Corrigendum: Predicting multiple types of associations between miRNAs and diseases based on graph regularized weighted tensor decomposition

A Corrigendum on
Predicting multiple types of associations between miRNAs and diseases based on graph regularized weighted tensor decomposition

by Ouyang D, Miao R, Wang J, Liu X, Xie S, Ai N, Dang Q and Liang Y (2022). Front. Bioeng. Biotechnol. 10:911769. doi: 10.3389/fbioe.2022.911769

In the published article, there was an error in affiliation(s) 1. Instead of “Faculty of Information Technology, Macau University of Science and Technology, Taipa, China,” it should be “Faculty of Information Technology, Macau University of Science and Technology, Macau, China.”

In the published article, there was an error. Mathematical symbols are inconsistent.

A correction has been made to 3 Methods, “3.1 CP decomposition,” Paragraph Number 5.

This sentence previously stated:

“CANDECOMP/PARAFAC (CP) decomposition is one of the most common tensor decomposition forms (Kolda and Bader, 2009). Given the miRNA-disease-type tensor $\mathcal{X}\in {\mathbb{R}}^{|m|\times |n|\times |t|}$, the CP decomposition model can be represented as follows:

$\mathcal{X}\approx \sum _{s=1}^S{m}_s◦d_s◦t_s\equiv [[M,D,T]](1)$

where the symbol ◦ represents the vector outer product, S is a positive integer and ${\mathit{m}}_s\in {\mathbb{R}}^{|m|\times |1|}$, ${\mathit{d}}_s\in {\mathbb{R}}^{|n|\times |1|}$ and ${\mathit{t}}_s\in {\mathbb{R}}^{|t|\times |1|}$. M = [m₁ m₂ ⋯ m_S], D = [d₁ d₂ ⋯ d_S], and T = [t₁ t₂ ⋯ t_S] are the factor matrices with respect to different dimensions.”

The corrected sentence appears below:

“CANDECOMP/PARAFAC (CP) decomposition is one of the most common tensor decomposition forms (Kolda and Bader, 2009). Given the miRNA-disease-type tensor $\mathcal{X}\in {\mathbb{R}}^{|m|\times |n|\times |t|}$, the CP decomposition model can be represented as follows:

$\mathcal{X}\approx \sum _{s=1}^S{\mathit{m}}_s◦{\mathit{d}}_s◦{\mathit{t}}_s\equiv [[M,D,T]](2)$

where the symbol ◦ represents the vector outer product, S is a positive integer and ${\mathit{m}}_s\in {\mathbb{R}}^{|m|\times 1}$, ${\mathit{d}}_s\in {\mathbb{R}}^{|n|\times 1}$ and ${\mathit{t}}_s\in {\mathbb{R}}^{|t|\times 1}$. M = [m₁ m₂ ⋯ m_S], D = [d₁ d₂ ⋯ d_S], and T = [t₁ t₂ ⋯ t_S] are the factor matrices with respect to different dimensions.”

Note that mathematic symbols are bolded to represent vectors. Also, “${\mathit{m}}_s\in {\mathbb{R}}^{|m|\times |1|}$, ${\mathit{d}}_s\in {\mathbb{R}}^{|n|\times |1|}$ and ${\mathit{t}}_s\in {\mathbb{R}}^{|t|\times |1|}$” should be changed to “${\mathit{m}}_s\in {\mathbb{R}}^{|m|\times 1}$, ${\mathit{d}}_s\in {\mathbb{R}}^{|n|\times 1}$ and ${\mathit{t}}_s\in {\mathbb{R}}^{|t|\times 1}$.”

The authors apologize for this error and state that this does not change the scientific conclusions of the article in any way. The original article has been updated.

Publisher’s note

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.

Reference

Kolda, T. G., and Bader, B. W. (2009). Tensor decompositions and applications. SIAM Rev. 51, 455–500. doi:10.1137/07070111X

CrossRef Full Text | Google Scholar