Identifying and Exploiting Potential miRNA-Disease Associations With Neighborhood Regularized Logistic Matrix Factorization
With the rapid development of biological research, microRNAs (miRNA) have become an attractive topic because lots of experimental studies have revealed the significant associations between miRNAs and diseases. However, considering that experiments are expensive and time-consuming, computational meth...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2018-08-01
|
Series: | Frontiers in Genetics |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/fgene.2018.00303/full |
id |
doaj-c83d2d1cbbe14b45a5c8d00da0fc6c7a |
---|---|
record_format |
Article |
spelling |
doaj-c83d2d1cbbe14b45a5c8d00da0fc6c7a2020-11-24T23:56:39ZengFrontiers Media S.A.Frontiers in Genetics1664-80212018-08-01910.3389/fgene.2018.00303409947Identifying and Exploiting Potential miRNA-Disease Associations With Neighborhood Regularized Logistic Matrix FactorizationBin-Sheng He0Jia Qu1Qi Zhao2Qi Zhao3The First Affiliated Hospital, Changsha Medical University, Changsha, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaSchool of Mathematics, Liaoning University, Shenyang, ChinaResearch Center for Computer Simulating and Information Processing of Bio-Macromolecules of Liaoning Province, Shenyang, ChinaWith the rapid development of biological research, microRNAs (miRNA) have become an attractive topic because lots of experimental studies have revealed the significant associations between miRNAs and diseases. However, considering that experiments are expensive and time-consuming, computational methods for predicting associations between miRNAs and diseases have become increasingly crucial. In this study, we proposed a neighborhood regularized logistic matrix factorization method for miRNA-disease association prediction (NRLMFMDA) by integrating miRNA functional similarity, disease semantic similarity, Gaussian interaction profile kernel similarity, and experimentally validation of disease-miRNA association. We used Gaussian interaction profile kernel similarity to cover the shortage of the traditional similarity to make it more reasonable and complete. Furthermore, NRLMFMDA also considered the important influences of the neighborhood information and took full advantage of them to improve the accuracy of the miRNA-disease association prediction. We also improved the accuracy by giving higher weights to the known association data in the process of calculating the potential association probabilities. In the global and the local leave-one-out cross validation, NRLMFMDA got the AUCs of 0.9068 and 0.8239, respectively. Moreover, the average AUC of NRLMFMDA in 5-fold cross validation was 0.8976 ± 0.0034. All the three kinds of cross validations have shown significant advantages to a number of previous models. In the case studies of breast neoplasms, esophageal neoplasms and lymphoma according to known miRNA-disease associations in the recent version of HMDD database, there were 78, 80, and 74% of top 50 predicted related miRNAs verified to have associations with these three diseases, respectively. In the further case studies for new disease without any known related miRNAs and the previous version of HMDD database, there were also high proportions of the predicted miRNAs verified by experimental reports. All the validation experiment results have demonstrated the effectiveness and practicability of NRLFMDA to predict the potential miRNA-disease associations.https://www.frontiersin.org/article/10.3389/fgene.2018.00303/fullmicroRNAdiseaseassociation predictionneighborhood regularizedmatrix factorization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Bin-Sheng He Jia Qu Qi Zhao Qi Zhao |
spellingShingle |
Bin-Sheng He Jia Qu Qi Zhao Qi Zhao Identifying and Exploiting Potential miRNA-Disease Associations With Neighborhood Regularized Logistic Matrix Factorization Frontiers in Genetics microRNA disease association prediction neighborhood regularized matrix factorization |
author_facet |
Bin-Sheng He Jia Qu Qi Zhao Qi Zhao |
author_sort |
Bin-Sheng He |
title |
Identifying and Exploiting Potential miRNA-Disease Associations With Neighborhood Regularized Logistic Matrix Factorization |
title_short |
Identifying and Exploiting Potential miRNA-Disease Associations With Neighborhood Regularized Logistic Matrix Factorization |
title_full |
Identifying and Exploiting Potential miRNA-Disease Associations With Neighborhood Regularized Logistic Matrix Factorization |
title_fullStr |
Identifying and Exploiting Potential miRNA-Disease Associations With Neighborhood Regularized Logistic Matrix Factorization |
title_full_unstemmed |
Identifying and Exploiting Potential miRNA-Disease Associations With Neighborhood Regularized Logistic Matrix Factorization |
title_sort |
identifying and exploiting potential mirna-disease associations with neighborhood regularized logistic matrix factorization |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Genetics |
issn |
1664-8021 |
publishDate |
2018-08-01 |
description |
With the rapid development of biological research, microRNAs (miRNA) have become an attractive topic because lots of experimental studies have revealed the significant associations between miRNAs and diseases. However, considering that experiments are expensive and time-consuming, computational methods for predicting associations between miRNAs and diseases have become increasingly crucial. In this study, we proposed a neighborhood regularized logistic matrix factorization method for miRNA-disease association prediction (NRLMFMDA) by integrating miRNA functional similarity, disease semantic similarity, Gaussian interaction profile kernel similarity, and experimentally validation of disease-miRNA association. We used Gaussian interaction profile kernel similarity to cover the shortage of the traditional similarity to make it more reasonable and complete. Furthermore, NRLMFMDA also considered the important influences of the neighborhood information and took full advantage of them to improve the accuracy of the miRNA-disease association prediction. We also improved the accuracy by giving higher weights to the known association data in the process of calculating the potential association probabilities. In the global and the local leave-one-out cross validation, NRLMFMDA got the AUCs of 0.9068 and 0.8239, respectively. Moreover, the average AUC of NRLMFMDA in 5-fold cross validation was 0.8976 ± 0.0034. All the three kinds of cross validations have shown significant advantages to a number of previous models. In the case studies of breast neoplasms, esophageal neoplasms and lymphoma according to known miRNA-disease associations in the recent version of HMDD database, there were 78, 80, and 74% of top 50 predicted related miRNAs verified to have associations with these three diseases, respectively. In the further case studies for new disease without any known related miRNAs and the previous version of HMDD database, there were also high proportions of the predicted miRNAs verified by experimental reports. All the validation experiment results have demonstrated the effectiveness and practicability of NRLFMDA to predict the potential miRNA-disease associations. |
topic |
microRNA disease association prediction neighborhood regularized matrix factorization |
url |
https://www.frontiersin.org/article/10.3389/fgene.2018.00303/full |
work_keys_str_mv |
AT binshenghe identifyingandexploitingpotentialmirnadiseaseassociationswithneighborhoodregularizedlogisticmatrixfactorization AT jiaqu identifyingandexploitingpotentialmirnadiseaseassociationswithneighborhoodregularizedlogisticmatrixfactorization AT qizhao identifyingandexploitingpotentialmirnadiseaseassociationswithneighborhoodregularizedlogisticmatrixfactorization AT qizhao identifyingandexploitingpotentialmirnadiseaseassociationswithneighborhoodregularizedlogisticmatrixfactorization |
_version_ |
1725457370464649216 |