Search

Background: Automatic disease named entity recognition (DNER) is of utmost importance for development of more sophisticated BioNLP tools. However, most conventional CRF based DNER systems rely on well-designed features whose selection is labor intensive and time-consuming. Though most deep learning methods can solve NER problems with little feature engineering, they employ additional CRF layer to capture the correlation information between labels in neighborhoods which makes them much complicated. Methods: In this paper, we propose a novel multiple label convolutional neural network (MCNN) based disease NER approach. In this approach, instead of the CRF layer, a multiple label strategy (MLS) first introduced by us, is employed. First, the character-level embedding, word-level embedding and lexicon feature embedding are concatenated. Then several convolutional layers are stacked over the concatenated embedding. Finally, MLS strategy is applied to the output layer to capture the correlation information between neighboring labels. Results: As shown by the experimental results, MCNN can achieve the state-of-the-art performance on both NCBI and CDR corpora. Conclusions: The proposed MCNN based disease NER method achieves the state-of-the-art performance with little feature engineering. And the experimental results show the MLS strategy's effectiveness of capturing the correlation information between labels in the neighborhood. [ABSTRACT FROM AUTHOR]

Motivation: Detecting drug-drug interaction (DDI) has become a vital part of public health safety. Therefore, using text mining techniques to extract DDIs from biomedical literature has received great attentions. However, this research is still at an early stage and its performance has much room to improve. Results: In this article, we present a syntax convolutional neural network (SCNN) based DDI extraction method. In this method, a novel word embedding, syntax word embedding, is proposed to employ the syntactic information of a sentence. Then the position and part of speech features are introduced to extend the embedding of each word. Later, auto-encoder is introduced to encode the traditional bag-of-words feature (sparse 0-1 vector) as the dense real value vector. Finally, a combination of embedding-based convolutional features and traditional features are fed to the softmax classifier to extract DDIs from biomedical literature. Experimental results on the DDIExtraction 2013 corpus show that SCNN obtains a better performance (an F-score of 0.686) than other state-of-theart methods. Availability and Implementation: The source code is available for academic use at http://202.118. 75.18:8080/DDI/SCNN-DDI.zip. [ABSTRACT FROM AUTHOR]

Background: The overactivation of NF-1B signaling is a key hallmark for the pathogenesis of extranodal natural killer/T cell lymphoma (ENKTL), a very aggressive subtype of non-Hodgkin's lymphoma yet with rather limited control strategies. Previously, we found that the dysregulated exportin-1 (also known as CRM1) is mainly responsible for tumor cells to evade apoptosis and promote tumor-associated pathways such as NF-B signaling. Methods: Herein we reported the discovery and biological evaluation of a potent small molecule CRM1 inhibitor, LFS-1107. We validated that CRM1 is a major cellular target of LFS-1107 by biolayer interferometry assay (BLI) and the knockdown of CRM1 conferred tumor cells with resistance to LFS-1107. Results: We found that LFS-1107 can strongly suppresses the growth of ENKTL cells at low-range nanomolar concentration yet with minimal effects on human platelets and healthy peripheral blood mononuclear cells. Treatment of ENKTL cells with LFS-1107 resulted in the nuclear retention of IkBa and consequent strong suppression of NF-B transcriptional activities, NF-B target genes downregulation and attenuated tumor cell growth and proliferation. Furthermore, LFS-1107 exhibited potent activities when administered to immunodeficient mice engrafted with human ENKTL cells. Conclusions: Therefore, LFS-1107 holds great promise for the treatment of ENKTL and may warrant translation for use in clinical trials. Funding: Yang's laboratory was supported by the National Natural Science Foundation of China (Grant: 81874301), the Fundamental Research Funds for Central University (Grant: DUT22YG122) and the Key Research project of 'be Recruited and be in Command' in Liaoning Province (Personal Target Discovery for Metabolic Diseases). [ABSTRACT FROM AUTHOR]

