Progressive Multigranularity Information Propagation for Coupled Aspect-Opinion Extraction.

Coupled aspect-opinion extraction aims to identify aspect-opinion pairs in the form of (aspect term, opinion term) or triplets in the form of (aspect term, opinion term, sentiment polarity) from user-generated texts. Compared to the traditional aspect-based sentiment prediction or extraction tasks, coupled aspect-opinion extraction needs to associate aspects with their corresponding opinions and organize opinion-related information into structured outputs. The existing works either divide this task into subproblems (i.e., term extraction and relation prediction) or utilize a unified tagging scheme. However, these methods only focus on atomic word-level interactions and ignore the intensive information propagation among different granularities (e.g., words and word pairs). To address this limitation, we propose a progressive multigranularity information propagation network that progressively explores three types of correlations with different granularities. Specifically, our model starts with the most basic word-level correlations by composing all possible word pairs. In the second stage, the pairwise relation information is used to update the word features. The last stage propagates information among word pairs to produce the relation scores. We treat the task as a unified relation prediction problem and construct an end-to-end framework that iteratively conducts the three-stage information propagation to refine the textual representations. Comprehensive experiments on different aspect-based sentiment analysis benchmarks clearly demonstrate the effectiveness of the proposed approach.

Establishment of a Novel Baculovirus-Silkworm Expression System.

The baculovirus vector expression system is a well-established tool for foreign protein production and gene delivery. In this study, we constructed a recombinant baculovirus vector system. The UAS promotor region and Bombyx mori nucleopolyhedrovirus (BmNPV) polyhedrin coding region were ligated into a pFastBac Dual vector to obtain a BmBac-UPS recombinant bacmid. The recombinant bacmid BmBac-Gal4 was generated by the same strategy which has a Gal4 coding region controlled by the IE2 promoter. BmBac-UPS and BmBac-IGal4 were co-infected into silkworm BmN cells to confirm the ability of the UAS/Gal4 system to form polyhedrons in B. mori cells. Furthermore, the recombinant viruses were tested for infection efficiency and the ability to generate polyhedra in transgenic B. mori cell line BmE. The results showed that recombinant viruses have the ability to form polyhedrons and gain raised pathogenicity when orally infected B. mori larvae and are applied as the preferred tool for foreign gene delivery and expression.

Current Therapy and Therapeutic Targets for Microsporidiosis.

Microsporidia are obligate intracellular, spore-forming parasitic fungi which are grouped with the Cryptomycota. They are both opportunistic pathogens in humans and emerging veterinary pathogens. In humans, they cause chronic diarrhea in immune-compromised patients and infection is associated with increased mortality. Besides their role in pébrine in sericulture, which was described in 1865, the prevalence and severity of microsporidiosis in beekeeping and aquaculture has increased markedly in recent decades. Therapy for these pathogens in medicine, veterinary, and agriculture has become a recent focus of attention. Currently, there are only a few commercially available antimicrosporidial drugs. New therapeutic agents are needed for these infections and this is an active area of investigation. In this article we provide a comprehensive summary of the current as well as several promising new agents for the treatment of microsporidiosis including: albendazole, fumagillin, nikkomycin, orlistat, synthetic polyamines, and quinolones. Therapeutic targets which could be utilized for the design of new drugs are also discussed including: tubulin, type 2 methionine aminopeptidase, polyamines, chitin synthases, topoisomerase IV, triosephosphate isomerase, and lipase. We also summarize reports on the utility of complementary and alternative medicine strategies including herbal extracts, propolis, and probiotics. This review should help facilitate drug development for combating microsporidiosis.

Significance of the 'line sign' in the diagnosis of congenital imperforate anus on prenatal ultrasound.

