A novel sentiment analysis method based on multi-scale deep learning.

As the college students have been a most active user group in various social media, it remains significant to make effective sentiment analysis for college public opinions. Capturing the direction of public opinion in the student community in a timely manner and guiding students to develop the right values can help in the ideological management of universities. Universally, the recurrent neural networks have been the mainstream technology in terms of sentiment analysis. Nevertheless, the existing research works more emphasized semantic characteristics in vertical direction, yet failing to capture sematic characteristics in horizonal direction. In other words, it is supposed to increase more balance into sentiment analysis models. To remedy such gap, this paper presents a novel sentiment analysis method based on multi-scale deep learning for college public opinions. To fit for bidirectional semantic characteristics, a typical sequential neural network with two propagation paths is selected as the backbone. It is then extended with more layers in horizonal direction. Such design is able to balance both model depth and model breadth. At last, some experiments on a real-world social media dataset are conducted for evaluation, well acknowledging efficiency of the proposed analysis model.

Decreased GDF9 and BMP15 in follicle fluid and granulosa cells and outcomes of IVF-ET among young patients with low prognosis.

PURPOSE: To analyze the level of growth differentiation factor 9 (GDF9) and bone morphogenetic protein 15 (BMP15) in follicle fluid (FF) and granulosa cells (GCs) derived from young patients with low prognosis for in vitro fertilization and embryo transfer (IVF-ET) treatment. METHODS: A prospective cohort study was carried out by enrolling 52 young patients with low prognosis according to the POSEIDON classification group 3 (low prognosis group) and 51 young patients with normal ovarian reserve (control group). The concentration of the GDF9 and BMP15 proteins in FF was determined by enzyme-linked immunosorbent assay. The mRNA level of the GDF9 and BMP15 in the GCs was measured by quantitative real-time PCR. RESULTS: The concentration of GDF9 (1026.72 ± 159.12 pg/mL vs. 1298.06 ± 185.41 pg/mL) and BMP15 (685.23 ± 143.91 pg/mL vs. 794.37 ± 81.79 pg/mL) in FF and the mRNA level of GDF9 and BMP15 in the GCs and the live birth rate per treatment cycle started (30.77% vs. 50.98%) and oocytes retrieved (4.25 ± 1.91 vs.12.04 ± 4.24) were significantly lower, whereas the canceled cycle rate was significantly higher (9.62% vs. 0) in the low prognosis group compared with the control group (P < 0.05). The expression of GDF9 and BMP15 in the ovary was positively correlated with live birth (P < 0.05). CONCLUSION: The expression of GDF9 and BMP15 in the ovary was decreased in young patients with low prognosis accompanied by a poorer outcome of IVF-ET treatment. TRIAL REGISTRATION: ChiCTR1800016107 (Chinese Clinical Trial Registry), May 11, 2018. ( http://www.chictr.org.cn/edit.aspx?pid=27216&htm=4 ).

Implementing targeted region capture sequencing for the clinical detection of Alagille syndrome: An efficient and cost­effective method.

Alagille syndrome (AGS) is a highly variable, autosomal dominant disease that affects multiple structures including the liver, heart, eyes, bones and face. Targeted region capture sequencing focuses on a panel of known pathogenic genes and provides a rapid, cost­effective and accurate method for molecular diagnosis. In a Chinese family, this method was used on the proband and Sanger sequencing was applied to validate the candidate mutation. A de novo heterozygous mutation (c.3254_3255insT p.Leu1085PhefsX24) of the jagged 1 gene was identified as the potential disease­causing gene mutation. In conclusion, the present study suggested that target region capture sequencing is an efficient, reliable and accurate approach for the clinical diagnosis of AGS. Furthermore, these results expand on the understanding of the pathogenesis of AGS.

Identification and Validation of Reference Genes for RT-qPCR Analysis in Non-Heading Chinese Cabbage Flowers.

Non-heading Chinese cabbage (Brassica rapa ssp. chinensis Makino) is an important vegetable member of Brassica rapa crops. It exhibits a typical sporophytic self-incompatibility (SI) system and is an ideal model plant to explore the mechanism of SI. Gene expression research are frequently used to unravel the complex genetic mechanism and in such studies appropriate reference selection is vital. Validation of reference genes have neither been conducted in Brassica rapa flowers nor in SI trait. In this study, 13 candidate reference genes were selected and examined systematically in 96 non-heading Chinese cabbage flower samples that represent four strategic groups in compatible and self-incompatible lines of non-heading Chinese cabbage. Two RT-qPCR analysis software, geNorm and NormFinder, were used to evaluate the expression stability of these genes systematically. Results revealed that best-ranked references genes should be selected according to specific sample subsets. DNAJ, UKN1, and PP2A were identified as the most stable reference genes among all samples. Moreover, our research further revealed that the widely used reference genes, CYP and ACP, were the least suitable reference genes in most non-heading Chinese cabbage flower sample sets. To further validate the suitability of the reference genes identified in this study, the expression level of SRK and Exo70A1 genes which play important roles in regulating interaction between pollen and stigma were studied. Our study presented the first systematic study of reference gene(s) selection for SI study and provided guidelines to obtain more accurate RT-qPCR results in non-heading Chinese cabbage.

The complete mitochondrial genome of the Sorex araneus.

The Sorex araneus (common shrew), a member of the Soricidae family, is the most common shrew throughout Northern Europe. The region includes Great Britain, but excludes Ireland. Herein, we first publish the complete mitochondrial genome of S. araneus. The mitogenome is 16 887 bp in length, which contains 24 tRNA genes, 13 protein-coding genes, 2 rRNA genes and a control region. The overall GC content is 38.28%, which is lower than AT. To verify the accuracy and utility of new determined mitogenome sequences, a species phylogenetic tree is constructed based on the complete mitogenomes of the species and other 10 close species. The current data provide important resources for the research of S. araneus mitochondrial evolution and the species identification.