Flowers: precious food and medicine resources

Flower plants are popular all over the world and important sources of ornamental plants,bioactive molecules and nutrients.Flowers have a wide range of biological activities and beneficial pharmacological effects.Flowers and their active ingredients are becoming more and more popular in the preparation of food,drugs and industrial products.This paper summarizes the active ingredients,pharmacological activities and applications in the pharmaceutical and food industries of flower plants in recent years.In addition,the possible molecular mechanism of pharmacological effects of flower plants were also discussed.302 active constituents from 55 species of flower plants were summarized,including flavonoids(115),terpenoids(90),phenylpropanoids(20),alkaloids(13),organic acids(27)and others(37).The pharmacological effects of flower plants are very extensive,mainly including antioxidant,anti-inflammatory,anti-tumor,anti-virus,and hypoglycemic.The mechanisms of anti-inflammatory,anti-tumor and hypoglycemic activities present the characteristics of multi-way and multi-target.Because of its rich nutrients,bioactive ingredients and plant essential oils,and its wide sources,flower plants are widely used in food,beverage,cosmetics and drug research.Flower plants also play an important role in pharmaceutical industry,food industry and other fields.

Interpreting Randomly Wired Graph Models for Chinese NER

Interpreting deep neural networks is of great importance to understand and verify deep models for natural language processing(NLP)tasks.However,most existing approaches only focus on improving the performance of models but ignore their interpretability.In this work,we propose a Randomly Wired Graph Neural Network(RWGNN)by using graph to model the structure of Neural Network,which could solve two major problems(word-boundary ambiguity and polysemy)of ChineseNER.Besides,we develop a pipeline to explain the RWGNNby using Saliency Map and Adversarial Attacks.Experimental results demonstrate that our approach can identify meaningful and reasonable interpretations for hidden states of RWGNN.

Lignans from Patrinia scabiosaefolia improve insulin resistance by activating PI-3K/AKT pathway and promoting GLUT4 expression

Patrinia scabiosaefolia,is used as wild vegetable in China for more than 2000 years,with a variety of pharmacological activities,including anti-inflammatory,anti-tumor and hypoglycemic.Based on our ongoing research on chemical constituents and hypoglycemic activity of P.scabiosaefolia,4 lignan compounds,(+)-isolariciresinol(1),7R,7’R,8S,8’S-(+)-neo-olivil-4-O-β-D-glucopyranoside(2),4-O-methylcedrusin(3)and patrinian A(4),were isolated and identifi ed.The hypoglycemic activity showed that compounds 2 and 3 could extremely signifi cantly improve insulin resistance at 100(P<0.001),50(P<0.001)and 25μmol/L(P<0.01)in IR 3T3-L1 cells.While compound 4 only promoted glucose uptake by IR 3T3-L1 cells at 100μmol/L(P<0.01).Western blotting experiments showed that compounds 2 and 4 up-regulated the protein expressions of p-IRS,PI-3K,p-AKT and glucose transporter 4(GLUT4),and promoted the transcription of GLUT4 mRNA.Therefore,the mechanisms of compounds 2 and 4 were presumed to improve IR by activating PI-3K/AKT signaling pathway.

Empirical Comparisons of Deep Learning Networks on Liver Segmentation

Accurate segmentation of CT images of liver tumors is an important adjunct for the liver diagnosis and treatment of liver diseases.In recent years,due to the great improvement of hard device,many deep learning based methods have been proposed for automatic liver segmentation.Among them,there are the plain neural network headed by FCN and the residual neural network headed by Resnet,both of which have many variations.They have achieved certain achievements in medical image segmentation.In this paper,we firstly select five representative structures,i.e.,FCN,U-Net,Segnet,Resnet and Densenet,to investigate their performance on liver segmentation.Since original Resnet and Densenet could not perform image segmentation directly,we make some adjustments for them to perform live segmentation.Our experimental results show that Densenet performs the best on liver segmentation,followed by Resnet.Both perform much better than Segnet,U-Net,and FCN.Among Segnet,U-Net,and FCN,U-Net performs the best,followed by Segnet.FCN performs the worst.

An Empirical Comparison on Multi-Target Regression Learning

Multi-target regression is concerned with the simultaneous prediction of multiple continuous target variables based on the same set of input variables.It has received relatively small attention from the Machine Learning community.However,multi-target regression exists in many real-world applications.In this paper we conduct extensive experiments to investigate the performance of three representative multi-target regression learning algorithms(i.e.Multi-Target Stacking(MTS),Random Linear Target Combination(RLTC),and Multi-Objective Random Forest(MORF)),comparing the baseline single-target learning.Our experimental results show that all three multi-target regression learning algorithms do improve the performance of the single-target learning.Among them,MTS performs the best,followed by RLTC,followed by MORF.However,the single-target learning sometimes still performs very well,even the best.This analysis sheds the light on multi-target regression learning and indicates that the single-target learning is a competitive baseline for multi-target regression learning on multi-target domains.

Predicting Simplified Thematic Progression Pattern for Discourse Analysis

The pattern of thematic progression,reflecting the semantic relationships between contextual two sentences,is an important subject in discourse analysis.We introduce a new corpus of Chinese news discourses annotated with thematic progression information and explore some computational methods to automatically extracting the discourse structural features of simplified thematic progression pattern(STPP)between contextual sentences in a text.Furthermore,these features are used in a hybrid approach to a major discourse analysis task,Chinese coreference resolution.This novel approach is built up via heuristic sieves and a machine learning method that comprehensively utilizes both the top-down STPP features and the bottom-up semantic features.Experimental results on the intersection of the CoNLL-2012 task shared dataset and the CDTC corpus demonstrate the effectiveness of our proposed approach.

Chemical constituents and anticoagulant activity from Delphinium brunonianum Royle

Delphinium brunonianum Royle belongs to Ranunculaceae family and has the effects of dispelling wind to relieve itching and cooling blood to detoxify.It was found that the extracts of D.brunonianum had good anticoagulant activity which was extracted with 70%ethanol in our previous researches.Then,16 compounds were isolated and identified from the extract of D.brunonianum,among which compounds 5,7-10,12,14,15-16 were isolated from this genus for the first time,and compounds 2-4 were isolated from this plant for the first time.And the coagulation activity assay showed that compounds 10,14 and 15 had good anticoagulant activity by activated partial thromboplastin time(APTT),thrombin time(TT)and prothrombin time(PT)in vitro.