An efficient approach based on multi-sources information to predict circRNA-disease associations using deep convolutional neural network

MOTIVATION Emerging evidence indicates that circular RNA (circRNA) plays a crucial role in human disease. Using circRNA as biomarker gives rise to a new perspective regarding our diagnosing of diseases and understanding of disease pathogenesis. However, detection of circRNA-disease associations by biological experiments alone is often blind, limited to small-scale, high-cost and time-consuming. Therefore, there is an urgent need for reliable computational methods to rapidly infer the potential circRNA-disease associations on a large scale and to provide the most promising candidates for biological experiments. RESULTS In this paper, we propose an efficient computational method based on multi-source information combined with deep convolutional neural network to predict circRNA-disease associations. The method first fuses multi-source information including disease semantic similarity, disease Gaussian interaction profile kernel similarity, and circRNA Gaussian interaction profile kernel similarity, and then extracts its hidden deep feature through the convolutional neural network, and finally sends them to the extreme learning machine classifier for prediction. The five-fold cross-validation results show that the proposed method achieves 87.21% prediction accuracy with 88.50% sensitivity at the AUC of 86.67% on the CIRCR2Disease dataset. In comparison with the state-of-the-art SVM classifier and other feature extraction methods on the same dataset, the proposed model achieves the best results. In addition, we also obtained experimental support for prediction results by searching published literature. As a result, 7 of the top 15 circRNA-disease pairs with the highest scores were confirmed by literature. These results demonstrate that the proposed model is a suitable method for predicting circRNA-disease associations and can provide reliable candidates for biological experiments. The source code and datasets explored in this work are available at https://github.com/look0012/circRNA-Disease-association. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.

[1]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[2]  Yanzhi Guo,et al.  Using support vector machine combined with auto covariance to predict protein–protein interactions from protein sequences , 2008, Nucleic acids research.

[3]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[4]  Yong Zhou,et al.  Advancing the prediction accuracy of protein-protein interactions by utilizing evolutionary information from position-specific scoring matrix and ensemble classifier. , 2017, Journal of theoretical biology.

[5]  Elena Marchiori,et al.  Gaussian interaction profile kernels for predicting drug-target interaction , 2011, Bioinform..

[6]  Schraga Schwartz,et al.  Transcriptome-wide discovery of circular RNAs in Archaea , 2011, Nucleic acids research.

[7]  Lingqing Wang,et al.  Predicting Protein-Protein Interactions from Matrix-Based Protein Sequence Using Convolution Neural Network and Feature-Selective Rotation Forest , 2019, Scientific Reports.

[8]  Bing Zhou,et al.  A novel identified circular RNA, circRNA_010567, promotes myocardial fibrosis via suppressing miR-141 by targeting TGF-β1. , 2017, Biochemical and biophysical research communications.

[9]  Zhouxiao Li,et al.  An emerging function of circRNA-miRNAs-mRNA axis in human diseases , 2017, Oncotarget.

[10]  Wathiq Laftah Al-Yaseen,et al.  Multi-level hybrid support vector machine and extreme learning machine based on modified K-means for intrusion detection system , 2017, Expert Syst. Appl..

[11]  Zhu-Hong You,et al.  RFDT: A Rotation Forest-based Predictor for Predicting Drug-Target Interactions Using Drug Structure and Protein Sequence Information. , 2016, Current protein & peptide science.

[12]  Yong Zhou,et al.  Ens-PPI: A Novel Ensemble Classifier for Predicting the Interactions of Proteins Using Autocovariance Transformation from PSSM , 2016, BioMed research international.

[13]  Yong Zhou,et al.  Using Two-dimensional Principal Component Analysis and Rotation Forest for Prediction of Protein-Protein Interactions , 2018, Scientific Reports.

[14]  Xiujuan Lei,et al.  PWCDA: Path Weighted Method for Predicting circRNA-Disease Associations , 2018, International journal of molecular sciences.

[15]  Menglong Li,et al.  Predicting G‐protein coupled receptors–G‐protein coupling specificity based on autocross‐covariance transform , 2006, Proteins.

[16]  D. Otaegui,et al.  Circular RNA profiling reveals that circular RNAs from ANXA2 can be used as new biomarkers for multiple sclerosis , 2017, Human molecular genetics.

