Article
Medicine, General & Internal
Sofia Tejada, Miia Jansson, Candela Sole-Lleonart, Jordi Rello
Summary: Neuraminidase inhibitors (NAIs) therapy significantly reduced the time to clinical resolution, total influenza-related complications, acute otitis media and need for antibiotic treatment. While reductions in mortality, pneumonia, asthma exacerbations, and hospitalization rates only demonstrated a trend benefit with NAIs treatment. The most significant adverse event associated with NAIs was an increase in nausea and vomiting.
EUROPEAN JOURNAL OF INTERNAL MEDICINE
(2021)
Review
Medicine, General & Internal
Jen-Wei Liu, Shen-Hua Lin, Lin-Chien Wang, Hsiao-Yean Chiu, Jen-Ai Lee
Summary: This study compared the efficacy and safety of neuraminidase inhibitors and the endonuclease inhibitor for the treatment of seasonal influenza among healthy adults and children. The results showed that zanamivir was associated with the shortest time to alleviation of influenza symptoms, while baloxavir was associated with reduced rate of influenza-related complications.
Article
Pharmacology & Pharmacy
Sofia Tejada, Alexandre M. Tejo, Yolanda Pena-Lopez, Carlos G. Forero, Xavier Corbella, Jordi Rello
Summary: The study found that baloxavir and neuraminidase inhibitors (NAIs) have a significant reduction effect on complications of uncomplicated influenza, especially in reducing antibiotic prescriptions. Single-dose baloxavir is non-inferior to NAIs in terms of safety and efficacy.
EXPERT REVIEW OF CLINICAL PHARMACOLOGY
(2021)
Article
Biochemistry & Molecular Biology
Sphamandla E. Mtambo, Samuel C. Ugbaja, Aganze G. Mushebenge, Bahijjahtu H. Abubakar, Mthobisi L. Ntuli, Hezekiel M. Kumalo
Summary: This study investigates the mechanism and dynamics of the E119V mutation on the peramivir-neuraminidase complex of the H7N9 virus. Molecular dynamic simulations and analysis reveal that the E119V substitution confers greater stability on the protein complex. This research provides valuable insights for future drug design and control of avian influenza.
Article
Environmental Sciences
Magdalena Swierczynska, Dagmara M. Mirowska-Guzel, Edyta Pindelska
Summary: This article presents the possibilities of using all available antiviral drugs specific for influenza A and B, and compares the currently recommended anti-influenza medications. It highlights the promising new drug baloxavir marboxil, and suggests further research on combination therapy.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2022)
Article
Biochemistry & Molecular Biology
Sphamandla E. Mtambo, Samuel C. Ugbaja, Hezekiel M. Kumalo
Summary: The emergence of the avian influenza virus H7N9 in China has raised concerns due to its potential to cause serious respiratory diseases in humans. Studies have shown that a specific mutation in the virus can lead to resistance to the antiviral drug peramivir. Molecular dynamics approaches have been used to evaluate the impact of this mutation on drug resistance, revealing changes in the binding affinity and interactions with the drug.
Article
Infectious Diseases
Deepali Kumar, Michael G. Ison, Jean-Paul Mira, Tobias Welte, Jick Hwan Ha, David S. Hui, Nanshan Zhong, Takefumi Saito, Laurie Katugampola, Neil Collinson, Sarah Williams, Steffen Wildum, Andrew Ackrill, Barry Clinch, Nelson Lee
Summary: This study tested the combination of baloxavir with NAIs in hospitalized patients with severe influenza but found no superior clinical outcomes compared to NAIs alone. The combination was well tolerated, suggesting that combination antivirals may not be routinely indicated in clinical practice for this patient population.
LANCET INFECTIOUS DISEASES
(2022)
Article
Biochemistry & Molecular Biology
Samuel C. Ugbaja, Sphamandla E. Mtambo, Aganze G. Mushebenge, Patrick Appiah-Kubi, Bahijjahtu H. Abubakar, Mthobisi L. Ntuli, Hezekiel M. Kumalo
Summary: The use of vaccinations and antiviral medications has become popular for treating avian influenza H7N9 virus. This study investigated the impact of the E119V mutation on the resistance of the virus to oseltamivir. Molecular dynamics simulations showed that the oseltamivir-wildtype complex was more thermodynamically stable than the oseltamivir-E119V mutant complex. The E119V mutation resulted in lower conformational stability and weaker protein-ligand interactions.