BACKGROUND: The prenatal diagnosis of foetal imperforate anus is difficult. Most previous studies have been case reports. To provide useful information for diagnosing foetal imperforate anus, a retrospective review of diagnostic approaches was conducted. Ultrasonography was performed in 19 cases of foetal imperforate anus from 2016 to 2019 at our prenatal diagnostic centre. The prenatal sonographic features and outcomes of each case were collected and evaluated. RESULT: The anal sphincter of a normal foetus shows the 'target sign' on cross-sectional observation. Of the 19 cases of imperforate anus, 16 cases were diagnosed by the ultrasound image feature called the 'line sign'. 1 case with tail degeneration was low type imperforate anus with the irregular 'target sign' not a real 'target sign'. There was two false-negative case, in which the 'target sign' was found, but irregular. CONCLUSION: In this study, we find that the anus of a foetus with imperforate anus presents a 'line sign' on sonographic observation. The absence of the 'target sign' and then the presence of the 'line sign' can assist in the diagnosis of imperforate anus. The 'line sign' can be used as a secondary assessment to determine the type of the malformation following non visualization of the 'target sign'. The higher the position of the imperforate anus is, the more obvious the 'line sign'. It is worth noting that the finding of the short 'line sign' and irregularr 'target sign' can not ignore the low type imperforate anus.

A Deep Learning Framework for Identifying Essential Proteins by Integrating Multiple Types of Biological Information.

Computational methods including centrality and machine learning-based methods have been proposed to identify essential proteins for understanding the minimum requirements of the survival and evolution of a cell. In centrality methods, researchers are required to design a score function which is based on prior knowledge, yet is usually not sufficient to capture the complexity of biological information. In machine learning-based methods, some selected biological features cannot represent the complete properties of biological information as they lack a computational framework to automatically select features. To tackle these problems, we propose a deep learning framework to automatically learn biological features without prior knowledge. We use node2vec technique to automatically learn a richer representation of protein-protein interaction (PPI) network topologies than a score function. Bidirectional long short term memory cells are applied to capture non-local relationships in gene expression data. For subcellular localization information, we exploit a high dimensional indicator vector to characterize their feature. To evaluate the performance of our method, we tested it on PPI network of S. cerevisiae. Our experimental results demonstrate that the performance of our method is better than traditional centrality methods and is superior to existing machine learning-based methods. To explore which of the three types of biological information is the most vital element, we conduct an ablation study by removing each component in turn. Our results show that the PPI network embedding contributes most to the improvement. In addition, gene expression profiles and subcellular localization information are also helpful to improve the performance in identification of essential proteins.

DMFLDA: A Deep Learning Framework for Predicting lncRNA-Disease Associations.

A growing amount of evidence suggests that long non-coding RNAs (lncRNAs) play important roles in the regulation of biological processes in many human diseases. However, the number of experimentally verified lncRNA-disease associations is very limited. Thus, various computational approaches are proposed to predict lncRNA-disease associations. Current matrix factorization-based methods cannot capture the complex non-linear relationship between lncRNAs and diseases, and traditional machine learning-based methods are not sufficiently powerful to learn the representation of lncRNAs and diseases. Considering these limitations in existing computational methods, we propose a deep matrix factorization model to predict lncRNA-disease associations (DMFLDA in short). DMFLDA uses a cascade of non-linear hidden layers to learn latent representation to represent lncRNAs and diseases. By using non-linear hidden layers, DMFLDA captures the more complex non-linear relationship between lncRNAs and diseases than traditional matrix factorization-based methods. In addition, DMFLDA learns features directly from the lncRNA-disease interaction matrix and thus can obtain more accurate representation learning for lncRNAs and diseases than traditional machine learning methods. The low dimensional representations of the lncRNAs and diseases are fused to estimate the new interaction value. To evaluate the performance of DMFLDA, we perform leave-one-out cross-validation and 5-fold cross-validation on known experimentally verified lncRNA-disease associations. The experimental results show that DMFLDA performs better than the existing methods. The case studies show that many predicted interactions of colorectal cancer, prostate cancer, and renal cancer have been verified by recent biomedical literature. The source code and datasets can be obtained from https://github.com/CSUBioGroup/DMFLDA.

The application of prenatal ultrasound in the diagnosis of congenital duodenal obstruction.

BACKGROUND: The purpose of this research is to summarize the prenatal ultrasound characteristics of congenital duodenal obstruction (CDO), especially in the diagnosis of duodenal diaphragm and annular pancreas. At present, few researchers have summarized the specific ultrasound features of duodenal diaphragm and annular pancreas. METHODS: In this study, a retrospective analysis of 40 patients diagnosed with CDO between January 2016 and December 2019 was carried out. Data on the diagnosis, ultrasound images and outcomes of the patients were gathered, and the features of the patients were analyzed. RESULTS: The results showed that there were 17 patients (42.5%) of congenital duodenal diaphragm, all with a 'rat tail' sign on the ultrasound images. Moreover, there were 4 patients (10.0%) of CDO caused by annular pancreas, all with a 'pliers' sign on the ultrasound images. We summarized the imaging features of the 'rat tail' sign and the 'pliers' sign. CONCLUSION: The main conclusion of this study was that the 'rat tail' sign could be used as an indirect ultrasound feature to diagnose duodenal diaphragm. The 'pliers' sign could be used as a direct ultrasound feature in the diagnosis of annular pancreas in CDO.

