Article
Biochemical Research Methods
Lizhi Liu, Hiroshi Mamitsuka, Shanfeng Zhu
Summary: Exploring the relationship between human proteins and abnormal phenotypes is crucial for disease prevention, diagnosis and treatment. HPOFiller, a graph convolutional network-based approach, aims to predict missing HPO annotations and outperforms other state-of-the-art methods through stringent evaluations.
Article
Biochemical Research Methods
Qiang Yang, Xiaokun Li
Summary: This study proposed a computational model named BiGAN for predicting lncRNA-disease associations. By utilizing disease semantic similarity, lncRNA sequence similarity, and Gaussian interaction profile kernel similarities, features were constructed to predict unverified associations, showing significantly better performance than other methods.
BMC BIOINFORMATICS
(2021)
Review
Pharmacology & Pharmacy
Jing Yan, Ruobing Wang, Jianjun Tan
Summary: Mutations and dysregulation of lncRNAs play a significant role in the development of complex human diseases. Predicting new potential LDAs can aid in understanding disease pathogenesis, detecting disease markers, and improving disease diagnosis, prevention, and treatment. Computational methods have proven to be effective in narrowing down the screening scope of biological experiments, reducing their duration and cost. This review highlights recent advances in computational methods for predicting LDAs, including LDA databases, lncRNA/disease similarity calculations, and advanced computational models. The limitations of various computational models are analyzed, and future challenges and directions for development are discussed.
DRUG DISCOVERY TODAY
(2023)
Article
Computer Science, Artificial Intelligence
Mei-Neng Wang, Zhu-Hong You, Lei Wang, Li-Ping Li, Kai Zheng
Summary: In this study, a new computational approach LDGRNMF was developed to predict lncRNA-disease associations, considering similarity calculation based on Gaussian interaction profile kernel and disease semantic information, as well as nearest known neighbor interaction profiles weighting to reconstruct association matrix. LDGRNMF outperformed other methods with an AUC of 0.8985 in cross-validation experiments, and showed high accuracy in predicting potential associations in case studies for stomach cancer, breast cancer, and lung cancer.
Article
Genetics & Heredity
Min Chen, Yingwei Deng, Ang Li, Yan Tan
Summary: This article presents an integrated method called LPARP, based on label-propagation algorithm and random projection, for predicting lncRNA-disease associations. Empirical experiments show that LPARP outperforms existing methods and is validated in case studies of various diseases. LPARP can serve as an effective and reliable tool for biomedical research.
FRONTIERS IN GENETICS
(2022)
Article
Biochemistry & Molecular Biology
Yongheng Wang, Jincheng Zhai, Xianglu Wu, Enoch Appiah Adu-Gyamfi, Lingping Yang, Taihang Liu, Meijiao Wang, Yubin Ding, Feng Zhu, Yingxiong Wang, Jing Tang
Summary: This study developed a novel strategy (DAnet) that combines disease associations with the cis-regulatory network between lncRNAs and neighboring protein-coding genes for functional annotation of lncRNAs. Compared to the traditional differential expression-based approach, DAnet performs better in identifying experimentally validated lncRNAs, and the identified biological pathways are associated with diseases.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2022)
Article
Biology
Guo-Zheng Zhang, Ying-Lian Gao
Summary: Many experiments have shown that human long non-coding RNAs (lncRNAs) are implicated in disease development. Predicting the association between lncRNAs and diseases is crucial for disease treatment and drug development. This paper proposes an algorithm called BRWMC that effectively predicts potential lncRNA-disease associations using similarity networks and matrix completion methods. Experimental results demonstrate the reliability of BRWMC.
COMPUTATIONAL BIOLOGY AND CHEMISTRY
(2023)
Article
Biochemical Research Methods
Jiaxin Zhang, Quanmeng Sun, Cheng Liang
Summary: The paper presents a novel computational framework for predicting lncRNA-disease associations by combining l1-norm graph and multi-label learning, achieving robustness and comparable performance. Experimental results demonstrate the effectiveness of the method in prediction tasks, particularly in the case of prostate cancer where it shows practicality in identifying potential prognostic biomarkers.
CURRENT BIOINFORMATICS
(2021)
Article
Biochemical Research Methods
Guo-Bo xie, Rui-Bin Chen, Zhi-Yi Lin, Guo-Sheng Gu, Jun-Rui Yu, Zhen-guo Liu, Ji Cui, Lie-qing Lin, Lang-cheng Chen
Summary: Recent studies have found that lncRNAs are closely linked to human diseases and provide new opportunities for detection and therapy. Existing similarity fusion methods suffer from noise and self-similarity loss. This paper proposes a new prediction approach, SSMF-BLNP, which combines selective similarity matrix fusion and bidirectional linear neighborhood label propagation, and achieves better performance compared to other state-of-the-art methods.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Genetics & Heredity
Yahan Li, Mingrui Zhang, Junliang Shang, Feng Li, Qianqian Ren, Jin-Xing Liu
Summary: In this study, a computational model iLncDA-RSN is proposed based on reliable similarity networks for identifying potential lncRNA-disease associations (LDAs). The model integrates feature vectors of lncRNA-disease pairs from lncRNA and disease perspectives and uses random forest algorithm to identify potential LDAs.
