Text Classification on Social Network Platforms Based on Deep Learning Models

Ya Chen,Tan Juan,정회경 한국정보통신학회 2023 Journal of information and communication convergen Vol.21 No.1

The natural language on social network platforms has a certain front-to-back dependency in structure, and the direct conversion of Chinese text into a vector makes the dimensionality very high, thereby resulting in the low accuracy of existing text classification methods. To this end, this study establishes a deep learning model that combines a big data ultra-deep convolutional neural network (UDCNN) and long short-term memory network (LSTM). The deep structure of UDCNN is used to extract the features of text vector classification. The LSTM stores historical information to extract the context dependency of long texts, and word embedding is introduced to convert the text into low-dimensional vectors. Experiments are conducted on the social network platforms Sogou corpus and the University HowNet Chinese corpus. The research results show that compared with CNN + rand, LSTM, and other models, the neural network deep learning hybrid model can effectively improve the accuracy of text classification.

An Investigation Into the Relationship Between Metabolic Responses and Energy Regulation in Antibody-Producing Cell

Ya Ting Sun,Liang Zhao,Zhao Yang Ye,Li Fan,Xu Ping Liu,Wen Song Tan 한국미생물생명공학회(구 한국산업미생물학회) 2013 Journal of microbiology and biotechnology Vol.23 No.11

Energy-efficient metabolic responses were often noted in high-productive cultures. To better understand these metabolic responses, an investigation into the relationship between metabolic responses and energy regulation was conducted via a comparative analysis among cultures with different energy source supplies. Both glycolysis and glutaminolysis were studied through the kinetic analyses of major extracellular metabolites concerning the fast and slow cell growth stages, respectively, as well as the time-course profiles of intracellular metabolites. In three cultures showing distinct antibody productivities, the amino acid metabolism and energy state were further examined. Both the transition of lactate from production to consumption and steady intracellular pools of pyruvate and lactate were observed to be correlated with efficient energy regulation. In addition, an efficient utilization of amino acids as the replenishment for the TCA cycle was also found in the cultures with upregulated energy metabolism. It was further revealed that the inefficient energy regulation would cause low cell productivity based on the comparative analysis of cell growth and productivity in cultures having distinct energy regulation.

Minimal Information Loss for Privacy-Preserved eHealth Applications

Ya-Ling Chen,Bo-Chao Cheng,Hsueh-lin Chen,Chia-I Lin,Guo-Tan Liao,Bo-Yu Hou,Shih-Chun Hsu 보안공학연구지원센터 2012 International Journal of Security and Its Applicat Vol.6 No.2

Radiation-induced Cochlea Hair Cell Death: Mechanisms and Protection

Tan, Pei-Xin,Du, Sha-Sha,Ren, Chen,Yao, Qi-Wei,Yuan, Ya-Wei Asian Pacific Journal of Cancer Prevention 2013 Asian Pacific journal of cancer prevention Vol.14 No.10

Cochlea hair cell death is regarded to be responsible for the radiation-induced sensorineural hearing loss (SNHL), which is one of the principal complications of radiotherapy (RT) for head and neck cancers. In this mini-review, we focus on the current progresses trying to unravel mechanisms of radiation-induced hair cell death and find out possible protection. P53, reactive oxygen species (ROS) and c-Jun N-terminal kinase (JNK) pathways have been proposed as pivotal in the processes leading to radiation hair cell death. Potential protectants, such as amifostine, N-acetylcysteine (NAC) and epicatechin (EC), are claimed to be effective at reducing radiation-inducedhair cell death. The RT dosage, selection and application of concurrent chemotherapy should be pre-examined in order to minimize the damage to cochlea hair cells.

The anti-obesity effect of lotus leaves on high-fat-diet-induced obesity by modulating lipid metabolism in C57BL/6J mice

Wu Ya,Tan Fang,Zhang Tianyu,Xie Binglin,Ran Lixian,Zhao Xin 한국응용생명화학회 2020 Applied Biological Chemistry (Appl Biol Chem) Vol.63 No.5