Automatic ICD code assignment of Chinese clinical notes based on multilayer attention BiRNN.

International Classification of Diseases (ICD) code is an important label of electronic health record. The automatic ICD code assignment based on the narrative of clinical documents is an essential task which has drawn much attention recently. When Chinese clinical notes are the input corpus, the nature of Chinese brings some issues that need to be considered, such as the accuracy of word segmentation and the representation of single Chinese characters which contain semantics. Taking the lengthy text of patient notes and the representation of Chinese words into account, we present a multilayer attention bidirectional recurrent neural network (MA-BiRNN) model to implement the assignment of disease codes. A hierarchical approach is used to represent the feature of discharge summaries without manual feature engineering. The combination of character level embedding and word level embedding can improve the representation of words. Attention mechanism is introduced into bidirectional long short term memory networks, which helps to solve the performance dropping problem when plain recurrent neural networks encounter long text sequences. The experiment is carried out on a real-world dataset containing 7732 admission records in Chinese and 1177 unique ICD-10 labels. The proposed model achieves 0.639 and 0.766 in F1-score on full-level code and block-level code, respectively. It outperforms the baseline neural network models and achieves the lowest Hamming loss value. Ablation analysis indicates that the multilevel attention mechanism plays a decisive role in the system for dealing with Chinese clinical notes.

Automated ICD-9 Coding via A Deep Learning Approach.

ICD-9 (the Ninth Revision of International Classification of Diseases) is widely used to describe a patient's diagnosis. Accurate automated ICD-9 coding is important because manual coding is expensive, time-consuming, and inefficient. Inspired by the recent successes of deep learning, in this study, we present a deep learning framework called DeepLabeler to automatically assign ICD-9 codes. DeepLabeler combines the convolutional neural network with the 'Document to Vector' technique to extract and encode local and global features. Our proposed DeepLabeler demonstrates its effectiveness by achieving state-of-the-art performance, i.e., 0.335 micro F-measure on MIMIC-II dataset and 0.408 micro F-measure on MIMIC-III dataset. It outperforms classical hierarchy-based SVM and flat-SVM both on these two datasets by at least 14 percent. Furthermore, we analyze the deep neural network structure to discover the vital elements in the success of DeepLabeler. We find that the convolutional neural network is the most effective component in our network and the 'Document to Vector' technique is also necessary for enhancing classification performance since it extracts well-recognized global features. Extensive experimental results demonstrate that the great promise of deep learning techniques in the field of text multi-label classification and automated medical coding.

An interpretable boosting model to predict side effects of analgesics for osteoarthritis.

BACKGROUND: Osteoarthritis (OA) is the most common disease of arthritis. Analgesics are widely used in the treat of arthritis, which may increase the risk of cardiovascular diseases by 20% to 50% overall.There are few studies on the side effects of OA medication, especially the risk prediction models on side effects of analgesics. In addition, most prediction models do not provide clinically useful interpretable rules to explain the reasoning process behind their predictions. In order to assist OA patients, we use the eXtreme Gradient Boosting (XGBoost) method to balance the accuracy and interpretability of the prediction model. RESULTS: In this study we used the XGBoost model as a classifier, which is a supervised machine learning method and can predict side effects of analgesics for OA patients and identify high-risk features (RFs) of cardiovascular diseases caused by analgesics. The Electronic Medical Records (EMRs), which were derived from public knee OA studies, were used to train the model. The performance of the XGBoost model is superior to four well-known machine learning algorithms and identifies the risk features from the biomedical literature. In addition the model can provide decision support for using analgesics in OA patients. CONCLUSION: Compared with other machine learning methods, we used XGBoost method to predict side effects of analgesics for OA patients from EMRs, and selected the individual informative RFs. The model has good predictability and interpretability, this is valuable for both medical researchers and patients.