Text classification is an important and classical problem in natural language processing. There have been a number of studies that applied convolutional neural networks (convolution on regular grid, e.g., sequence) to classification. However, only a limited number of studies have explored the more flexible graph convolutional neural networks (convolution on non-grid, e.g., arbitrary graph) for the task. In this work, we propose to use graph convolutional networks for text classification. We build a single text graph for a corpus based on word co-occurrence and document word relations, then learn a Text Graph Convolutional Network (Text GCN) for the corpus. Our Text GCN is initialized with one-hot representation for word and document, it then jointly learns the embeddings for both words and documents, as supervised by the known class labels for documents. Our experimental results on multiple benchmark datasets demonstrate that a vanilla Text GCN without any external word embeddings or knowledge outperforms state-of-the-art methods for text classification. On the other hand, Text GCN also learns predictive word and document embeddings. In addition, experimental results show that the improvement of Text GCN over state-of-the-art comparison methods become more prominent as we lower the percentage of training data, suggesting the robustness of Text GCN to less training data in text classification.
The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused the pandemic of the coronavirus induced disease 2019 (COVID-19) with evolving variants of concern. It remains urgent to identify novel approaches against broad strains of SARS-CoV-2, which infect host cells via the entry receptor angiotensin-converting enzyme 2 (ACE2). Herein, we report an increase in circulating extracellular vesicles (EVs) that express ACE2 (evACE2) in plasma of COVID-19 patients, which levels are associated with severe pathogenesis. Importantly, evACE2 isolated from human plasma or cells neutralizes SARS-CoV-2 infection by competing with cellular ACE2. Compared to vesicle-free recombinant human ACE2 (rhACE2), evACE2 shows a 135-fold higher potency in blocking the binding of the viral spike protein RBD, and a 60- to 80-fold higher efficacy in preventing infections by both pseudotyped and authentic SARS-CoV-2. Consistently, evACE2 protects the hACE2 transgenic mice from SARS-CoV-2-induced lung injury and mortality. Furthermore, evACE2 inhibits the infection of SARS-CoV-2 variants (α, β, and δ) with equal or higher potency than for the wildtype strain, supporting a broad-spectrum antiviral mechanism of evACE2 for therapeutic development to block the infection of existing and future coronaviruses that use the ACE2 receptor.
Extended Data Fig. 5 | Comparison of the drug screening results using different variations of the network proximity-based screening methods. (a) Network proximity-based drug screening using directed human protein-protein interactome vs. undirected human protein-protein interactome. (b) Network proximity-based drug screening using degree preserved edge shuffling vs. degree preserved node shuffling. PCC, Pearson correlation coefficient.
Clinical text classification is an important problem in medical natural language processing. Existing studies have conventionally focused on rules or knowledge sources-based feature engineering, but only a few have exploited effective feature learning capability of deep learning methods. In this study, we propose a novel approach which combines rule-based features and knowledge-guided deep learning techniques for effective disease classification. Critical Steps of our method include identifying trigger phrases, predicting classes with very few examples using trigger phrases and training a convolutional neural network with word embeddings and Unified Medical Language System (UMLS) entity embeddings. We evaluated our method on the 2008 Integrating Informatics with Biology and the Bedside (i2b2) obesity challenge. The results show that our method outperforms the state of the art methods.
Traditional Chinese Medicine (TCM) has been developed for several thousand years and plays a significant role in health care for Chinese people. This paper studies the problem of classifying TCM clinical records into 5 main disease categories in TCM. We explored a number of state-of-the-art deep learning models and found that the recent Bidirectional Encoder Representations from Transformers can achieve better results than other deep learning models and other state-of-the-art methods. We further utilized an unlabeled clinical corpus to fine-tune the BERT language model before training the text classifier. The method only uses Chinese characters in clinical text as input without preprocessing or feature engineering. We evaluated deep learning models and traditional text classifiers on a benchmark data set. Our method achieves a state-of-the-art accuracy 89.39% ± 0.35%, Macro F1 score 88.64% ± 0.40% and Micro F1 score 89.39% ± 0.35%. We also visualized attention weights in our method, which can reveal indicative characters in clinical text.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.