Lotus leaves (Nelumbo nucifera) are widely used in medicines and foods. The investigate systematically studied the anti-obesity effect of lotus leaf extracts. It could reduce body weight, alleviate liver damage, and inhibit fat accumulation in high-fat-diet-induced obese mice. Lotus leaf extracts reduced serum alanine aminotransferase (ALT), aspartate transaminase (AST), and alkaline phosphatase (AKP) levels; decreased total cholesterol (TC), triglycerides (TG), and low-density lipoprotein cholesterol (LDL-C) levels in the serum; and increased high-density lipoprotein cholesterol (HDL-C) levels to improve dyslipidemia. Lotus leaves also inhibited inflammation accompanied by obesity via decreasing inflammatory cytokine interleukin (IL)-1β, tumor necrosis factor-α (TNF-α), interferon gamma (IFN-γ), and IL-6 levels and increasing anti-inflammatory cytokine IL-4 and IL-10 levels. qPCR analysis revealed that lotus leaves upregulated peroxisome proliferator-activated receptor alpha (PPAR-α), lipoprotein lipase (LPL), carnitine palmitoyltransferase 1 (CPT1), and cholesterol 7 alpha hydroxylase (CYP7A1) mRNA expressions and downregulated peroxisome proliferator- activated receptor gamma (PPAR-γ) and CCAAT/enhancer-binding protein alpha (C/EBP-α) mRNA expressions, to reduce adipocyte differentiation and fat accumulation, promote oxidation of fat and decomposition of triglyceride and cholesterol. So, lotus leaves effectively regulated lipid metabolism, alleviated inflammation and liver injury in obese mice; thus, lotus leaves could be further developed as a food to combat obesity.

Direct Determination of Uric Acid in Human Serum Samples Using Polypyrrole Nanoelectrode Ensembles

Yang, Guangming,Tan, Lin,Shi, Ya,Wang, Suiping,Lu, Xuxiao,Bai, Huiping,Yang, Yunhui Korean Chemical Society 2009 Bulletin of the Korean Chemical Society Vol.30 No.2

Polypyrrole (PPy) nanotubes have been synthesized by chemical oxidative polymerization of pyrrole within the pores of polycarbonate membrane using the technology of diffusion of solutes. The nanotubes array prepared by the proposed method can be considered as nanoelectrode ensembles (NEEs). An amperometric uric acid sensor based on PPy NEEs has been developed and used for determination of uric acid in human serum samples. The electrode can direct response to uric acid at potential of 0.60V vs. SCE with wide linear range of $1.52{\times}10^{-6}\;to\;1.54{\times}10^{-3}\;M.\;The\;detection\;limit\;is \;3.02{\times}10^{-7}$ M. This sensor has been used to determine uric acid in real serum samples. PPy NEEs is thought of as a good application in the foreground.

Direct Determination of Uric Acid in Human Serum Samples Using Polypyrrole Nanoelectrode Ensembles

Guangming Yang,Lin Tan,Ya Shi,Suiping Wang,Xuxiao Lu,Huiping Bai,Yunhui Yang 대한화학회 2009 Bulletin of the Korean Chemical Society Vol.30 No.2

Polypyrrole (PPy) nanotubes have been synthesized by chemical oxidative polymerization of pyrrole within the pores of polycarbonate membrane using the technology of diffusion of solutes. The nanotubes array prepared by the proposed method can be considered as nanoelectrode ensembles (NEEs). An amperometric uric acid sensor based on PPy NEEs has been developed and used for determination of uric acid in human serum samples. The electrode can direct response to uric acid at potential of 0.60V vs. SCE with wide linear range of 1.52×10-6 to 1.54×10-3 M. The detection limit is 3.02×10-7 M. This sensor has been used to determine uric acid in real serum samples. PPy NEEs is thought of as a good application in the foreground.

Next-generation sequencing of the mitochondrial genome of Dolichovespula panda (Hymenoptera: Vespidae) with a phylogenetic analysis of Vespidae

Xu-Lei Fan,Ya-Jun Gong,Peng-Yan Chen,Qing-Qing Tan,Jiang-Li Tan,Shu-Jun Wei 한국응용곤충학회 2017 Journal of Asia-Pacific Entomology Vol.20 No.3

For the first time the mitochondrial genome of a Dolichovespula species, D. panda Archer (Hymenoptera: Vespidae), was sequenced with a next-generation sequencing approach. The sequenced mitochondrial genome is 17137 bp long and consists of 13 protein-coding, 22 tRNA and two rRNA genes, as well as a partial A +T-rich region. Twenty-two of the genes are encoded on the majority strand and 15 genes on the minority strand. All protein-coding genes start with ATN codons and have a TAA termination codon, except for one with a TA codon. Compared with the putative ancestral arrangement of insects, the D. panda mitochondrial genome shows the shuffling of trnN and trnE, and of trnQ and trnM, the translocation of trnY to upstream of trnI, and of trnL1 to the region between trnS2 and nad1 and a reversal of trnS1. A phylogenetic tree within the Vespidae was reconstructed using the 13 protein-coding mitochondrial genes. This shows a sister group relationship between Dolichovespula and a clade formed by Vespa and Vespula. It also corroborated the position of Eumeninae as sister group of the clade Polistinae +Vespinae.

