, which are major protein kinases involved in ABA signaling. Taken together, our results revealed very distinctive phosphosignaling networks in FH and AR embryos of barley, and suggested that the after-ripening of barley grains is associated with differential regulation of phosphosignaling pathways leading to a decay of ABA signaling.


Iproceedings ◽  
10.2196/15225 ◽  
2019 ◽  
Vol 5 (1) ◽  
pp. e15225
Author(s):  
Felipe Masculo ◽  
Jorn op den Buijs ◽  
Mariana Simons ◽  
Aki Harma

Background A Personal Emergency Response Service (PERS) enables an aging population to receive help quickly when an emergency situation occurs. The reasons that trigger a PERS alert are varied, including a sudden worsening of a chronic condition, a fall, or other injury. Every PERS case is documented by the response center using a combination of structured variables and free text notes. The text notes, in particular, contain a wealth of information in case of an incident such as contextual information, details about the situation, symptoms and more. Analysis of these notes at a population level could provide insight into the various situations that cause PERS medical alerts. Objective The objectives of this study were to (1) develop methods to enable the large-scale analysis of text notes from a PERS response center, and (2) to apply these methods to a large dataset and gain insight into the different situations that cause medical alerts. Methods More than 2.5 million deidentified PERS case text notes were used to train a document embedding model (ie, a deep learning Recurrent Neural Network [RNN] that takes the medical alert text note as input and produces a corresponding fixed length vector representation as output). We applied this model to 100,000 PERS text notes related to medical incidents that resulted in emergency department admission. Finally, we used t-SNE, a nonlinear dimensionality reduction method, to visualize the vector representation of the text notes in 2D as part of a graphical user interface that enabled interactive exploration of the dataset and visual analytics. Results Visual analysis of the vectors revealed the existence of several well-separated clusters of incidents such as fall, stroke/numbness, seizure, breathing problems, chest pain, and nausea, each of them related to the emergency situation encountered by the patient as recorded in an existing structured variable. In addition, subclusters were identified within each cluster which grouped cases based on additional features extracted from the PERS text notes and not available in the existing structured variables. For example, the incidents labeled as falls (n=37,842) were split into several subclusters corresponding to falls with bone fracture (n=1437), falls with bleeding (n=4137), falls caused by dizziness (n=519), etc. Conclusions The combination of state-of-the-art natural language processing, deep learning, and visualization techniques enables the large-scale analysis of medical alert text notes. This analysis demonstrates that, in addition to falls alerts, the PERS service is broadly used to signal for help in situations often related to underlying chronic conditions and acute symptoms such as respiratory distress, chest pain, diabetic reaction, etc. Moreover, the proposed techniques enable the extraction of structured information related to the medical alert from unstructured text with minimal human supervision. This structured information could be used, for example, to track trends over time, to generate concise medical alert summaries, and to create predictive models for desired outcomes.


Molecules ◽  
2020 ◽  
Vol 25 (16) ◽  
pp. 3693
Author(s):  
Tingting Li ◽  
Linjun Chen ◽  
Di Wu ◽  
Guochao Dong ◽  
Wanchao Chen ◽  
...  

Sanghuangporous sanghuang is a rare medicinal fungus which contains polysaccharide as the main active substance and was used to treat gynecological diseases in ancient China. The intracellular polysaccharide yield of S. sanghuang was enhanced by the strain A130 which was screened from mutant strains via atmospheric and room temperature plasma (ARTP) mutagenesis. The objective of this research was to investigate the effects of ARTP mutagenesis on structural characteristics and biological activities of intracellular polysaccharides from S. sanghuang. Six intracellular polysaccharide components were obtained from S. sanghuang mycelia cultivated by the mutagenic strain (A130) and original strain (SH1), respectively. The results revealed that the yields of polysaccharide fractions A130-20, A130-50 and A130-70 isolated from the mutagenic strain fermentation mycelia were significantly higher than those of the original ones by 1.5-, 1.3- and 1.2-fold, and the clear physicochemical differences were found in polysaccharide fractions precipitated by 20% ethanol. A130-20 showed a relatively expanded branching chain with higher molecular weight and better in vitro macrophage activation activities and the IL-6, IL-1, and TNF-α production activities of macrophages were improved by stimulation of A130-20 from the mutagenic strain. This study demonstrates that ARTP is a novel and powerful tool to breed a high polysaccharide yield strain of S. sanghuang and may, therefore, contribute to the large-scale utilization of rare medicinal fungi.


