Article
Biochemistry & Molecular Biology
Shimei Qin, Wan Li, Hongzheng Yu, Manyi Xu, Chao Li, Lei Fu, Shibin Sun, Yuehan He, Junjie Lv, Weiming He, Lina Chen
Summary: Drug repositioning is an effective approach to develop drugs for complex diseases like cancer and network-based computational biology approaches have been successfully applied to drug repurposing. In this study, a new strategy for network-based drug repositioning against cancer was developed. By constructing a cancer-related drug similarity network and quantifying the correlation score of each drug with specific cancer, potential repositionable drugs were identified and confirmed by clinical trial articles and databases. The targets of these drugs were significantly associated with the prognosis of NSCLC and provided valuable perspective for drug repurposing in cancer.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Biology
Xiuhong Li, Hao Yuan, Xiaoliang Wu, Chengyi Wang, Hongbo Shi, Yingli Lv
Summary: Metabolic processes in the human body are crucial for maintaining normal life activities, and abnormal concentrations of metabolites are closely linked to disease occurrence and development. Drug usage has a significant impact on metabolism, as drug metabolites can influence efficacy, toxicity, and interactions. However, our understanding of metabolite-drug associations remains incomplete, and individual data sources are often incomplete and noisy. Thus, there is an urgent need to integrate various data sources to infer reliable metabolite-drug associations.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Information Systems
Hoang Nguyen, Radin Hamidi Rad, Fattane Zarrinkalam, Ebrahim Bagheri
Summary: This paper introduces DyHNet, which learns representations for dynamic heterogeneous networks by capturing local node semantics, global network semantics, and longer-range temporal associations. Experimental results show that our proposed method outperforms state-of-the-art techniques on link prediction and node classification tasks.
INFORMATION SCIENCES
(2023)
Article
Genetics & Heredity
He-Gang Chen, Xiong-Hui Zhou
Summary: Drug repurposing/repositioning using gene expression data and protein-protein interactions can lead to novel drug indications. The MNBDR method, combining random walk algorithms and a new indicator, is effective in identifying potential drugs and revealing biological mechanisms in drug response.
Article
Biochemical Research Methods
Lijun Cai, Changcheng Lu, Junlin Xu, Yajie Meng, Peng Wang, Xiangzheng Fu, Xiangxiang Zeng, Yansen Su
Summary: The study introduces a novel method for drug repositioning based on graph convolutional network, which effectively discovers potential drugs. By designing feature extraction modules and attention mechanism, higher prediction performance is achieved. Experiments demonstrate the superior performance of this method in multiple benchmark datasets, identifying several novel drugs for disease treatment.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Biochemical Research Methods
Bo-Wei Zhao, Xiao-Rui Su, Peng-Wei Hu, Yu-Peng Ma, Xi Zhou, Lun Hu
Summary: Drug repositioning is a strategy that uses artificial intelligence techniques to discover new indicators for approved drugs and improve traditional drug discovery and development. However, most computational methods fail to consider the non-Euclidean nature of biomedical network data. To address this, a deep learning framework called DDAGDL is proposed to predict drug-drug associations. Experimental results show that this method outperforms state-of-the-art drug repositioning methods in terms of several evaluation metrics.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Pharmacology & Pharmacy
Song Lei, Xiujuan Lei, Lian Liu
Summary: The drug repositioning method VGAEDR is based on a heterogeneous network and a variational graph autoencoder, and it predicts new drug-disease associations by learning low-dimensional feature representations. Comparative experiments demonstrate the excellent performance of VGAEDR, and it has achieved success in the case study of COVID-19 drug repositioning.
FRONTIERS IN PHARMACOLOGY
(2022)
Article
Genetics & Heredity
Zhixian Liu, Qingfeng Chen, Wei Lan, Haiming Pan, Xinkun Hao, Shirui Pan
Summary: The article introduces a graph autoencoder approach for DTI prediction, which integrates diverse datasets related to drugs and targets. This method outperforms baseline methods in predictive accuracy.
