iLncDA-LTR: Identification of lncRNA-disease associations by learning to rank

Wu, Hao; Qi, Liang; Zhang, Wenxiang; Zou, Quan; Hesham, Abd El-Latif; Liu, Bin

doi:10.1016/j.compbiomed.2022.105605

Cited by 12 publications

(6 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare AGLDA with seven advanced methods for predicting disease-associated lncRNAs, including GAIRD, GSMV, MGLDA, GTAN, iLncDA-LTR, VADLP, and CNNLDA GAIRD: The method integrated the homogeneous and heterogeneous information from the lncRNA–-disease–miRNA network and inferred the disease-related lncRNAs by the graph convolution and group convolution. GSMV: The prediction model was constructed based on meta-path and transformer to encode the semantic information from multiple perspectives and the dependencies among the lncRNA, disease, and miRNA nodes. MGLDA: The method sampled subgraphs based on multiple meta-paths, and then, the subgraph topologies were encoded and integrated by the graph convolutional autoencoder and the topology-level attention. GTAN: GTAN encoded the neighbor topology of each lncRNA (disease) node and the pairwise attributes by the graph attention mechanism and convolutional neural network, respectively. iLncDA-LTR: The lncRNA similarities and the disease similarities were calculated by the DOSE package and the Needleman Wunsch alignment method.…”

Section: Experimental Evaluation and Analysismentioning

confidence: 99%

“…Performance Comparison. We compare AGLDA with seven advanced methods for predicting disease-associated lncRNAs, including GAIRD, 34 GSMV, 33 MGLDA, 32 GTAN, 31 iLncDA-LTR, 41 VADLP, 30 and CNNLDA. 29 • GAIRD: The method integrated the homogeneous and heterogeneous information from the lncRNA−-disease− miRNA network and inferred the disease-related lncRNAs by the graph convolution and group convolution.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Learning Association Characteristics by Dynamic Hypergraph and Gated Convolution Enhanced Pairwise Attributes for Prediction of Disease-Related lncRNAs

Xuan,

Lu,

Cui

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

As the long non-coding RNAs (lncRNAs) play important roles during the incurrence and development of various human diseases, identifying disease-related lncRNAs can contribute to clarifying the pathogenesis of diseases. Most of the recent lncRNA-disease association prediction methods utilized the multisource data about the lncRNAs and diseases. A single lncRNA may participate in multiple disease processes, and multiple lncRNAs usually are involved in the same disease process synergistically. However, the previous methods did not completely exploit the biological characteristics to construct the informative prediction models. We construct a prediction model based on adaptive hypergraph and gated convolution for lncRNA-disease association prediction (AGLDA), to embed and encode the biological characteristics about lncRNA−disease associations, the topological features from the entire heterogeneous graph perspective, and the gated enhanced pairwise features. First, the strategy for constructing hyperedges is designed to reflect the biological characteristic that multiple lncRNAs are involved in multiple disease processes. Furthermore, each hyperedge has its own biological perspective, and multiple hyperedges are beneficial for revealing the diverse relationships among multiple lncRNAs and diseases. Second, we encode the biological features of each lncRNA (disease) node using a strategy based on dynamic hypergraph convolutional networks. The strategy may adaptively learn the features of the hyperedges and formulate the dynamically evolved hypergraph topological structure. Third, a group convolutional network is established to integrate the entire heterogeneous topological structure and multiple types of node attributes within an lncRNA−disease−miRNA graph. Finally, a gated convolutional strategy is proposed to enhance the informative features of the lncRNA−disease node pairs. The comparison experiments indicate that AGLDA outperforms seven advanced prediction methods. The ablation studies confirm the effectiveness of major innovations, and the case studies validate AGLDA's ability in application for discovering potential disease-related lncRNA candidates.

show abstract

Section: Experimental Evaluation and Analysismentioning

confidence: 99%

mentioning

confidence: 99%

Learning Association Characteristics by Dynamic Hypergraph and Gated Convolution Enhanced Pairwise Attributes for Prediction of Disease-Related lncRNAs