Article
Pharmacology & Pharmacy
Andrei A. Ivashchenko, Jeremy C. Jones, Dmitry O. Shkil, Yan A. Ivanenkov, Philippe Noriel Q. Pascua, Melissa K. Penaflor, Ruben N. Karapetian, Elena A. Govorkova, Alexandre V. Ivachtchenko
Summary: In this study, the efficacy of a new orally-dosed neuraminidase inhibitor (NAI) AV5080 against different subtypes of influenza viruses was examined. AV5080 showed superior in vitro efficacy compared to currently approved NAIs, oseltamivir and zanamivir. However, it exhibited reduced inhibition against certain viral variants, such as NA-E119G and NA-R292K. These findings suggest that AV5080 is a promising orally-dosed NAI.
ANTIVIRAL RESEARCH
(2023)
Article
Immunology
Chia-Ping Su, K. Arnold Chan, Ching-Tai Huang, Chi-Tai Fang
Summary: The study shows that inhaled zanamivir is as effective as oral oseltamivir in preventing influenza-related hospitalization or death for outpatients.
CLINICAL INFECTIOUS DISEASES
(2022)
Article
Infectious Diseases
Maki Kiso, Seiya Yamayoshi, Yoshihiro Kawaoka
Summary: This study discovered mutations in influenza viruses that confer resistance to neuraminidase inhibitors and baloxavir, and evaluated the effectiveness of oseltamivir, baloxavir, and favipiravir against these mutant viruses. The results showed that favipiravir was effective in treating infections caused by these mutant viruses, while oseltamivir and baloxavir were not.
JOURNAL OF ANTIMICROBIAL CHEMOTHERAPY
(2023)
Review
Chemistry, Medicinal
Kuanglei Wang, Huicong Zhang, Yongshou Tian
Summary: This review covers influenza drugs, mutation types of neuraminidase, molecular mechanisms of drug resistance, strategies to enhance drug susceptibility, and alternative therapies.
EUROPEAN JOURNAL OF MEDICINAL CHEMISTRY
(2022)
Article
Infectious Diseases
Yu-Hsing Fang, Tzu-Herng Hsu, Tzu-Yin Lin, Chia-Hung Liu, Shou-Chu Chou, Jie-Ying Wu, Pang-Chung Perng
Summary: The study compared the efficacy of IV peramivir and oral oseltamivir treatments in influenza patients, showing similar clinical efficacy between the two treatments with no significant difference.
EXPERT REVIEW OF ANTI-INFECTIVE THERAPY
(2021)
Article
Multidisciplinary Sciences
Hiroshige Mikamo, Yusuke Koizumi, Yuka Yamagishi, Nobuhiro Asai, Yuko Miyazono, Toshikazu Shinbo, Michiko Horie, Kenichi Togashi, Elissa M. Robbins, Nobuo Hirotsu
Summary: This study compared the performance of the Liat test on the cobas Liat system with RADTs in diagnosing influenza. The results showed that the Liat test had higher sensitivity and specificity in the early stages of infection, making it more effective for diagnosing influenza in children and adults.
Article
Infectious Diseases
Yu-Hsiang Hsieh, Andrea F. Dugas, Frank LoVecchio, Breana McBryde, Erin P. Ricketts, Kathryn Saliba-Shaw, Richard E. Rothman
Summary: The study compared outcomes of high-risk emergency department patients treated with IV peramivir versus oral oseltamivir, and found that both treatment options were similarly effective in managing influenza infections.
