Back to Search
Start Over
GCAEMDA: Predicting miRNA-disease associations via graph convolutional autoencoder
- Source :
- PLoS Computational Biology, Vol 17, Iss 12, p e1009655 (2021), PLoS Computational Biology
- Publication Year :
- 2021
- Publisher :
- Public Library of Science (PLoS), 2021.
-
Abstract
- microRNAs (miRNAs) are small non-coding RNAs related to a number of complicated biological processes. A growing body of studies have suggested that miRNAs are closely associated with many human diseases. It is meaningful to consider disease-related miRNAs as potential biomarkers, which could greatly contribute to understanding the mechanisms of complex diseases and benefit the prevention, detection, diagnosis and treatment of extraordinary diseases. In this study, we presented a novel model named Graph Convolutional Autoencoder for miRNA-Disease Association Prediction (GCAEMDA). In the proposed model, we utilized miRNA-miRNA similarities, disease-disease similarities and verified miRNA-disease associations to construct a heterogeneous network, which is applied to learn the embeddings of miRNAs and diseases. In addition, we separately constructed miRNA-based and disease-based sub-networks. Combining the embeddings of miRNAs and diseases, graph convolutional autoencoder (GCAE) was utilized to calculate association scores of miRNA-disease on two sub-networks, respectively. Furthermore, we obtained final prediction scores between miRNAs and diseases by adopting an average ensemble way to integrate the prediction scores from two types of subnetworks. To indicate the accuracy of GCAEMDA, we applied different cross validation methods to evaluate our model whose performances were better than the state-of-the-art models. Case studies on a common human diseases were also implemented to prove the effectiveness of GCAEMDA. The results demonstrated that GCAEMDA was beneficial to infer potential associations of miRNA-disease.<br />Author summary Numerous studies have demonstrated that miRNAs are closely related to several common human diseases, so observing unverified associations between miRNAs and diseases is conducive to the diagnose and treatment of complex diseases. Considerable models proposed to infer potential miRNA-disease associations have made the prediction more effective and productive. We constructed GCAEMDA model to acquire more accuracy prediction result by integrating graph convolutional network and autoencoder to make prediction based on multi-source miRNA and disease information. The five-fold cross validation and global leave-one-out cross validation were implemented to evaluate the performance of our model. Consequently, GCAEMDA reached AUCs of 0.9415 and 0.9505 respectively that were distinctly higher than AUCs of other comparative models. Furthermore, we carried out case studies on lung neoplasms and breast neoplasms to demonstrate the practical application of the model, 47 and 47 of top-50 candidate miRNAs were confirmed by experimental reports. In summary, GCAEMDA could be considered as an effective and accuracy model to reveal relationship between miRNAs and diseases.
- Subjects :
- Social Sciences
Disease Vectors
Biochemistry
Lung and Intrathoracic Tumors
Machine Learning
Mathematical and Statistical Techniques
Medical Conditions
Neoplasms
Breast Tumors
Medicine and Health Sciences
Biology (General)
Ecology
Applied Mathematics
Simulation and Modeling
Semantics
Nucleic acids
Infectious Diseases
Computational Theory and Mathematics
Oncology
Modeling and Simulation
Area Under Curve
Physical Sciences
Algorithms
Research Article
Computer and Information Sciences
QH301-705.5
Research and Analysis Methods
Cellular and Molecular Neuroscience
Machine Learning Algorithms
Artificial Intelligence
Breast Cancer
Genetics
Humans
Genetic Predisposition to Disease
Non-coding RNA
Molecular Biology
Ecology, Evolution, Behavior and Systematics
Natural antisense transcripts
Biology and life sciences
Models, Genetic
Cancers and Neoplasms
Computational Biology
Linguistics
Convolution
Gene regulation
MicroRNAs
Species Interactions
RNA
Gene expression
Neural Networks, Computer
Mathematical Functions
Mathematics
Subjects
Details
- Language :
- English
- ISSN :
- 15537358
- Volume :
- 17
- Issue :
- 12
- Database :
- OpenAIRE
- Journal :
- PLoS Computational Biology
- Accession number :
- edsair.doi.dedup.....d6ed2da924d3c8698cc3dbb07d75a3a5