Integrating random walk and binary regression to identify novel miRNA-disease association
Abstract Background In the last few decades, cumulative experimental researches have witnessed and verified the important roles of microRNAs (miRNAs) in the development of human complex diseases. Benefitting from the rapid growth both in the availability of miRNA-related data and the development of...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-01-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12859-019-2640-9 |
| _version_ | 1818061354997645312 |
|---|---|
| author | Ya-Wei Niu Guang-Hui Wang Gui-Ying Yan Xing Chen |
| author_facet | Ya-Wei Niu Guang-Hui Wang Gui-Ying Yan Xing Chen |
| author_sort | Ya-Wei Niu |
| collection | DOAJ |
| description | Abstract Background In the last few decades, cumulative experimental researches have witnessed and verified the important roles of microRNAs (miRNAs) in the development of human complex diseases. Benefitting from the rapid growth both in the availability of miRNA-related data and the development of various analysis methodologies, up until recently, some computational models have been developed to predict human disease related miRNAs, efficiently and quickly. Results In this work, we proposed a computational model of Random Walk and Binary Regression-based MiRNA-Disease Association prediction (RWBRMDA). RWBRMDA extracted features for each miRNA from random walk with restart on the integrated miRNA similarity network for binary logistic regression to predict potential miRNA-disease associations. RWBRMDA obtained AUC of 0.8076 in the leave-one-out cross validation. Additionally, we carried out three different patterns of case studies on four human complex diseases. Specifically, Esophageal cancer and Prostate cancer were conducted as one kind of case study based on known miRNA-disease associations in HMDD v2.0 database. Out of the top 50 predicted miRNAs, 94 and 90% were respectively confirmed by recent experimental reports. To simulate new disease without known related miRNAs, the information of known Breast cancer related miRNAs was removed. As a result, 98% of the top 50 predicted miRNAs for Breast cancer were confirmed. Lymphoma, the verified ratio of which was 88%, was used to assess the prediction robustness of RWBRMDA based on the association records in HMDD v1.0 database. Conclusions We anticipated that RWBRMDA could benefit the future experimental investigations about the relation between human disease and miRNAs by generating promising and testable top-ranked miRNAs, and significantly reducing the effort and cost of identification works. |
| first_indexed | 2024-12-10T13:46:59Z |
| format | Article |
| id | doaj.art-486bf5e042ce4cc3b7cdcbbe2794228a |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-10T13:46:59Z |
| publishDate | 2019-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-486bf5e042ce4cc3b7cdcbbe2794228a2022-12-22T01:46:21ZengBMCBMC Bioinformatics1471-21052019-01-0120111310.1186/s12859-019-2640-9Integrating random walk and binary regression to identify novel miRNA-disease associationYa-Wei Niu0Guang-Hui Wang1Gui-Ying Yan2Xing Chen3School of Mathematics, Shandong UniversitySchool of Mathematics, Shandong UniversityAcademy of Mathematics and Systems Science, Chinese Academy of SciencesSchool of Information and Control Engineering, China University of Mining and TechnologyAbstract Background In the last few decades, cumulative experimental researches have witnessed and verified the important roles of microRNAs (miRNAs) in the development of human complex diseases. Benefitting from the rapid growth both in the availability of miRNA-related data and the development of various analysis methodologies, up until recently, some computational models have been developed to predict human disease related miRNAs, efficiently and quickly. Results In this work, we proposed a computational model of Random Walk and Binary Regression-based MiRNA-Disease Association prediction (RWBRMDA). RWBRMDA extracted features for each miRNA from random walk with restart on the integrated miRNA similarity network for binary logistic regression to predict potential miRNA-disease associations. RWBRMDA obtained AUC of 0.8076 in the leave-one-out cross validation. Additionally, we carried out three different patterns of case studies on four human complex diseases. Specifically, Esophageal cancer and Prostate cancer were conducted as one kind of case study based on known miRNA-disease associations in HMDD v2.0 database. Out of the top 50 predicted miRNAs, 94 and 90% were respectively confirmed by recent experimental reports. To simulate new disease without known related miRNAs, the information of known Breast cancer related miRNAs was removed. As a result, 98% of the top 50 predicted miRNAs for Breast cancer were confirmed. Lymphoma, the verified ratio of which was 88%, was used to assess the prediction robustness of RWBRMDA based on the association records in HMDD v1.0 database. Conclusions We anticipated that RWBRMDA could benefit the future experimental investigations about the relation between human disease and miRNAs by generating promising and testable top-ranked miRNAs, and significantly reducing the effort and cost of identification works.http://link.springer.com/article/10.1186/s12859-019-2640-9microRNADiseasemiRNA-disease associationRandom walkBinary regression |
| spellingShingle | Ya-Wei Niu Guang-Hui Wang Gui-Ying Yan Xing Chen Integrating random walk and binary regression to identify novel miRNA-disease association BMC Bioinformatics microRNA Disease miRNA-disease association Random walk Binary regression |
| title | Integrating random walk and binary regression to identify novel miRNA-disease association |
| title_full | Integrating random walk and binary regression to identify novel miRNA-disease association |
| title_fullStr | Integrating random walk and binary regression to identify novel miRNA-disease association |
| title_full_unstemmed | Integrating random walk and binary regression to identify novel miRNA-disease association |
| title_short | Integrating random walk and binary regression to identify novel miRNA-disease association |
| title_sort | integrating random walk and binary regression to identify novel mirna disease association |
| topic | microRNA Disease miRNA-disease association Random walk Binary regression |
| url | http://link.springer.com/article/10.1186/s12859-019-2640-9 |
| work_keys_str_mv | AT yaweiniu integratingrandomwalkandbinaryregressiontoidentifynovelmirnadiseaseassociation AT guanghuiwang integratingrandomwalkandbinaryregressiontoidentifynovelmirnadiseaseassociation AT guiyingyan integratingrandomwalkandbinaryregressiontoidentifynovelmirnadiseaseassociation AT xingchen integratingrandomwalkandbinaryregressiontoidentifynovelmirnadiseaseassociation |