INFLUENZA AND OTHER RESPIRATORY VIRUSES
(2021)
Article
Computer Science, Artificial Intelligence
Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, Xiaoli Li, Cuntai Guan
Summary: Sleep staging is crucial for diagnosing and treating sleep disorders. Current data-driven deep learning models for automatic sleep staging have limitations when dealing with real-world scenarios. To overcome these limitations, this study proposes a novel adversarial learning framework called ADAST, which addresses the domain shift problem in the unlabeled target domain. The proposed framework outperforms state-of-the-art methods in six cross-domain scenarios.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Biochemical Research Methods
Shamima Rashid, Suresh Sundaram, Chee Keong Kwoh
Summary: Protein secondary structure prediction is a classic problem in computational biology, and it is widely used in structural characterization and homology inference. This study extends a previous approach of using a compact model and applies it to Deep Belief Networks (DBN). The results show that the performance of DBN is superior to other deep learning models, and it is effective in detecting structural fold switching.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Computer Science, Information Systems
Bentao Zou, Yuefen Wang, Chee Keong Kwoh, Yonghua Cen
Summary: This study investigates collaboration patterns in funded teams from the perspective of knowledge flow. By identifying scientific teams, we found that common collaboration patterns play important roles in knowledge exchange, while uncommon patterns hinder knowledge activities. These findings have significant implications for understanding funded collaborations and the funding system.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Article
Computer Science, Interdisciplinary Applications
Rui Yin, Zihan Luo, Pei Zhuang, Min Zeng, Min Li, Zhuoyi Lin, Chee Keong Kwoh
Summary: This study proposes a framework called ViPal for virulence prediction in mice, which incorporates discrete prior viral mutation and reassortment information into machine learning models to improve the accuracy of influenza virus virulence prediction. Experimental results demonstrate that ViPal outperforms existing methods in terms of computational efficiency and performance, and the use of SHAP analysis provides interpretable insights into the contributing factors for prediction.
JOURNAL OF BIOMEDICAL INFORMATICS
(2023)
Article
Engineering, Environmental
Junjie Yang, Fanrong Zhao, Jie Zheng, Yulan Wang, Xunchang Fei, Yongjun Xiao, Mingliang Fang
Summary: Identification of harmful environmental pollutants is commonly done using liquid chromatography with high-resolution mass spectrometry. Prioritization of candidates is important yet challenging due to the large number of candidates. This study aimed to prioritize candidates based on their toxicity and identification evidence. An R package, NTAprioritization.R, was developed for fast prioritization of suspect lists.
JOURNAL OF HAZARDOUS MATERIALS
(2023)
Article
Computer Science, Information Systems
Mohamed Ragab, Emadeldeen Eldele, Wee Ling Tan, Chuan-Sheng Foo, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, Xiaoli Li
Summary: Unsupervised domain adaptation methods aim to generalize well on unlabeled test data with shifted distribution. Existing works on time series domain adaptation suffer from inconsistencies in evaluation schemes, datasets, and neural network architectures. To address these issues, a benchmarking evaluation suite (AdaTime) is developed to evaluate different domain adaptation methods on time series data. Extensive experiments have been conducted to evaluate 11 methods on five datasets, revealing practical insights and building a foundation for future works.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2023)
Article
Computer Science, Artificial Intelligence
Zhuoyi Lin, Lei Feng, Xingzhi Guo, Yu Zhang, Rui Yin, Chee Keong Kwoh, Chi Xu
Summary: In this article, a novel representation learning-based model called COMET is proposed, which can simultaneously model the high-order interaction patterns among historical interactions and embedding dimensions. This is achieved through horizontal stacking of embeddings and utilization of convolutional neural networks (CNN) with different kernel sizes. The effectiveness and rationality of the proposed method are demonstrated through extensive experiments on various public implicit feedback datasets.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2023)
Article
Biochemical Research Methods
Ke Zhang, Min Wu, Yong Liu, Yimiao Feng, Jie Zheng
Summary: The study proposes a model named KR4SL to predict synthetic lethality (SL) partners for a given primary gene. This model captures the structural semantics of a knowledge graph (KG) by efficiently constructing and learning from relational digraphs in the KG. It encodes the semantic information of the relational digraphs by fusing textual semantics of entities into propagated messages and enhancing the sequential semantics of paths using a recurrent neural network. Extensive experiments show that KR4SL outperforms all the baselines and provides explanatory subgraphs for the predicted gene pairs, unveiling the prediction process and mechanisms underlying synthetic lethality. The improved predictive power and interpretability indicate the practical usefulness of deep learning in SL-based cancer drug target discovery.