Background: Drug-drug interactions (DDIs) often bring unexpected side effects. The clinical recognition of DDIs is a crucial issue for both patient safety and healthcare cost control. However, although text-mining-based systems explore various methods to classify DDIs, the classification performance with regard to DDIs in long and complex sentences is still unsatisfactory. Methods: In this study, we propose an effective model that classifies DDIs from the literature by combining an attention mechanism and a recurrent neural network with long short-term memory (LSTM) units. In our approach, first, a candidate-drug-oriented input attention acting on word-embedding vectors automatically learns which words are more influential for a given drug pair. Next, the inputs merging the position- and POS-embedding vectors are passed to a bidirectional LSTM layer whose outputs at the last time step represent the high-level semantic information of the whole sentence. Finally, a softmax layer performs DDI classification. Results: Experimental results from the DDIExtraction 2013 corpus show that our system performs the best with respect to detection and classification (84.0% and 77.3%, respectively) compared with other state-of-the-art methods. In particular, for the Medline-2013 dataset with long and complex sentences, our F-score far exceeds those of top-ranking systems by 12.6%. Conclusions: Our approach effectively improves the performance of DDI classification tasks. Experimental analysis demonstrates that our model performs better with respect to recognizing not only close-range but also long-range patterns among words, especially for long, complex and compound sentences. [ABSTRACT FROM AUTHOR]

Medical images are valuable for clinical diagnosis and decision making. Image modality is an important primary step, as it is capable of aiding clinicians to access required medical image in retrieval systems. Traditional methods of modality classification are dependent on the choice of hand-crafted features and demand a clear awareness of prior domain knowledge. The feature learning approach may detect efficiently visual characteristics of different modalities, but it is limited to the number of training datasets. To overcome the absence of labeled data, on the one hand, we take deep convolutional neural networks (VGGNet, ResNet) with different depths pre-trained on ImageNet, fix most of the earlier layers to reserve generic features of natural images, and only train their higher-level portion on ImageCLEF to learn domain-specific features of medical figures. Then, we train from scratch deep CNNs with only six weight layers to capture more domain-specific features. On the other hand, we employ two data augmentation methods to help CNNs to give the full scope to their potential characterizing image modality features. The final prediction is given by our voting system based on the outputs of three CNNs. After evaluating our proposed model on the subfigure classification task in ImageCLEF2015 and ImageCLEF2016, we obtain new, state-of-the-art results--76.87% in ImageCLEF2015 and 87.37% in ImageCLEF2016--which imply that CNNs, based on our proposed transfer learning methods and data augmentation skills, can identify more efficiently modalities of medical images. [ABSTRACT FROM AUTHOR]

Compound figure detection on figures and associated captions is the first step to making medical figures from biomedical literature available for further analysis. The performance of traditional methods is limited to the choice of hand-engineering features and prior domain knowledge. We train multiple convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and gated recurrent unit (GRU) networks on top of pre-trained word vectors to learn textual features from captions and employ deep CNNs to learn visual features from figures. We then identify compound figures by combining textual and visual prediction. Our proposed architecture obtains remarkable performance in three run types--textual, visual and mixed--and achieves better performance in ImageCLEF2015 and ImageCLEF2016. [ABSTRACT FROM AUTHOR]

Sentiment analysis of online social media has attracted significant interest recently. Many studies have been performed, but most existing methods focus on either only textual content or only visual content. In this paper, we utilize deep learning models in a convolutional neural network (CNN) to analyze the sentiment in Chinese microblogs from both textual and visual content. We first train a CNN on top of pre-trained word vectors for textual sentiment analysis and employ a deep convolutional neural network (DNN) with generalized dropout for visual sentiment analysis. We then evaluate our sentiment prediction framework on a dataset collected from a famous Chinese social media network (SinaWeibo) that includes text and related images and demonstrate state-of-the-art results on this Chinese sentiment analysis benchmark. [ABSTRACT FROM AUTHOR]