[17]  Julia Salzman,et al.  Cell-Type Specific Features of Circular RNA Expression , 2013, PLoS genetics.

[18]  Michael K. Slevin,et al.  Circular RNAs are abundant, conserved, and associated with ALU repeats. , 2013, RNA.

[19]  Karin M. Verspoor,et al.  Associating disease-related genetic variants in intergenic regions to the genes they impact , 2014, PeerJ.

[20]  Petar Glažar,et al.  Circular RNAs in the Mammalian Brain Are Highly Abundant, Conserved, and Dynamically Expressed. , 2015, Molecular cell.

[21]  Xiujuan Lei,et al.  CircR2Disease: a manually curated database for experimentally supported circular RNAs associated with various diseases , 2018, Database J. Biol. Databases Curation.

[22]  M. Zweig,et al.  Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. , 1993, Clinical chemistry.

[23]  Yongqun He,et al.  A genome-wide MeSH-based literature mining system predicts implicit gene-to-gene relationships and networks , 2013, BMC Systems Biology.

[24]  Ney Lemke,et al.  An improved interolog mapping-based computational prediction of protein-protein interactions with increased network coverage. , 2014, Integrative biology : quantitative biosciences from nano to macro.

[25]  Lei Liu,et al.  Hsa_circ_0001649: A circular RNA and potential novel biomarker for hepatocellular carcinoma. , 2016, Cancer biomarkers : section A of Disease markers.

[26]  Yiguo Jiang,et al.  A novel regulatory network among LncRpa, CircRar1, MiR-671 and apoptotic genes promotes lead-induced neuronal cell apoptosis , 2016, Archives of Toxicology.

[27]  Yufei Huang,et al.  Correction: Prediction of microRNAs Associated with Human Diseases Based on Weighted k Most Similar Neighbors , 2013, PloS one.

[28]  Shenmin Zhang,et al.  circRNA_100290 plays a role in oral cancer by functioning as a sponge of the miR-29 family , 2017, Oncogene.

[29]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[30]  Li-Ping Li,et al.  MLMDA: a machine learning approach to predict and validate MicroRNA–disease associations by integrating of heterogenous information sources , 2019, Journal of Translational Medicine.

[31]  Dong Wang,et al.  Inferring the human microRNA functional similarity and functional network based on microRNA-associated diseases , 2010, Bioinform..

[32]  D. Riesner,et al.  Viroids are single-stranded covalently closed circular RNA molecules existing as highly base-paired rod-like structures. , 1976, Proceedings of the National Academy of Sciences of the United States of America.

[33]  J A Swets,et al.  Measuring the accuracy of diagnostic systems. , 1988, Science.

[34]  Alexandros Iosifidis,et al.  Graph Embedded Extreme Learning Machine , 2016, IEEE Transactions on Cybernetics.

[35]  Fang-Xiang Wu,et al.  DWNN-RLS: regularized least squares method for predicting circRNA-disease associations , 2018, BMC Bioinformatics.

[36]  S. Hazen,et al.  Gut Microbial Metabolite TMAO Enhances Platelet Hyperreactivity and Thrombosis Risk , 2016, Cell.

[37]  Xing Chen,et al.  LMTRDA: Using logistic model tree to predict MiRNA-disease associations by fusing multi-source information of sequences and similarities , 2019, PLoS Comput. Biol..

[38]  J. Kjems,et al.  Natural RNA circles function as efficient microRNA sponges , 2013, Nature.

[39]  Sebastian D. Mackowiak,et al.  Circular RNAs are a large class of animal RNAs with regulatory potency , 2013, Nature.

[40]  R. Venkatesh Babu,et al.  DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations , 2015, IEEE Transactions on Image Processing.

[41]  Fang-Xiang Wu,et al.  Prediction of CircRNA-Disease Associations Using KATZ Model Based on Heterogeneous Networks , 2018, International journal of biological sciences.

[42]  J. D. Mills,et al.  Characterization of circular RNAs landscape in multiple system atrophy brain , 2016, Journal of neurochemistry.

[43]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[44]  Hong-Bin Shen,et al.  Learning distributed representations of RNA sequences and its application for predicting RNA-protein binding sites with a convolutional neural network , 2018, Neurocomputing.

[45]  Feng Li,et al.  The landscape of microRNA, Piwi-interacting RNA, and circular RNA in human saliva. , 2015, Clinical chemistry.