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
Biochemistry & Molecular Biology
Yoonbee Kim, Young-Rae Cho
Summary: Drug repositioning, which identifies new therapeutic indications for existing drugs, has the advantage of reducing cost and time of drug discovery. This article proposes a network-based method that integrates drug-disease, drug-gene, and disease-gene associations to predict drug-gene-disease associations through tensor decomposition. Experimental results show that the proposed method outperforms existing models in triple association prediction and also achieves competitive accuracy in pairwise association prediction.
Article
Genetics & Heredity
Zihu Guo, Yingxue Fu, Chao Huang, Chunli Zheng, Ziyin Wu, Xuetong Chen, Shuo Gao, Yaohua Ma, Mohamed Shahen, Yan Li, Pengfei Tu, Jingbo Zhu, Zhenzhong Wang, Wei Xiao, Yonghua Wang
Summary: NOGEA is a method for accurately inferring master genes that control specific diseases by quantitatively calculating their perturbation abilities on directed disease-specific gene networks. The master genes identified by NOGEA have a high reliability for predicting disease-specific initiation events and progression risk, and can be used to extract the underlying information of different diseases, thus revealing mechanisms of disease comorbidity. The approved therapeutic targets are topologically localized in a small neighborhood of master genes in the interactome network, providing a new way for predicting drug-disease associations.
GENOMICS PROTEOMICS & BIOINFORMATICS
(2021)
Article
Biochemical Research Methods
Yajie Meng, Changcheng Lu, Min Jin, Junlin Xu, Xiangxiang Zeng, Jialiang Yang
Summary: In this study, a novel neural collaborative filtering approach is proposed for drug repositioning, which utilizes deep-learning approaches based on a heterogeneous network. The approach takes advantage of localized information in different networks and models the complex drug-disease associations effectively. The effectiveness of the approach is verified through benchmarking comparisons and validated against clinical trials and authoritative databases.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Pharmacology & Pharmacy
Rui Xuan Huang, Damrongrat Siriwanna, William C. Cho, Tsz Kin Wan, Yan Rong Du, Adam N. Bennett, Qian Echo He, Jun Dong Liu, Xiao Tai Huang, Kei Hang Katie Chan
Summary: In this study, a pipeline based on machine learning was developed to predict potential target genes for LUAD and discover potential drugs for its treatment through drug repositioning. The pipeline achieved good predictive performance and identified several potential therapeutic drugs for LUAD.
FRONTIERS IN PHARMACOLOGY
(2022)
Review
Biochemical Research Methods
Apurva Badkas, Sebastien De Landtsheer, Thomas Sauter
Summary: Drug repositioning has gained significant attention in the past decade. Computational approaches, particularly network-based methods, have played a crucial role in uncovering unintuitive functional relationships and identifying repositioning candidates in drug-disease and other networks. Various structural network measures contribute to these efforts and hold potential for wider applications, especially in the field of drug repositioning.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Computer Science, Information Systems
Jiazhou Chen, Jie Huang, Yi Liao, Lei Zhu, Hongmin Cai
Summary: Identifying gene-drug interactions is crucial for precise drug repurposing and understanding biological mechanisms. Existing studies mainly focus on one-to-one or one-to-many interactions, overlooking the multivariate patterns between genes and drugs.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Immunology
Xinyue Yin, Xinming Rang, Xiangxiang Hong, Yinglian Zhou, Chaohan Xu, Jin Fu
Summary: In this study, target genes and target pathways for drug repositioning in multiple sclerosis (MS) were identified based on transcriptomic changes in MS immune cells. The study found that targeting both the PI3K-Akt signaling pathway and Chemokine signaling pathway, or using tyrosine kinase inhibitors may be potential therapies for the treatment of MS.
