A novel approach to select differential pathways associated with hypertrophic cardiomyopathy based on gene co-expression analysis

Chen, Xiaomin; Feng, Mingjun; Shen, Caijie; He, Bin; Du, Xianfeng; Yu, Yibo; Liu, Jing

doi:10.3892/mmr.2017.6667

Cited by 7 publications

(10 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the analysis of cancer data, the feature selection is to find differentially expressed genes for cancer (that is, pathogenic genes). This is of great significance in exploring the link between cancer and genes (Chen et al, 2017). For each method, the top 500 genes with the greatest differential expression are analyzed.…”

Section: Resultsmentioning

confidence: 99%

Sparse Graph Regularization Non-Negative Matrix Factorization Based on Huber Loss Model for Cancer Data Analysis

Wang

Liu

et al. 2019

Front. Genet.

View full text Add to dashboard Cite

Non-negative matrix factorization (NMF) is a matrix decomposition method based on the square loss function. To exploit cancer information, cancer gene expression data often uses the NMF method to reduce dimensionality. Gene expression data usually have some noise and outliers, while the original NMF loss function is very sensitive to non-Gaussian noise. To improve the robustness and clustering performance of the algorithm, we propose a sparse graph regularization NMF based on Huber loss model for cancer data analysis (Huber-SGNMF). Huber loss is a function between L 1-norm and L 2-norm that can effectively handle non-Gaussian noise and outliers. Taking into account the sparsity matrix and data geometry information, sparse penalty and graph regularization terms are introduced into the model to enhance matrix sparsity and capture data manifold structure. Before the experiment, we first analyzed the robustness of Huber-SGNMF and other models. Experiments on The Cancer Genome Atlas (TCGA) data have shown that Huber-SGNMF performs better than other most advanced methods in sample clustering and differentially expressed gene selection.

show abstract

Section: Resultsmentioning

confidence: 99%

Sparse Graph Regularization Non-Negative Matrix Factorization Based on Huber Loss Model for Cancer Data Analysis

Wang

Liu

et al. 2019

Front. Genet.

View full text Add to dashboard Cite

show abstract

“…Characteristic gene selection is an important task in genomics and has profound significance in exploring the relationship between pathogenic genes and cancer. 36 Due to the characteristics of a small sample, high dimensionality, and high redundancy of gene expression data, it is necessary to use the dimension reduction to select only a few pathogenic genes that are closely related to cancer from tens of thousands of genes. To explore the potential links between the characteristic genes and various diseases for early diagnosis, treatment, and precautions of cancer.…”

Section: Robustmentioning

confidence: 99%

Enhancing Characteristic Gene Selection and Tumor Classification by the Robust Laplacian Supervised Discriminative Sparse PCA

Zhang

Liu

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Characteristic gene selection and tumor classification of gene expression data play major roles in genomic research. Due to the characteristics of a small sample size and high dimensionality of gene expression data, it is a common practice to perform dimensionality reduction prior to the use of machine learning-based methods to analyze the expression data. In this context, classical principal component analysis (PCA) and its improved versions have been widely used. Recently, methods based on supervised discriminative sparse PCA have been developed to improve the performance of data dimensionality reduction. However, such methods still have limitations: most of them have not taken into consideration the improvement of robustness to outliers and noise, label information, sparsity, as well as capturing intrinsic geometrical structures in one objective function. To address this drawback, in this study, we propose a novel PCA-based method, known as the robust Laplacian supervised discriminative sparse PCA, termed RLSDSPCA, which enforces the L2,1 norm on the error function and incorporates the graph Laplacian into supervised discriminative sparse PCA. To evaluate the efficacy of the proposed RLSDSPCA, we applied it to the problems of characteristic gene selection and tumor classification problems using gene expression data. The results demonstrate that the proposed RLSDSPCA method, when used in combination with other related methods, can effectively identify new pathogenic genes associated with diseases. In addition, RLSDSPCA has also achieved the best performance compared with the state-of-the-art methods on tumor classification in terms of major performance metrics. The codes and data sets used in the study are freely available at .

show abstract

“…Reported gene-enriched pathways involve immune modulation, signal transduction, hemostasis, metabolism, muscle contraction, inflammation, and fibrosis (TGFβ pathways). [52][53][54][55] Results published so far are based on the analysis of whole myocardial samples, including cardiomyocytes, vessels, fibroblasts, and interstitial tissue, and do not provide information on the possible existence of expression profiles selectively related to coronary microvascular dysfunction.…”

Section: Comparative Functional Enrichment Analyses Identify Tissue-s...mentioning

confidence: 99%

RNA‐seq profiling reveals different pathways between remodeled vessels and myocardium in hypertrophic cardiomyopathy

et al. 2022

View full text Add to dashboard Cite

Objective: Coronary microvascular dysfunction (CMD) is a key pathophysiological feature of hypertrophic cardiomyopathy (HCM), contributing to myocardial ischemia and representing a critical determinant of patients' adverse outcome. The molecular mechanisms underlying the morphological and functional changes of CMD are still unknown. Aim of this study was to obtain insights on the molecular pathways associated with microvessel remodeling in HCM. Methods: Interventricular septum myectomies from patients with obstructive HCM (n = 20) and donors' hearts (CTRL, discarded for technical reasons, n = 7) were collected. Remodeled intramyocardial arterioles and cardiomyocytes were microdissected by laser capture and next-generation sequencing was used to delineate the transcriptome profile.

show abstract

A novel approach to select differential pathways associated with hypertrophic cardiomyopathy based on gene co-expression analysis

Cited by 7 publications

References 37 publications

Sparse Graph Regularization Non-Negative Matrix Factorization Based on Huber Loss Model for Cancer Data Analysis

Sparse Graph Regularization Non-Negative Matrix Factorization Based on Huber Loss Model for Cancer Data Analysis

Enhancing Characteristic Gene Selection and Tumor Classification by the Robust Laplacian Supervised Discriminative Sparse PCA

RNA‐seq profiling reveals different pathways between remodeled vessels and myocardium in hypertrophic cardiomyopathy

Contact Info

Product

Resources

About