Kun Wang, Junlin Xu, Geng Tian, Yang Li, Xueying Zeng, Jialiang Yang
{"title":"MDAlmc: A Novel Low-rank Matrix Completion Model for MiRNADisease Association Prediction by Integrating Similarities among MiRNAs and Diseases.","authors":"Kun Wang, Junlin Xu, Geng Tian, Yang Li, Xueying Zeng, Jialiang Yang","doi":"10.2174/1566523223666230419101405","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>The importance of microRNAs (miRNAs) has been emphasized by an increasing number of studies, and it is well-known that miRNA dysregulation is associated with a variety of complex diseases. Revealing the associations between miRNAs and diseases are essential to disease prevention, diagnosis, and treatment.</p><p><strong>Methods: </strong>However, traditional experimental methods in validating the roles of miRNAs in diseases could be very expensive, labor-intensive and time-consuming. Thus, there is a growing interest in predicting miRNA-disease associations by computational methods. Though many computational methods are in this category, their prediction accuracy needs further improvement for downstream experimental validation. In this study, we proposed a novel model to predict miRNA-disease associations by low-rank matrix completion (MDAlmc) integrating miRNA functional similarity, disease semantic similarity, and known miRNA-disease associations. In the 5-fold cross-validation, MDAlmc achieved an average AUROC of 0.8709 and AUPRC of 0.4172, better than those of previous models.</p><p><strong>Results: </strong>Among the case studies of three important human diseases, the top 50 predicted miRNAs of 96% (breast tumors), 98% (lung tumors), and 90% (ovarian tumors) have been confirmed by previous literatures. And the unconfirmed miRNAs were also validated to be potential disease-associated miRNAs.</p><p><strong>Conclusion: </strong>MDAlmc is a valuable computational resource for miRNA-disease association prediction.</p>","PeriodicalId":10798,"journal":{"name":"Current gene therapy","volume":"23 4","pages":"316-327"},"PeriodicalIF":3.8000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Current gene therapy","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2174/1566523223666230419101405","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GENETICS & HEREDITY","Score":null,"Total":0}
引用次数: 0
Abstract
Introduction: The importance of microRNAs (miRNAs) has been emphasized by an increasing number of studies, and it is well-known that miRNA dysregulation is associated with a variety of complex diseases. Revealing the associations between miRNAs and diseases are essential to disease prevention, diagnosis, and treatment.
Methods: However, traditional experimental methods in validating the roles of miRNAs in diseases could be very expensive, labor-intensive and time-consuming. Thus, there is a growing interest in predicting miRNA-disease associations by computational methods. Though many computational methods are in this category, their prediction accuracy needs further improvement for downstream experimental validation. In this study, we proposed a novel model to predict miRNA-disease associations by low-rank matrix completion (MDAlmc) integrating miRNA functional similarity, disease semantic similarity, and known miRNA-disease associations. In the 5-fold cross-validation, MDAlmc achieved an average AUROC of 0.8709 and AUPRC of 0.4172, better than those of previous models.
Results: Among the case studies of three important human diseases, the top 50 predicted miRNAs of 96% (breast tumors), 98% (lung tumors), and 90% (ovarian tumors) have been confirmed by previous literatures. And the unconfirmed miRNAs were also validated to be potential disease-associated miRNAs.
Conclusion: MDAlmc is a valuable computational resource for miRNA-disease association prediction.
期刊介绍：
Current Gene Therapy is a bi-monthly peer-reviewed journal aimed at academic and industrial scientists with an interest in major topics concerning basic research and clinical applications of gene and cell therapy of diseases. Cell therapy manuscripts can also include application in diseases when cells have been genetically modified. Current Gene Therapy publishes full-length/mini reviews and original research on the latest developments in gene transfer and gene expression analysis, vector development, cellular genetic engineering, animal models and human clinical applications of gene and cell therapy for the treatment of diseases.
Current Gene Therapy publishes reviews and original research containing experimental data on gene and cell therapy. The journal also includes manuscripts on technological advances, ethical and regulatory considerations of gene and cell therapy. Reviews should provide the reader with a comprehensive assessment of any area of experimental biology applied to molecular medicine that is not only of significance within a particular field of gene therapy and cell therapy but also of interest to investigators in other fields. Authors are encouraged to provide their own assessment and vision for future advances. Reviews are also welcome on late breaking discoveries on which substantial literature has not yet been amassed. Such reviews provide a forum for sharply focused topics of recent experimental investigations in gene therapy primarily to make these results accessible to both clinical and basic researchers. Manuscripts containing experimental data should be original data, not previously published.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