Article
Computer Science, Interdisciplinary Applications
Xiaolei Yu, Zhibin Zhao, Xingwu Zhang, Shaohua Tian, Chee-Keong Kwoh, Xiaoli Li, Xuefeng Chen
Summary: This paper proposes a universal transfer network for fault diagnosis that can handle various domain adaptation settings. It utilizes self-supervised learning and entropy-based feature alignment to improve the diagnosis performance.
COMPUTERS IN INDUSTRY
(2023)
Article
Computer Science, Artificial Intelligence
Zhuoyi Lin, Sheng Zang, Rundong Wang, Zhu Sun, J. Senthilnath, Chi Xu, Chee Keong Kwoh
Summary: In this paper, we propose a novel Intention-aware Re-ranking Model with Dynamic Transformer Encoder (RAISE) to perform user-specific prediction based on their intentions. We mine latent user intentions from text reviews and model them explicitly for each user-item pair. We introduce a dynamic transformer encoder to capture user-specific inter-item relationships, utilizing the learned latent user intentions. Experimental results show the superiority of our proposed RAISE, with significant improvements in Precision@5, MAP@5, and NDCG@5.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Chi Li, Jacqueline Chua, Florian Schwarzhans, Rahat Husain, Michael J. A. Girard, Shivani Majithia, Yih-Chung Tham, Ching-Yu Cheng, Tin Aung, Georg Fischer, Clemens Vass, Inna Bujor, Chee Keong Kwoh, Alina Popa-Cherecheanu, Leopold Schmetterer, Damon Wong
Summary: Studies have shown that machine learning can accurately detect glaucoma, but the performance of models across different ethnicities has not been evaluated. This study aimed to validate machine learning models for glaucoma detection using optical coherence tomography (OCT) data. The study involved constructing and testing machine learning models on Asian and Caucasian datasets. Results showed that the machine learning models performed better than the measured data for glaucoma detection in the Asian dataset, but the performance varied in the Caucasian dataset. The study highlights the importance of considering ethnicity when applying machine learning models in clinical practice.
SCIENTIFIC REPORTS
(2023)
Article
Engineering, Biomedical
Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, Xiaoli Li
Summary: In the past few years, there has been a significant advancement in deep learning for EEG-based sleep stage classification. However, the success of these models relies on a large amount of labeled data for training, making them less applicable in real-world scenarios. Self-supervised learning has emerged as a successful technique to overcome the scarcity of labeled data. This paper evaluates the effectiveness of self-supervised learning in improving the performance of existing sleep stage classification models with limited labels.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Biochemical Research Methods
Rui Yin, Nyi Nyi Thwin, Pei Zhuang, Zhuoyi Lin, Chee Keong Kwoh
Summary: This study presents a 2D convolutional neural network (IAV-CNN) model to predict influenza antigenic variants. By using a new distributed representation of amino acids and a specific architecture, the model achieves state-of-the-art performance in experiments.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2022)
Proceedings Paper
Automation & Control Systems
Chenyang Li, Chee Keong Kwoh, Xiaoli Li, Lingfei Mo, Ruqiang Yan
Summary: This paper presents a fault diagnosis algorithm based on multi-sensor information fusion using the modified Graph Attention Network. The algorithm can effectively reflect the fault states of machinery and improve the diagnostic accuracy.
2022 17TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION (ICARCV)
(2022)
Article
Computer Science, Artificial Intelligence
Mohamed Ragab, Emadeldeen Eldele, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, Xiaoli Li
Summary: This paper presents a method to address the domain shift problem in time series data through a self-supervised autoregressive domain adaptation (SLARDA) framework. The proposed framework improves the performance of time series domain adaptation by utilizing a self-supervised learning module, a novel autoregressive domain adaptation technique, and an ensemble teacher model to align the class-wise distribution in the target domain.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)