2020 ◽  
Vol 27 ◽  
Author(s):  
Karim Abbasi ◽  
Parvin Razzaghi ◽  
Antti Poso ◽  
Saber Ghanbari-Ara ◽  
Ali Masoudi-Nejad

Drug-target Interactions (DTIs) prediction plays a central role in drug discovery. Computational methods in DTIs prediction have gotten more attention because carrying out in vitro and in vivo experiments on a large scale is costly and time-consuming. Machine learning methods, especially deep learning, are widely applied to DTIs prediction. In this study, the main goal is to provide a comprehensive overview of deep learning-based DTIs prediction approaches. Here, we investigate the existing approaches from multiple perspectives. We explore these approaches to find out which deep network architectures are utilized to extract features from drug compound and protein sequences. Also, the advantages and limitations of each architecture are analyzed and compared. Moreover, we explore the process of how to combine descriptors for drug and protein features. Likewise, a list of datasets that are commonly used in DTIs prediction is investigated. Finally, current challenges are discussed and a short future outlook of deep learning in DTI prediction is given.


Molecules ◽  
2019 ◽  
Vol 24 (10) ◽  
pp. 1913 ◽  
Author(s):  
Bahare Salehi ◽  
Lorene Armstrong ◽  
Antonio Rescigno ◽  
Balakyz Yeskaliyeva ◽  
Gulnaz Seitimova ◽  
...  

This work is an updated snapshot of Lamium plants and their biological activities. The main features of the plant are described and the components of its essential oils are summarized. The traditional medicinal uses of Lamium plants has been reported. The presence of these chemicals i.e., hydroxycinnamic acids, iridoids, secoiridoids, flavonoids, anthocyanins, phenylpropanoids, phytoecdysteroids, benzoxazinoids, betaine can provide biological activities. After the discussion of antioxidant properties documented for Lamium plants, the biological activities, studied using in vitro models, antimicrobial, antiviral, anti-inflammatory, anti-nociceptive activity, and pain therapy and cytotoxicity and cytoprotective activity are here described and discussed. Finally, targeted examples of in vivo studies are reported.


2013 ◽  
Vol 15 (2) ◽  
pp. 293-308 ◽  
Author(s):  
J. Ascari ◽  
J.A. Takahashi ◽  
M.A.D. Boaventura

The Caryocaraceae family is constituted of 25 species distributed in two genera (Caryocar and Anthodiscus). Plants of this family have been used in several phytochemical studies for isolation and characterization of chemical compounds. Some of these studies evaluated in vitro and in vivo biological activities of extracts and pure substances isolated from plants of this family. Nine species of Anthodiscus genus have been described, while no phytochemical study related to them has been reported. On the other hand, Caryocar genus presents 16 species with several medicinal uses like for the treatment of colds and bronchitis, in the prevention of tumours, as a regulating agent of the menstrual flow, to treat ophthalmological problems and for the cure of hematomas and bruises. Some species of this genus were targeted by phytochemical studies and presented, in their composition, the following classes of secondary metabolites: triterpenes, fatty acids, tannins, carotenoids, triterpenic saponins, phenolic coumarins, phenolic glycosides, and others. The fruits of Caryocar species are very nutritive, containing in their composition fibers, proteins, carbohydrates and minerals. Seeds have been widely used as oil source with nutritional and cosmetic value. The biological evaluation of some species was carried out by using relevant biological assays such as: antioxidant, allelopathic and antifungal activities against Biomphalaria glabrata and toxicity on Artemia salina.