FRONTIERS IN GENETICS
(2021)
Article
Medical Informatics
Hongkui Cao, Liang Zhang, Bo Jin, Shicheng Cheng, Xiaopeng Wei, Chao Che
Summary: This study focuses on mining father-son information for rare diseases, proposing a new network model GCAN for drug prediction, which outperforms traditional methods. The results show that GCAN has achieved good performance in drug repositioning.
BMC MEDICAL INFORMATICS AND DECISION MAKING
(2021)
Review
Biochemistry & Molecular Biology
Yoonbee Kim, Yi-Sue Jung, Jong-Hoon Park, Seon-Jun Kim, Young-Rae Cho
Summary: Drug repositioning, utilizing heterogeneous networks, is an effective approach to identify new therapeutic indications for approved drugs. This review summarizes network-based methods, including graph mining, matrix factorization, and deep learning, for predicting drug-disease associations. A comparison of predictive performances was conducted, revealing that methods in the graph mining and matrix factorization categories performed well overall.
Article
Physics, Multidisciplinary
Zhenpeng Liu, Shengcong Zhang, Jialiang Zhang, Mingxiao Jiang, Yi Liu
Summary: Most HIN embedding methods use meta-paths to guide random walks and overcome the bias of traditional random walks. However, the performance of these methods depends on the suitability of the generated meta-paths. This paper proposes a meta-path free method called HeteEdgeWalk, which utilizes a bidirectional edge-sampling walk strategy to better sample the network structure and achieve improved performance in node classification and clustering experiments.
Article
Computer Science, Information Systems
Baofang Hu, Hong Wang, Lutong Wang
Summary: In this study, a user feedback-based weighted signed HIN embedding method was proposed to learn comprehensive embeddings of users and items, by utilizing weighted meta-paths to measure polar similarities of users and designing a weighted signed network embedding method based on weighted sampling random walk. Through an attention mechanism, embeddings of different meta-paths were deeply fused, and further fused with attribute information using a pooling operation to capture interactions. The model optimization through a rating prediction task demonstrated its effectiveness in four datasets.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Kamal Berahmand, Elahe Nasiri, Saman Forouzandeh, Yuefeng Li
Summary: This article proposes an improved method for local random walk by encouraging the movement towards nodes with stronger influence, resulting in higher prediction accuracy. A comparison with other similarity-based methods was conducted on 11 real-world networks, and the results demonstrated its superior performance in link prediction.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Biochemical Research Methods
Lu Jiang, Jiahao Sun, Yue Wang, Qiao Ning, Na Luo, Minghao Yin
Summary: Accurate identification of drug-target interactions is crucial in drug discovery. This paper proposes a new method, DTIHNC, that integrates heterogeneous networks and cross-modal similarities to identify drug-target interactions. The method outperforms state-of-the-art methods and demonstrates its effectiveness.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Physics, Multidisciplinary
Anthony Baptista, Aitor Gonzalez, Anais Baudot
Summary: The amount and variety of data have been increasing, requiring new methods to deal with the diversity and complexity of multilayer networks. The authors propose MultiXrank, a framework that uses random walks with restart to study multilayer networks, highlighting the important influence of bipartite networks.
COMMUNICATIONS PHYSICS
(2022)
Article
Biochemical Research Methods
Chengqian Lu, Lishen Zhang, Min Zeng, Wei Lan, Guihua Duan, Jianxin Wang
Summary: Emerging evidence suggests that circRNAs, with their covalently closed loop structures, can serve as promising biomarkers for diagnosis in pathogenic processes. Computational approaches provide a cost-effective way to identify circRNA-disease associations by aggregating multi-source pathogenesis data and inferring potential associations at the system level. The proposed CDHGNN model, based on edge-weighted graph attention and heterogeneous graph neural networks, outperforms state-of-the-art algorithms in predicting circRNA-disease associations and can identify specific molecular associations and investigate biomolecular regulatory relationships in pathogenesis.