FRONTIERS IN IMMUNOLOGY
(2022)
Article
Biochemical Research Methods
Yiran Huang, Yongjin Bin, Pingfan Zeng, Wei Lan, Cheng Zhong
Summary: Drug repositioning is an important approach for predicting new disease indications for existing drugs. This paper proposes a neighborhood interaction-based method called NetPro for drug repositioning via label propagation. Experimental results show that NetPro can effectively identify potential drug-disease associations and achieve better prediction performance than existing methods. Case studies demonstrate that NetPro is capable of predicting promising candidate disease indications for drugs.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Computer Science, Theory & Methods
Sumin Li, Xiuqin Pan
Summary: Computational drug repositioning technology aims to rediscover the potential use of drugs already on the market, accelerate the traditional drug development process, and reduce costs and instability. The new HSSIGNN model utilizes graph neural networks and side information to capture effective hidden feature representations of drugs and diseases, improving the model's generalization capability.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Review
Oncology
Binsheng He, Fangxing Hou, Changjing Ren, Pingping Bing, Xiangzuo Xiao
Summary: Drug repositioning, the practice of using existing drugs for new disease indications, has become popular due to the high cost and failure rate of developing new drugs. With the aid of high-throughput sequencing techniques, efficient methods have been proposed and applied in drug repositioning and personalized tumor treatment. Computational methods for drug repositioning can be divided into four categories, with future directions focusing on more sensitive methods for individualized tumor treatment.
FRONTIERS IN ONCOLOGY
(2021)
Article
Mathematics, Applied
Ying Ying Keng, Kiam Heong Kwa, Kurunathan Ratnavelu
Summary: The study demonstrates the significance of central drugs in a drug network for drug repositioning, suggesting that top central drugs are more likely to repurpose their neighboring drugs as new treatment options. This research provides novel insights into complementing drug repositioning efforts and highlights the importance of network centrality measures in guiding systematic analysis.
APPLIED MATHEMATICS AND COMPUTATION
(2021)
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)
Review
Biochemical Research Methods
Fei Wang, Yulian Ding, Xiujuan Lei, Bo Liao, Fang-Xiang Wu
Summary: Drug repositioning is an important method for exploring new uses of existing drugs in drug discovery, especially in pre-clinical stages. Computational approaches, including machine learning and deep learning, have shown great potential in saving time and reducing costs compared to traditional drug discovery methods.
CURRENT BIOINFORMATICS
(2022)
Review
Biochemical Research Methods
Huimin Luo, Min Li, Mengyun Yang, Fang-Xiang Wu, Yaohang Li, Jianxin Wang
Summary: Drug repositioning, through computational methods, can systematically identify potential drug-target interactions and drug-disease interactions, significantly reducing cost and duration. This review summarizes available biomedical data and public databases, discusses various drug repositioning approaches, and analyzes common data sets and evaluation metrics used in this field.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Biochemical Research Methods
Liang Yu, Mingfei Xia, Qi An
Summary: In this paper, a Network Embedding frameWork in MultIplex Network (NEWMIN) is proposed to predict synthetic drug combinations. By integrating information from multiple networks and determining their importance, several novel drug combinations have been discovered, with better performance compared to other methods.
BRIEFINGS IN BIOINFORMATICS
(2022)
Review
Biochemistry & Molecular Biology
Chunyan Ao, Lin Gao, Liang Yu
Summary: This review provides a systematic summary of DNA methylation and its relationship with related diseases, including DNA methylation databases, prediction tools, and machine learning algorithms. A deep understanding of DNA methylation mechanisms can contribute to accurate prediction and treatment of related diseases.
CURRENT MEDICINAL CHEMISTRY
(2022)
Article
Biochemical Research Methods
Liang Yu, Yujia Zheng, Lin Gao
Summary: In this study, a novel method for predicting miRNA-disease associations was proposed, achieving high accuracy in miRNA-disease association prediction and providing new insights for drug development and disease prediction.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Chunyan Ao, Quan Zou, Liang Yu
Summary: This study developed a predictor based on machine learning to identify 2'-O-methylation modification sites in RNA. The predictor showed high efficiency and accuracy in identifying modification sites across multiple species, outperforming existing tools.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Pharmacology & Pharmacy
Haozheng Li, Yihe Pang, Bin Liu, Liang Yu
Summary: This study highlights the importance and functions of intrinsically disordered regions (IDRs) and their molecular recognition features (MoRFs) in protein structures. Understanding the functions of MoRFs is crucial for pharmaceutical and disease pathogenesis. However, existing computational methods fail to distinguish the different functions of MoRFs. In this paper, a multi-label learning approach using the Binary Relevance (BR) strategy and ensemble learning techniques is proposed to predict MoRF functions. The experimental results show that the MoRF-FUNCpred model performs well in predicting MoRF functions. To the best of our knowledge, MoRF-FUNCpred is the first predictor for predicting MoRF functions.
