Integrative Deep Learning for Identifying Differentially Expressed (DE) Biomarkers

Lim, Jayeon; Bang, SoYoun; Kim, Jiyeon; Park, Cheolyong; Cho, JunSang; Kim, Sunghwan

doi:10.1155/2019/8418760

Cited by 10 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional statistical approaches are not suitable for detecting gene interactions, especially when interactions appear between more than two genes, or when the data are high-dimensional, meaning the data have many attributes or independent variables ( McKinney et al, 2006 ; Lai et al, 2019 ). Machine learning approaches have been widely used to identify disease biomarkers ( Lim et al, 2019 ; Moni et al, 2019 ; Tabl et al, 2019 ; Sanchez and Mackenzie, 2020 ). Recently, Sanchez et al identified methylation biomarkers for leukemia by investigating PPI for differentially methylated genes (DMGs) and differentially expressed genes (DEGs) using machine learning approach ( Sanchez and Mackenzie, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

A Network-Based Methodology to Identify Subnetwork Markers for Diagnosis and Prognosis of Colorectal Cancer

et al. 2021

View full text Add to dashboard Cite

The development of reliable methods for identification of robust biomarkers for complex diseases is critical for disease diagnosis and prognosis efforts. Integrating multi-omics data with protein-protein interaction (PPI) networks to investigate diseases may help better understand disease characteristics at the molecular level. In this study, we developed and tested a novel network-based method to detect subnetwork markers for patients with colorectal cancer (CRC). We performed an integrated omics analysis using whole-genome gene expression profiling and copy number alterations (CNAs) datasets followed by building a gene interaction network for the significantly altered genes. We then clustered the constructed gene network into subnetworks and assigned a score for each significant subnetwork. We developed a support vector machine (SVM) classifier using these scores as feature values and tested the methodology in independent CRC transcriptomic datasets. The network analysis resulted in 15 subnetwork markers that revealed several hub genes that may play a significant role in colorectal cancer, including PTP4A3, FGFR2, PTX3, AURKA, FEN1, INHBA, and YES1. The 15-subnetwork classifier displayed over 98 percent accuracy in detecting patients with CRC. In comparison to individual gene biomarkers, subnetwork markers based on integrated multi-omics and network analyses may lead to better disease classification, diagnosis, and prognosis.

show abstract

Section: Introductionmentioning

confidence: 99%

A Network-Based Methodology to Identify Subnetwork Markers for Diagnosis and Prognosis of Colorectal Cancer

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The authors used the deep learning-based feature representation of tumor-infiltrating lymphocytes in the cancer of the breast based on histopathological imaging for improving the detection process. Several other studies used the DNN model for detecting the subtypes of cancer by combining several types of transcriptomics data on breast cancer using deep learning techniques [62] and Identifying Differentially Expressed (DE) Biomarkers [63].…”

Section: Rq1: What Are the Common Deep Learning Methods For Breast Ca...mentioning

confidence: 99%

Deep Learning Based Methods for Breast Cancer Diagnosis: A Systematic Review and Future Direction

Nasser

Yusof

2023

Diagnostics

View full text Add to dashboard Cite

Breast cancer is one of the precarious conditions that affect women, and a substantive cure has not yet been discovered for it. With the advent of Artificial intelligence (AI), recently, deep learning techniques have been used effectively in breast cancer detection, facilitating early diagnosis and therefore increasing the chances of patients’ survival. Compared to classical machine learning techniques, deep learning requires less human intervention for similar feature extraction. This study presents a systematic literature review on the deep learning-based methods for breast cancer detection that can guide practitioners and researchers in understanding the challenges and new trends in the field. Particularly, different deep learning-based methods for breast cancer detection are investigated, focusing on the genomics and histopathological imaging data. The study specifically adopts the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), which offer a detailed analysis and synthesis of the published articles. Several studies were searched and gathered, and after the eligibility screening and quality evaluation, 98 articles were identified. The results of the review indicated that the Convolutional Neural Network (CNN) is the most accurate and extensively used model for breast cancer detection, and the accuracy metrics are the most popular method used for performance evaluation. Moreover, datasets utilized for breast cancer detection and the evaluation metrics are also studied. Finally, the challenges and future research direction in breast cancer detection based on deep learning models are also investigated to help researchers and practitioners acquire in-depth knowledge of and insight into the area.

show abstract

“…Recent advances in bioinformatics technologies have allowed significant improvements in the discovery of pathogenic genes of cardiovascular diseases. A large amount of gene data has been accumulated, and sophisticated methods for analyzing data have become crucial to explain the causes of disease (15). In this study, we screened differentially expressed genes (DEGs) in response to the regulation of KDM5A.…”

Section: Introductionmentioning

confidence: 99%

Transcriptomic and ChIP-seq Integrative Analysis Identifies KDM5A-Target Genes in Cardiac Fibroblasts

Jiang

Zhang

Wei

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Cardiac fibrosis is a common pathological feature in cardiac remodeling. This study aimed to explore the role of KDM5A in cardiac fibrosis via bioinformatics analysis. Cardiac fibroblasts (CFs) were harvested and cultured from 10 dilated cardiomyopathy (DCM) patients who underwent heart transplantation. Western blotting was applied to verify that KDM5A is regulated by angiotensin II (Ang II) via the PI3k/AKT signaling pathway. The differentially expressed genes (DEGs) were analyzed by transcriptomics. ChIP-seq and ChIP-qPCR were used to identify the genes bound by KDM5A. In integrative analysis, weighted gene coexpression network analysis (WGCNA) was performed to identify highly relevant gene modules. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were performed for the key genes in modules. The STRING database, Cytoscape, and MCODE were applied to construct the protein–protein interaction (PPI) network and screen hub genes. To verify the expression of DEGs regulated by KDM5A, Western blotting and immunofluorescence were performed in myocardial tissue samples. Immunofluorescence verified the vimentin positivity of CFs. Ang II upregulated the expression of KDM5A in CFs via the PI3K/AKT signaling pathway. GO analysis of DEGs indicated that regulation of vasoconstriction, extracellular region, and calcium ion binding were enriched when KDM5A interfered with CPI or Ang II. KEGG analysis of the DEGs revealed the involvement of ECM-receptor interaction, focal adhesion, PI3K-Akt signaling pathway, cell adhesion, and arrhythmogenic right ventricular cardiomyopathy pathways. Three hub genes (IGF1, MYH11, and TGFB3) were identified via four different algorithms. Subsequent verification in patient samples demonstrated that the hub genes, which were regulated by KDM5A, were downregulated in DCM samples. KDM5A is a key regulator in the progression of cardiac fibrosis. In this successful integrative analysis, IGF1, MYH11, and TGFB3 were determined to be coordinately expressed to participate in cardiac fibrosis.

show abstract

Integrative Deep Learning for Identifying Differentially Expressed (DE) Biomarkers

Cited by 10 publications

References 26 publications

A Network-Based Methodology to Identify Subnetwork Markers for Diagnosis and Prognosis of Colorectal Cancer

A Network-Based Methodology to Identify Subnetwork Markers for Diagnosis and Prognosis of Colorectal Cancer

Deep Learning Based Methods for Breast Cancer Diagnosis: A Systematic Review and Future Direction

Transcriptomic and ChIP-seq Integrative Analysis Identifies KDM5A-Target Genes in Cardiac Fibroblasts

Contact Info

Product

Resources

About