2020 ◽  
Vol 10 (5) ◽  
pp. 257-263
Author(s):  
Alfred Maroyi

Antidesma laciniatum and A. membranaceum are small trees used as traditional medicines in tropical Africa. This extensive literature review synthesizes the information currently available on the medicinal uses, phytochemistry and biological activities of A. laciniatum and A. membranaceum. The university library and electronic search engines such as Google Scholar, Scopus, Web of Science, ScienceDirect, and PubMed were searched for pertinent information on the medicinal uses, phytochemistry, and biological activities of A. laciniatum and A. membranaceum. Traditionally, the species have been used as aphrodisiac, and traditional medicine for cough, kwashiorkor, mouth ulcers, pneumonia, prevent miscarriage, snakebites, stomachache and wounds. Various phytochemicals such as essential oils, isoflavonoid glycosides, phytosterols, benzopyranones, lignin glucosides, megastigmane, phenolics, steroids, squalene, terpenoids, triterpenoids, and tetrahydroisoquinoline alkaloids have been isolated from A. laciniatum and A. membranaceum. In vitro studies have confirmed the biological activities of A. laciniatum and A. membranaceum which, include antimicrobial, antioxidant, antiplasmodial, antitrypanosomal, leishmanicidal, molluscicidal and cytotoxicity activities. More pharmacological studies including phytochemical, toxicological, in vitro and in vivo experiments are needed to provide evidence for the clinical effectiveness of remedies prepared from the species.


2016 ◽  
Vol 2016 ◽  
pp. 1-20 ◽  
Author(s):  
Hock Eng Khoo ◽  
Azrina Azlan ◽  
Kin Weng Kong ◽  
Amin Ismail

Hundreds of fruit-bearing trees are native to Southeast Asia, but many of them are considered as indigenous or underutilized. These species can be categorized as indigenous tropical fruits with potential for commercial development and those possible for commercial development. Many of these fruits are considered as underutilized unless the commercialization is being realized despite the fact that they have the developmental potential. This review discusses seven indigenous tropical fruits from 15 species that have been identified, in which their fruits are having potential for commercial development. As they are not as popular as the commercially available fruits, limited information is found. This paper is the first initiative to provide information on the phytochemicals and potential medicinal uses of these fruits. Phytochemicals detected in these fruits are mainly the phenolic compounds, carotenoids, and other terpenoids. Most of these phytochemicals are potent antioxidants and have corresponded to the free radical scavenging activities and other biological activities of the fruits. The scientific research that covered a broad range ofin vitrotoin vivostudies on the medicinal potentials of these fruits is also discussed in detail. The current review is an update for researchers to have a better understanding of the species, which simultaneously can provide awareness to enhance their commercial value and promote their utilization for better biodiversity conservation.


2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Ahmad M. Eid ◽  
Mohammed Hawash

Abstract Background Safrole is a natural compound extracted from various plants, and has shown various biological activities. The current study aimed to investigate the antioxidant, antidiabetic, antimicrobial, and anticancer activity of safrole oil and to study the influence of safrole nanoemulgel on these activities. Methods The antioxidant and antidiabetic in-vitro assays were conducted using standard biomedical methods. The safrole oil nanoemulgel was developed using a self-emulsifying technique. Then the antimicrobial activity of the safrole oil and safrole nanoemulgel were performed on different microbial species, and cytotoxicity was determined against Hep3B cancer cell lines using the MTS assay. Results Safrole oil showed moderate antioxidant activity compared with standard Trolox, with IC50 value 50.28 ± 0.44 and 1.55 ± 0.32 μg/ml, respectively. Moreover, it had potent α-amylase inhibitory activity (IC50 11.36 ± 0.67 μg/ml) compared with Acarbose (IC50 value 5.88 ± 0.63). The safrole nanoemulgel had pseudo-plastic behaviour, droplet sizes below 200 nm, a polydispersity index (PDI) below 0.3, and a zeta potential of less than − 30 mV. Safrole oil has potential antimicrobial and anticancer activities, and these activities were improved with safrole nanoemulgel. Conclusion The safrole oil may be applied for the prevention and treatment of oxidative stress, diabetes, different microbial species and cancer, and these activities could be improved by nano-carriers.


Sign in / Sign up

Export Citation Format

Share Document