FRONTIERS IN PHARMACOLOGY
(2022)
Article
Biochemical Research Methods
Shujie Ren, Liang Yu, Lin Gao
Summary: In this study, we propose a pretraining framework called MGP-DR for drug pair representation learning. By integrating drug molecular graph information and target information, the model utilizes self-supervised learning strategies to predict drug-drug interactions and drug combinations. It achieves promising performance across multiple metrics compared to other state-of-the-art methods.
Article
Biochemical Research Methods
Chunyan Ao, Quan Zou, Liang Yu
Summary: A novel predictor, RFhy-m2G, was developed in this study to identify m2G modification sites using hybrid features and random forest. The predictor achieved high accuracies through feature fusion and optimal feature selection.
Article
Biochemical Research Methods
Yanming Wei, Quan Zou, Furong Tang, Liang Yu
Summary: WMSA software uses the divide-and-conquer method to split sequences into clusters, aligns them into profiles with the center star strategy, and then performs a progressive profile-profile alignment. This method balances time, space, and alignment quality better than MAFFT, and performs well in test experiments on highly conserved datasets.
Article
Biochemistry & Molecular Biology
Liang Yu, Bingyi Ju, Shujie Ren
Summary: The study proposes a heuristic learning method based on graph neural networks for predicting microRNA-disease associations (HLGNN-MDA); demonstrates its performance through tenfold cross-validation; and showcases its reliability in breast cancer, hepatocellular carcinoma, and renal cell carcinoma through case studies.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Biology
Bo Li, Liang Yu, Lin Gao
Summary: This study proposes a method to classify cancer based on multidimensional SNV features. By analyzing SNVs in cancer samples, the extracted features exhibit similar distribution patterns in the cluster centers of each cancer type. The classification accuracy using the KNN algorithm reaches approximately 97%, with the potential for oncogene discovery. The validated oncogenes in the identified features have the highest importance among the 8 cancers.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Biology
Kai Yang, Lin Gao, HongXia Hao, Liang Yu
Summary: This study identified potential prognostic markers of sepsis by analyzing the molecular characteristics of sepsis patients. A 9-gene prognostic signature for sepsis was constructed and its predictive effect was verified in two cohorts. Furthermore, the study revealed the association between these genes and sepsis through immune infiltration analysis and gene set enrichment analysis.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Biology
Xinyu Xu, Lin Gao, Liang Yu
Summary: The global spread of COVID-19 has posed significant health risks, and researchers are seeking new methods to detect lung infections. Utilizing CT scans and deep learning models to accurately segment infected areas remains a challenge. To address this, a novel segmentation network called GOLF-Net is proposed, combining global and local features to enhance the accuracy of infected area segmentation. Transfer learning is implemented to overcome limited CT data. Results show that GOLF-Net outperforms existing models with a Dice coefficient of 95.09% and an IoU of 92.58%.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Biology
Zhaoyang Huang, Shengjian Chen, Liang Yu
Summary: Drug development is expensive, complex, and time-consuming, and the number of drugs put into application is limited. Identifying drug-disease correlations can provide valuable information for drug discovery and repurposing. Computational drug repurposing, specifically the application of deep neural networks, has become a popular and effective method for predicting novel treatments for diseases. This study proposes a drug indication prediction algorithm called DIDVAE, which utilizes double variational autoencoders to generate new data and predict drug-disease associations. Experimental results demonstrate that the DIDVAE algorithm outperforms other prediction algorithms and the predicted drug-disease associations have been practically validated.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Biochemical Research Methods
Lu Chen, Liang Yu, Lin Gao
Summary: The MDAGS framework provides a solution to the problem of drug-resistant bacteria by optimizing and generating novel compounds with potent antibacterial activity.
Review
Multidisciplinary Sciences
Chunyan Ao, Shihu Jiao, Yansu Wang, Liang Yu, Quan Zou
Summary: The rapid growth of biological sequences has driven the application of machine learning in this field, focusing on function and modification classification. Establishing a support website to provide information and datasets for classification methods, discussing current challenges and future prospects.