FRONTIERS IN GENETICS
(2023)
Article
Biochemical Research Methods
Mei-Neng Wang, Xue-Jun Xie, Zhu-Hong You, Leon Wong, Li-Ping Li, Zhan-Heng Chen
Summary: In this paper, a novel method called KNN-NMF is proposed to infer associations between circRNA and disease. The experiment results indicate that KNN-NMF outperforms other methods in prediction performance and shows good performance in case studies of two common diseases.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Zhonghao Lu, Hua Zhong, Lin Tang, Jing Luo, Wei Zhou, Lin Liu
Summary: Long non-coding RNAs (lncRNAs) play crucial roles in the development and progression of various diseases. Accurately predicting potential lncRNA-disease associations remains challenging. This study proposes a novel computational method, HGC-GAN, which combines heterogeneous graph convolutional neural networks (GCN) and generative adversarial networks (GAN) to predict potential lncRNA-disease associations.
PLOS COMPUTATIONAL BIOLOGY
(2023)
Article
Biochemical Research Methods
Buwen Cao, Shuguang Deng, Hua Qin, Jiawei Luo, Guanghui Li, Cheng Liang
Summary: This study successfully inferred miRNA-disease relationships by constructing a miRNA functional similarity network and utilizing an improved K-means algorithm. Experimental results demonstrated that the performance of IK-means algorithm was superior to classical K-means algorithms in identifying new miRNA-disease associations.
JOURNAL OF COMPUTATIONAL BIOLOGY
(2021)
Review
Biochemical Research Methods
Zhongqi Wen, Cheng Yan, Guihua Duan, Suning Li, Fang-Xiang Wu, Jianxin Wang
Summary: This study provides a comprehensive overview of existing methods for predicting human microbe-disease associations, including data sources, method classification, and performance evaluation. Based on computational principles and experimental results, the advantages and disadvantages of these methods are discussed, and suggestions for improvement are proposed.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Genetics & Heredity
Lingyun Dai, Rong Zhu, Jinxing Liu, Feng Li, Juan Wang, Junliang Shang
Summary: This paper introduces a novel method, MSF-UBRW, to explore new long non-coding RNA-disease associations (LDAs). The method calculates the similarities of lncRNAs and diseases and predicts potential associations. The fusion of multiple similarities improves the prediction performance, and the method's reliable prediction ability is validated through statistical methods and case studies.
Article
Computer Science, Information Systems
Cui-Na Jiao, Jin-Xing Liu, Juan Wang, Junliang Shang, Chun-Hou Zheng
Summary: The MccNLRR method, based on the maximum correntropy criterion, offers robustness in handling high technical noise and dropouts in scRNA-seq data. By combining an effective loss function with low rank representation, it accurately and robustly distinguishes cell subtypes while capturing global and local structures of the data.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Genetics & Heredity
Yijun Gu, Yan Sun, Junliang Shang, Feng Li, Boxin Guan, Jin-Xing Liu
Summary: In genome-wide association studies, detecting epistasis is crucial for the occurrence and diagnosis of complex human diseases. However, existing methods have limitations. In this study, a multi-objective artificial bee colony algorithm based on a scale-free network (SFMOABC) was proposed and demonstrated to outperform other methods in simulation and real data experiments.
Article
Genetics & Heredity
Feng Li, Xin Chu, Lingyun Dai, Juan Wang, Jinxing Liu, Junliang Shang
Summary: The study utilizes machine learning algorithms and multi-omics characteristics to detect cancer driver genes in pan-cancer data. It is found that mutational features are crucial, but other types of features also play a role in the top 45 feature combinations which are the most effective.
Article
Biochemistry & Molecular Biology
Fanjie Meng, Feng Li, Jin-Xing Liu, Junliang Shang, Xikui Liu, Yan Li
Summary: Compared to single-drug therapy, drug combinations have great potential in cancer treatment. This study proposes a network-embedding-based prediction model, NEXGB, which integrates protein interaction network information to predict the synergistic relationship between drug combinations and cancer cell lines. Experimental results show that NEXGB outperforms current methods and improves the predictive power in discovering relationships between drugs and cancer cell lines.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Genetics & Heredity
Feng Li, Zhensheng Sun, Jin-Xing Liu, Junliang Shang, Lingyun Dai, Xikui Liu, Yan Li
Summary: Tumor stratification is crucial for cancer diagnosis and treatment. Recent advances in high-throughput sequencing technologies have enabled the integration of multiple molecular datasets for cancer type stratification. In this study, a network embedding approach was introduced for tumor stratification by integrating multi-omics data. The results showed that this method achieved high accuracy in classifying cancer types and identifying subtypes that were significantly associated with patient survival.