Xuan,

Lu,

Cui

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Recently, with the vigorous development of computer technology and the emergence of machine learning–based methods, 16 researchers have developed related models to solve different biological problems, 17 , 18 such as predicting noncoding RNA (ncRNA)–protein interactions (NPIs), miRNA-disease association (MDAs), and so on. For instance, Zhou et al.…”

Section: Introductionmentioning

confidence: 99%

Joint masking and self-supervised strategies for inferring small molecule-miRNA associations

Zhou,

Zhuo,

et al. 2024

Molecular Therapy - Nucleic Acids

Self Cite

View full text Add to dashboard Cite

“…Long noncoding RNAs (lncRNAs) regulate many significant biological processes (such as immune response and embryonic stem cell pluripotency) by linking to RNA-binding proteins ( Wapinski and Chang (2011) ; Chen and Huang (2017) ; Ping et al (2018) ; Wang et al (2020 )), Wang et al (2021 W. ) ; Peng et al (2020) ). They have been important biomarkers for cancers ( Wu et al (2022a) ; Banerjee et al (2020) ; Zhang S. et al (2021) ; Zhou G. et al (2021) ; Peng et al (2022a) ; Liang et al (2022b) ; Peng et al (2021) ; Zhou L. et al (2021) ). For example, lncRNAs AFAP1-AS1, CCAT1, CYTOR, GAS5, HOTAIR, and PVT1 are molecular regulators of lung caner ( Aftabi et al (2021) ).…”

mentioning

confidence: 99%

“…Many machine learning methods have been proposed to infer new LncRNA-Disease Associations (LDAs). For example, graph convolutional completion with conditional random ( Fan et al (2022) ), heterogeneous graph attention network with meta-paths ( Zhao et al (2022) ), graph convolutional auto-encoders ( Silva and Spinosa (2021) ), multi-view attention graph convolutional network and stacking ensemble ( Liang et al (2022b) ), and learning to rank-based model ( Wu et al (2022a) ) are widely used methods for LDA prediction.…”

mentioning

confidence: 99%

Editorial: Machine learning-based methods for RNA data analysis—Volume II

Peng

Yang²,

Wang³

et al. 2022

Front. Genet.

View full text Add to dashboard Cite

Editorial on the Research Topic Machine learning-based methods for RNA data analysis-Volume II RNAs regulate multiple biological processes including RNA transcription, splicing, stability, and translation. They play significant roles in cell biology (Connelly et al. (2016); Licatalosi and Darnell (2010); Mukherjee et al. (2022); Chen et al. (2018b)). The Encyclopedia of DNA elements project reported that only 1.5% of human genome is translated into proteins, while approximately 70%-90% is transcribed to RNAs (Falese et al. (2021)). RNAs greatly expand the range of targets from proteins to RNAs by retargeting mutated targets (Yu et al. (2019); Chen et al. (2020); Li et al. (2022); Yang et al. (2022)). Particularly, noncoding RNAs have dense linkages with human diseases including cancers. Now, RNAs have been diagnostic or prognostic markers of complex diseases (Hui et al. (2011); Xu et al. (2022); Peng et al. (2022a); Shen et al. (2022); Zhang T. et al. (2022); Chai et al. (2022)). In this topic, we aim to analyze diverse RNA data to provide clues for the diagnosis and therapy of various diseases (Dal Molin et al. (2022); Wang S. et al. (2022); Li J. et al. (2019); Liu et al. ( 2020)). Long noncoding RNAs (lncRNAs) regulate many significant biological processes (such as immune response and embryonic stem cell pluripotency) by linking to RNA-binding proteins

show abstract

iLncDA-LTR: Identification of lncRNA-disease associations by learning to rank

Cited by 12 publications

References 55 publications

Learning Association Characteristics by Dynamic Hypergraph and Gated Convolution Enhanced Pairwise Attributes for Prediction of Disease-Related lncRNAs

Learning Association Characteristics by Dynamic Hypergraph and Gated Convolution Enhanced Pairwise Attributes for Prediction of Disease-Related lncRNAs

Joint masking and self-supervised strategies for inferring small molecule-miRNA associations

Editorial: Machine learning-based methods for RNA data analysis—Volume II

Contact Info

Product

Resources

About