BRIEFINGS IN BIOINFORMATICS
(2023)
Review
Biochemical Research Methods
Yongfan Ming, Wenkang Wang, Rui Yin, Min Zeng, Li Tang, Shizhe Tang, Min Li
Summary: The design of enzyme catalytic stability is important in medicine and industry, but traditional methods are time-consuming and costly. Complementary computational tools using AI algorithms such as natural language processing, machine learning, and deep learning have been developed to address this issue. However, challenges in designing enzyme catalytic stability include insufficient data, large search space, inaccurate prediction, low experimental efficiency, and complex design process. The design of enzyme catalytic stability involves adjusting the flexibility and stability of the enzyme structure by designing its amino acid sequence, thereby controlling its catalytic stability.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Xiaoqing Peng, Wenjin Zhang, Wanxin Cui, Binrong Ding, Qingtong Lyu, Jianxin Wang
Summary: Alzheimer's disease (AD) is a common neurodegenerative disease, and DNA methylation is closely related to its pathological mechanism. A database named ADmeth has been designed to collect AD-related differential methylation data, containing 16,709 items identified from various brain regions and cell types in the blood, including 209 genes, 2,229 regions, and 14,271 CpG sites. The ADmeth database provides user-friendly functions for searching, submitting, and downloading data, aiming to facilitate research on the pathological mechanism of AD and non-invasive diagnosis using cell-free DNA.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Computer Science, Hardware & Architecture
Jiawei Huang, Wenlu Zhang, Yijun Li, Lin Li, Zhaoyi Li, Jin Ye, Jianxin Wang
Summary: Identifying heavy flows is crucial for network management, but it is challenging to detect heavy flow quickly and accurately in highly dynamic traffic and rapidly growing network capacity. Existing schemes trade-off efficiency, accuracy, and speed, requiring large memory for acceptable performance. To address this, ChainSketch is proposed, with advantages in memory efficiency, accuracy, and fast detection. ChainSketch utilizes selective replacement, hash chain, and compact structure, significantly improving F1-score compared to existing solutions, especially in small memory conditions.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2023)
Article
Computer Science, Hardware & Architecture
Jingling Liu, Jiawei Huang, Weihe Li, Jianxin Wang, Tian He
Summary: Datacenter networks often face path asymmetry, leading to problems like packet reordering and under-utilization of multiple paths. In this paper, we propose a load balancing mechanism called AG that adaptively adjusts switching granularity based on the degree of topology asymmetry. We also design a switch-based scheme to measure the difference of one-way delay, allowing accurate detection of topology asymmetry. Experimental results show that AG outperforms existing load balancing schemes in terms of flow completion time.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2023)
Article
Computer Science, Information Systems
Minghan Fu, Meiyun Wang, Yaping Wu, Na Zhang, Yongfeng Yang, Haining Wang, Yun Zhou, Yue Shang, Fang-Xiang Wu, Hairong Zheng, Dong Liang, Zhanli Hu
Summary: A novel two-branch network architecture called SW-GCN is proposed to improve PET image quality. The network utilizes Swin Transformer units and graph convolution operation to handle different types of input information flow and enables better processing of long-range contextual information. Experimental results demonstrate that the proposed approach outperforms state-of-the-art methods in both quantitative and qualitative evaluations.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Chemistry, Analytical
Kawsar Ahmed, Francis M. Bui, Fang-Xiang Wu
Summary: To reduce the development time and effort of standard optical biosensors, machine learning approaches have been used to predict crucial parameters and evaluate the performance of the models based on performance indicators.
