An ensemble learning-based method for prediction of novel disease-microrna associations. Le, D. H., Pham, V. H., & Nguyen, T. T. In Proceedings - 2017 9th International Conference on Knowledge and Systems Engineering, KSE 2017, volume 2017-Janua, pages 7–12, November, 2017. Institute of Electrical and Electronics Engineers Inc..
An ensemble learning-based method for prediction of novel disease-microrna associations [link]Paper  doi  abstract   bibtex   
Many studies have shown the associations of microRNAs on human diseases. A number of computational methods have been proposed to predict such associations by ranking candidate microRNAs ac-cording to their relevance to a disease. Among them, network-based methods are usually based on microRNA functional similarity networks which are constructed based on microRNA-target interactions. Therefore, the prediction performances of these methods are highly dependent on the quality of such interactions which are usually predicted by computational methods. Meanwhile, machine learning-based methods usually formulate the disease miRNA prediction as a classification problem, where novel associations between disease and miRNA are predicted based on known disease-miRNA associations. However, those methods are mainly based on single binary classifiers; therefore, they have a limitation in prediction performance. In this study, we proposed a new method, namely RFMDA, to predict disease-associated miRNAs. Our method based on Random Forest (RF), an ensemble technique, where the final classifier is constructed by multitude of decision trees, to perform the prediction. In order to compare with other previous methods, we use the same procedure to build training samples, where positive training samples are known disease-miRNA associations. In addition, features of each sample measure either functional or phenotypical similarities between miRNAs or phenotypes, respectively. Simulation results showed that RFMDA outperformed previous learning-based methods including two binary classifiers (i.e., Naïve Bayes and two-class Support Vector Machines) and one semi-supervised classifier (i.e., Regularized Least Square). Moreover, using the trained model, we can predict novel miRNAs associated to some diseases such as breast cancer, colorectal cancer and hepatocellular carcinoma.
@inproceedings{Le2017,
	title = {An ensemble learning-based method for prediction of novel disease-microrna associations},
	volume = {2017-Janua},
	isbn = {978-1-5386-3576-6},
	url = {http://www.scopus.com/inward/record.url?eid=2-s2.0-85043686097%7B%5C&%7DpartnerID=MN8TOARS},
	doi = {10.1109/KSE.2017.8119426},
	abstract = {Many studies have shown the associations of microRNAs on human diseases. A number of computational methods have been proposed to predict such associations by ranking candidate microRNAs ac-cording to their relevance to a disease. Among them, network-based methods are usually based on microRNA functional similarity networks which are constructed based on microRNA-target interactions. Therefore, the prediction performances of these methods are highly dependent on the quality of such interactions which are usually predicted by computational methods. Meanwhile, machine learning-based methods usually formulate the disease miRNA prediction as a classification problem, where novel associations between disease and miRNA are predicted based on known disease-miRNA associations. However, those methods are mainly based on single binary classifiers; therefore, they have a limitation in prediction performance. In this study, we proposed a new method, namely RFMDA, to predict disease-associated miRNAs. Our method based on Random Forest (RF), an ensemble technique, where the final classifier is constructed by multitude of decision trees, to perform the prediction. In order to compare with other previous methods, we use the same procedure to build training samples, where positive training samples are known disease-miRNA associations. In addition, features of each sample measure either functional or phenotypical similarities between miRNAs or phenotypes, respectively. Simulation results showed that RFMDA outperformed previous learning-based methods including two binary classifiers (i.e., Naïve Bayes and two-class Support Vector Machines) and one semi-supervised classifier (i.e., Regularized Least Square). Moreover, using the trained model, we can predict novel miRNAs associated to some diseases such as breast cancer, colorectal cancer and hepatocellular carcinoma.},
	booktitle = {Proceedings - 2017 9th {International} {Conference} on {Knowledge} and {Systems} {Engineering}, {KSE} 2017},
	publisher = {Institute of Electrical and Electronics Engineers Inc.},
	author = {Le, Duc Hau and Pham, Van Huy and Nguyen, Thuy Thi},
	month = nov,
	year = {2017},
	keywords = {Binary classifier, Ensemble learning, Prediction of disease-miRNA association, Semi-supervised classifier},
	pages = {7--12},
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021