Aspect based sentiment analysis (ABSA) can provide more detailed information than general sentiment analysis, because it aims to predict the sentiment polarities of the given aspects or entities in text. We summarize previous approaches into two subtasks: aspect-category sentiment analysis (ACSA) and aspect-term sentiment analysis (ATSA). Most previous approaches employ long short-term memory and attention mechanisms to predict the sentiment polarity of the concerned targets, which are often complicated and need more training time. We propose a model based on convolutional neural networks and gating mechanisms, which is more accurate and efficient. First, the novel Gated Tanh-ReLU Units can selectively output the sentiment features according to the given aspect or entity. The architecture is much simpler than attention layer used in the existing models. Second, the computations of our model could be easily parallelized during training, because convolutional layers do not have time dependency as in LSTM layers, and gating units also work independently. The experiments on SemEval datasets demonstrate the efficiency and effectiveness of our models. 1

Multiplexed high-throughput pyrosequencing is currently limited in complexity (number of samples sequenced in parallel), and in capacity (number of sequences obtained per sample). Physical-space segregation of the sequencing platform into a fixed number of channels allows limited multiplexing, but obscures available sequencing space. To overcome these limitations, we have devised a novel barcoding approach to allow for pooling and sequencing of DNA from independent samples, and to facilitate subsequent segregation of sequencing capacity. Forty-eight forward–reverse barcode pairs are described: each forward and each reverse barcode unique with respect to at least 4 nt positions. With improved read lengths of pyrosequencers, combinations of forward and reverse barcodes may be used to sequence from as many as n2 independent libraries for each set of ‘n’ forward and ‘n’ reverse barcodes, for each defined set of cloning-linkers. In two pilot series of barcoded sequencing using the GS20 Sequencer (454/Roche), we found that over 99.8% of obtained sequences could be assigned to 25 independent, uniquely barcoded libraries based on the presence of either a perfect forward or a perfect reverse barcode. The false-discovery rate, as measured by the percentage of sequences with unexpected perfect pairings of unmatched forward and reverse barcodes, was estimated to be <0.005%.

Entropy-type measures for the heterogeneity of clusters have been used for a long time. This paper studies the entropy-based criterion in clustering categorical data. It first shows that the entropy-based criterion can be derived in the formal framework of probabilistic clustering models and establishes the connection between the criterion and the approach based on dissimilarity coefficients. An iterative Monte-Carlo procedure is then presented to search for the partitions minimizing the criterion. Experiments are conducted to show the effectiveness of the proposed procedure.

No abstract

Recent studies suggest that IVF and assisted reproduction technologies (ART) may result in abnormal genomic imprinting, leading to an increased frequency of Angelman syndrome (AS) and Beckwith-Weidemann syndrome (BWS) in IVF children. To learn how ART might alter the epigenome, we examined morulas and blastocysts derived from C57BL/6J X M. spretus F1 mice conceived in vivo and in vitro and determined the allelic expression of four imprinted genes: Igf2, H19, Cdkn1c and Slc221L. IVF-derived mouse embryos that were cultured in human tubal fluid (HTF) (Quinn's advantage) media displayed a high frequency of aberrant H19 imprinting, whereas in vivo and IVF embryos showed normal maternal expression of Cdkn1c and normal biallelic expression of Igf2 and Slc221L. Embryonic stem (ES) cells derived from IVF blastocysts also showed abnormal Igf2/H19 imprinting. Allele-specific bisulphite PCR reveals abnormal DNA methylation at a CCCTC-binding factor (CTCF) site in the imprinting control region (ICR), as the normally unmethylated maternal allele acquired a paternal methylation pattern. Chromatin immunoprecipitation (ChIP) assays indicate an increase of lysine 4 methylation (dimethyl Lys4-H3) on the paternal chromatin and a gain in lysine 9 methylation (trimethyl Lys9-H3) on the maternal chromatin at the same CTCF-binding site. Our results indicate that de novo DNA methylation on the maternal allele and allele-specific acquisition of histone methylation lead to aberrant Igf2/H19 imprinting in IVF-derived ES cells. We suggest that ART, which includes IVF and various culture media, might cause imprinting errors that involve both aberrant DNA methylation and histone methylation at an epigenetic switch of the Igf2-H19 gene region.

Dynamic epigenetic reprogramming occurs during normal embryonic development at the preimplantation stage. Erroneous epigenetic modifications due to environmental perturbations such as manipulation and culture of embryos during in vitro fertilization (IVF) are linked to various short-or long-term consequences. Among these, the skewed sex ratio, an indicator of reproductive hazards, was reported in bovine and porcine embryos and even human IVF newborns. However, since the first case of sex skewing reported in 1991, the underlying mechanisms remain unclear. We reported herein that sex ratio is skewed in mouse IVF offspring, and this was a result of female-biased peri-implantation developmental defects that were originated from impaired imprinted X chromosome inactivation (iXCI) through reduced ring finger protein 12 (Rnf12)/X-inactive specific transcript (Xist) expression. Compensation of impaired iXCI by overexpression of Rnf12 to up-regulate Xist significantly rescued femalebiased developmental defects and corrected sex ratio in IVF offspring. Moreover, supplementation of an epigenetic modulator retinoic acid in embryo culture medium up-regulated Rnf12/Xist expression, improved iXCI, and successfully redeemed the skewed sex ratio to nearly 50% in mouse IVF offspring. Thus, our data show that iXCI is one of the major epigenetic barriers for the developmental competence of female embryos during preimplantation stage, and targeting erroneous epigenetic modifications may provide a potential approach for preventing IVF-associated complications.in vitro fertilization | sex ratio | X chromosome inactivation | Xist | Rnf12

The advent of microarray technology enables us to monitor an entire genome in a single chip using a systematic approach. Clustering, as a widely used data mining approach, has been used to discover phenotypes from the raw expression data. However traditional clustering algorithms have limitations since they can not identify the substructures of samples and features hidden behind the data. Different from clustering, biclustering is a new methodology for discovering genes that are highly related to a subset of samples. Several biclustering models/methods have been presented and used for tumor clinical diagnosis and pathological research. In this paper, we present a new biclustering model using Binary Matrix Factorization (BMF). BMF is a new variant rooted from non-negative matrix factorization (NMF). We begin by proving a new boundedness property of NMF. Two different algorithms to implement the model and their comparison are then presented. We show that the microarray data biclustering problem can be formulated as a BMF problem and can be solved effectively using our proposed algorithms. Unlike the greedy strategy-based algorithms, our proposed Responsible editor:123 BMF for analyzing gene expression data 29 algorithms for BMF are more likely to find the global optima. Experimental results on synthetic and real datasets demonstrate the advantages of BMF over existing biclustering methods. Besides the attractive clustering performance, BMF can generate sparse results (i.e., the number of genes/features involved in each biclustering structure is very small related to the total number of genes/features) that are in accordance with the common practice in molecular biology.

No abstract