Article
Biochemical Research Methods
Yanping Zeng, Yongxin He, Ruiqing Zheng, Min Li
Summary: Gene regulatory network plays a crucial role in controlling biological processes. Deciphering complex gene regulatory networks remains challenging. Recent advances in single-cell RNA sequencing enable computational inference of cell-specific gene regulatory networks. Normi is a novel gene regulatory network inference method that addresses challenges of pseudo-time information and dropout data. Normi outperforms other methods and identifies key regulators and crucial biological processes.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Bin Wang, Kun Liu, Yaohang Li, Jianxin Wang
Summary: In this research, a novel method called DFHiC is proposed to generate high-resolution Hi-C matrix from low-resolution Hi-C matrix using the dilated convolutional neural network framework. DFHiC can reliably and accurately improve the resolution of Hi-C matrix, and the super-resolution Hi-C data enhanced by DFHiC is more similar to real high-resolution Hi-C data in terms of both chromatin significant interactions and identifying topologically associating domains.
Article
Biochemical Research Methods
Xuhua Yan, Ruiqing Zheng, Fangxiang Wu, Min Li
Summary: CIAIRE is a novel contrastive learning-based batch correction framework that achieves a superior mix-heterogeneity trade-off. It proposes two complementary strategies, construction strategy and refinement strategy, to improve the appropriateness of positive pairs. CLAIRE outperforms existing methods in terms of mix-heterogeneity trade-off and achieves the best integration performance on six real datasets.
Article
Biochemical Research Methods
Neng Huang, Minghua Xu, Fan Nie, Peng Ni, Chuan-Le Xiao, Feng Luo, Jianxin Wang
Summary: We developed a deep learning-based method called NanoSNP for identifying SNP sites in low-coverage Nanopore sequencing data. NanoSNP uses a multi-step, multi-scale, and haplotype-aware pipeline to detect SNP sites and predict genotypes. Comparison with other methods showed that NanoSNP outperformed Clair, Pepper-DeepVariant, and NanoCaller in identifying SNPs, especially in difficult-to-map regions and the major histocompatibility complex regions of the human genome. NanoSNP performed comparably to Clair3 when coverage exceeded 16x.
Article
Computer Science, Information Systems
Weihe Li, Jiawei Huang, Wenjun Lyu, Baoshen Guo, Wanchun Jiang, Jianxin Wang
Summary: Current ABR algorithms do not pay enough attention to audio bitrate selection, assuming it has minimal impact on video selection. However, with the advancement of audio technologies, audio bitrate can significantly affect video selection and viewing experience. To address this issue, we propose a deep reinforcement learning-based ABR algorithm that considers both audio and video quality, achieving significant improvements in overall viewing quality.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Shigeng Zhang, Zijing Ma, Kaixuan Lu, Xuan Liu, Jia Liu, Song Guo, Albert Y. Zomaya, Jian Zhang, Jianxin Wang
Summary: This paper presents HearMe, an accurate and real-time lip-reading system built on commercial RFID devices. HearMe can help people with speech disorders communicate and interact with the world effectively. By utilizing effective data collection, signal pattern extraction, and feature extraction techniques, HearMe achieves high accuracy in mouth motion recognition and word-level recognition. The use of transfer learning enhances the model's robustness in different environments.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Multidisciplinary Sciences
Huimin Zhu, Renyi Zhou, Dongsheng Cao, Jing Tang, Min Li
Summary: This article introduces a deep learning approach called PGMG, guided by pharmacophore, to generate bioactive molecules. The molecules generated by PGMG have strong docking affinities and high scores of validity, uniqueness, and novelty.
NATURE COMMUNICATIONS
(2023)
Article
Biochemical Research Methods
Yiming Li, Min Zeng, Fuhao Zhang, Fang-Xiang Wu, Min Li
Summary: In this study, DeepCellEss, a sequence-based interpretable deep learning framework, is proposed for cell line-specific essential protein predictions. By utilizing convolutional neural networks, bidirectional long short-term memory, and multi-head self-attention mechanism, DeepCellEss achieves effective prediction performance for different cell lines and outperforms existing methods and metrics.