Cargando…

MDMF: Predicting miRNA–Disease Association Based on Matrix Factorization with Disease Similarity Constraint

MicroRNAs (miRNAs) have drawn enormous attention owing to their significant roles in various biological processes, as well as in the pathogenesis of human diseases. Therefore, predicting miRNA–disease associations is a pivotal task for the early diagnosis and better understanding of disease pathogen...

Descripción completa

Detalles Bibliográficos
Autor principal: Ha, Jihwan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9224864/
https://www.ncbi.nlm.nih.gov/pubmed/35743670
http://dx.doi.org/10.3390/jpm12060885
_version_ 1784733473515241472
author Ha, Jihwan
author_facet Ha, Jihwan
author_sort Ha, Jihwan
collection PubMed
description MicroRNAs (miRNAs) have drawn enormous attention owing to their significant roles in various biological processes, as well as in the pathogenesis of human diseases. Therefore, predicting miRNA–disease associations is a pivotal task for the early diagnosis and better understanding of disease pathogenesis. To date, numerous computational frameworks have been proposed to identify potential miRNA–disease associations without escalating the costs and time required for clinical experiments. In this regard, I propose a novel computational framework (MDMF) for identifying potential miRNA–disease associations using matrix factorization with a disease similarity constraint. To evaluate the performance of MDMF, I calculated the area under the ROC curve (AUCs) in the framework of global and local leave-one-out cross-validation (LOOCV). In conclusion, MDMF achieved reliable AUC values of 0.9147 and 0.8905 for global and local LOOCV, respectively, which was a significant improvement upon the previous methods. Additionally, case studies were conducted on two major human cancers (breast cancer and lung cancer) to validate the effectiveness of MDMF. Comprehensive experimental results demonstrate that MDMF not only discovers miRNA–disease associations efficiently but also deciphers the underlying roles of miRNAs in the pathogenesis of diseases at a system level.
format Online
Article
Text
id pubmed-9224864
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-92248642022-06-24 MDMF: Predicting miRNA–Disease Association Based on Matrix Factorization with Disease Similarity Constraint Ha, Jihwan J Pers Med Article MicroRNAs (miRNAs) have drawn enormous attention owing to their significant roles in various biological processes, as well as in the pathogenesis of human diseases. Therefore, predicting miRNA–disease associations is a pivotal task for the early diagnosis and better understanding of disease pathogenesis. To date, numerous computational frameworks have been proposed to identify potential miRNA–disease associations without escalating the costs and time required for clinical experiments. In this regard, I propose a novel computational framework (MDMF) for identifying potential miRNA–disease associations using matrix factorization with a disease similarity constraint. To evaluate the performance of MDMF, I calculated the area under the ROC curve (AUCs) in the framework of global and local leave-one-out cross-validation (LOOCV). In conclusion, MDMF achieved reliable AUC values of 0.9147 and 0.8905 for global and local LOOCV, respectively, which was a significant improvement upon the previous methods. Additionally, case studies were conducted on two major human cancers (breast cancer and lung cancer) to validate the effectiveness of MDMF. Comprehensive experimental results demonstrate that MDMF not only discovers miRNA–disease associations efficiently but also deciphers the underlying roles of miRNAs in the pathogenesis of diseases at a system level. MDPI 2022-05-27 /pmc/articles/PMC9224864/ /pubmed/35743670 http://dx.doi.org/10.3390/jpm12060885 Text en © 2022 by the author. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ha, Jihwan
MDMF: Predicting miRNA–Disease Association Based on Matrix Factorization with Disease Similarity Constraint
title MDMF: Predicting miRNA–Disease Association Based on Matrix Factorization with Disease Similarity Constraint
title_full MDMF: Predicting miRNA–Disease Association Based on Matrix Factorization with Disease Similarity Constraint
title_fullStr MDMF: Predicting miRNA–Disease Association Based on Matrix Factorization with Disease Similarity Constraint
title_full_unstemmed MDMF: Predicting miRNA–Disease Association Based on Matrix Factorization with Disease Similarity Constraint
title_short MDMF: Predicting miRNA–Disease Association Based on Matrix Factorization with Disease Similarity Constraint
title_sort mdmf: predicting mirna–disease association based on matrix factorization with disease similarity constraint
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9224864/
https://www.ncbi.nlm.nih.gov/pubmed/35743670
http://dx.doi.org/10.3390/jpm12060885
work_keys_str_mv AT hajihwan mdmfpredictingmirnadiseaseassociationbasedonmatrixfactorizationwithdiseasesimilarityconstraint