Transcriptome profiling identifies immune response genes against porcine reproductive and respiratory syndrome virus and Haemophilus parasuis co-infection in the lungs of piglets

Jing Zhang,Jing Wang,Xiong Zhang,Chunping Zhao,Sixuan Zhou,Chunlin Du,Ya Tan,Yu Zhang,Kaizhi Shi 대한수의학회 2022 Journal of Veterinary Science Vol.23 No.1

Background: Co-infections of the porcine reproductive and respiratory syndrome virus (PRRSV) and the Haemophilus parasuis (HPS) are severe in Chinese pigs, but the immune response genes against co-infected with 2 pathogens in the lungs have not been reported. Objectives: To understand the effect of PRRSV and/or HPS infection on the genes expression associated with lung immune function. Methods: The expression of the immune-related genes was analyzed using RNA-sequencing and bioinformatics. Differentially expressed genes (DEGs) were detected and identified by quantitative real-time polymerase chain reaction (qRT-PCR), immunohistochemistry (IHC) and western blotting assays. Results: All experimental pigs showed clinical symptoms and lung lesions. RNA-seq analysis showed that 922 DEGs in co-challenged pigs were more than in the HPS group (709 DEGs) and the PRRSV group (676 DEGs). Eleven DEGs validated by qRT-PCR were consistent with the RNA sequencing results. Eleven common Kyoto Encyclopedia of Genes and Genomes pathways related to infection and immune were found in single-infected and co-challenged pigs, including autophagy, cytokine-cytokine receptor interaction, and antigen processing and presentation, involving different DEGs. A model of immune response to infection with PRRSV and HPS was predicted among the DEGs in the co-challenged pigs. Dual oxidase 1 (DUOX1) and interleukin-21 (IL21) were detected by IHC and western blot and showed significant differences between the co-challenged pigs and the controls. Conclusions: These findings elucidated the transcriptome changes in the lungs after PRRSV and/or HPS infections, providing ideas for further study to inhibit ROS production and promote pulmonary fibrosis caused by co-challenging with PRRSV and HPS.

Let-7c Inhibits NSCLC Cell Proliferation by Targeting HOXA1

Zhan, Min,Qu, Qiang,Wang, Guo,Liu, Ying-Zi,Tan, Sheng-Lan,Lou, Xiao-Ya,Yu, Jing,Zhou, Hong-Hao Asian Pacific Journal of Cancer Prevention 2013 Asian Pacific journal of cancer prevention Vol.14 No.1

Objective: The aim of the present study was to explore mechanisms by which let-7c suppresses NSCLC cell proliferation. Methods: The expression level of let-7c was quantified by qRT-PCR. A549 and H1299 cells were transfected with let-7c mimics to restore the expression of let-7c. The effects of let-7c were then assessed by cell proliferation, colony formation and cell cycle assay. Mouse experiments were used to confirm the effect of let-7c on tumorigenicity in vivo. Luciferase reporter assays and Western blotting were performed to identify target genes for let-7c. Results: HOXA1 was identified as a novel target of let-7c. MTS, colony formation and flow cytometry assays demonstrated that forced expression of let-7c inhibited NSCLC cell proliferation by inducing G1 arrest in vitro, consistent with inhibitory effects induced by knockdown of HOXA1. Mouse experiments demonstrated that let-7c expression suppressed tumorigenesis. Furthermore, we found that let-7c could regulate the expression of HOXA1 downstream effectors CCND1, CDC25A and CDK2. Conclusions: Collectively, these results demonstrate let-7c inhibits NSCLC cell proliferation and tumorigenesis by partial direct targeting of the HOXA1 pathway, which suggests that restoration of let-7c expression may thus offer a potential therapeutic intervention strategy for NSCLC.