G3-GENES GENOMES GENETICS
(2022)
Article
Neurosciences
Xiang Liu, Juan Wang, Junliang Shang, Jinxing Liu, Lingyun Dai, Shasha Yuan
Summary: This paper presents a seizure detection algorithm based on VMD and DF model, which can effectively improve the accuracy of automatic identification of epileptic seizures.
Article
Genetics & Heredity
Junliang Shang, Xinrui Cai, Tongdui Zhang, Yan Sun, Yuanyuan Zhang, Jinxing Liu, Boxin Guan
Summary: This study proposes a new simulation method called EpiReSIM for generating models without marginal effects. Two strategies are provided to solve the models and simulation data is generated using a resampling method. Experimental results show that EpiReSIM has advantages in preserving allele frequencies and calculating high-order models.
Article
Genetics & Heredity
Lingyun Dai, Rong Zhu, Jinxing Liu, Feng Li, Juan Wang, Junliang Shang
Summary: This paper introduces a novel method, MSF-UBRW, to explore new long non-coding RNA-disease associations (LDAs). The method calculates the similarities of lncRNAs and diseases and predicts potential associations. The fusion of multiple similarities improves the prediction performance, and the method's reliable prediction ability is validated through statistical methods and case studies.
Article
Genetics & Heredity
Yan Sun, Yijun Gu, Qianqian Ren, Yiting Li, Junliang Shang, Jin-Xing Liu, Boxin Guan
Summary: This paper proposes a module detection method called MDSN for identifying high-order epistatic interactions. By constructing an SNP network and using a node evaluation measure, it can effectively detect high-order interactions associated with diseases.
Article
Computer Science, Information Systems
Tian-Jing Qiao, Jin-Xing Liu, Junliang Shang, Shasha Yuan, Chun-Hou Zheng, Juan Wang
Summary: Single-cell RNA sequencing (scRNA-seq) technology provides expression profiles of individual cells, driving biological research into a new stage. However, the high-dimensional, sparse, and noisy nature of scRNA-seq data poses challenges for single-cell clustering. In response, we propose a personalized low-rank subspace clustering method (PLRLS) that learns more accurate subspace structures from both global and local perspectives.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Information Systems
Shasha Yuan, Xiang Liu, Junliang Shang, Jin-Xing Liu, Juan Wang, Weidong Zhou
Summary: Automatic seizure detection can improve early detection, treatment planning, and reduce medical workload. This study proposes a novel LE-GMMs and improved Deep Forest learning algorithm for epileptic seizure detection, achieving high accuracy in distinguishing seizure and non-seizure EEG signals.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Information Systems
Junliang Shang, Qi Zou, Qianqian Ren, Boxin Guan, Feng Li, Jin-Xing Liu, Yan Sun
Summary: In this study, the graph capsule convolutional network (GCCN) method was proposed to predict the progression from mild cognitive impairment to dementia and identify its pathogenesis. The method involved discovering risk genes with higher interactions, constructing heterogeneous pathogenic information association graphs, establishing graph capsules, modeling information flows among pathogenic factors, and capturing discriminative pathogenic information flows through dynamic routing mechanism. GCCN demonstrated significant advancements and identified evidential and closely related pathogenic factors for progressive mild cognitive impairment.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Review
Chemistry, Medicinal
Yuanyuan Zhang, Zengqian Deng, Xiaoyu Xu, Yinfei Feng, Junliang Shang
Summary: Drug-drug interactions (DDI) are an important aspect of drug research that can have serious consequences for patients. Predicting these interactions accurately can improve clinical decision-making and treatment outcomes. Utilizing Artificial Intelligence (AI) advancements is crucial for achieving accurate forecasts of DDIs.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Computer Science, Information Systems
Juan Wang, Lin-Ping Wang, Sha-Sha Yuan, Feng Li, Jin-Xing Liu, Jun-Liang Shang
Summary: The development of single-cell RNA sequencing technology has provided new insights into studying disease mechanisms at the single-cell level. However, the high noise and dropout of single-cell data present challenges in cell clustering. This study proposes a novel matrix factorization method called NLRRC, which combines non-negative low-rank representation and random walk graph regularized NMF to accurately reveal the natural grouping of cells.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Yi Yang, Yan Sun, Feng Li, Boxin Guan, Jin-Xing Liu, Junliang Shang
Summary: This study proposed a model based on multiple graph convolutional networks and random forest (MGCNRF) for predicting the associations between miRNAs and diseases (MDAs). MGCNRF mapped miRNA functional similarity, sequence similarity, disease semantic similarity, target similarity, and known MDAs into four different heterogeneous networks. It then applied graph convolutional networks to extract MDA embeddings and predicted potential MDAs using random forest. MGCNRF outperformed seven state-of-the-art methods in terms of prediction performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)