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

Al‐Harazi, Olfat; Kaya, Ibrahim; Allali, Achraf El; Çolak, Dilek

doi:10.3389/fgene.2021.721949

Cited by 16 publications

(9 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been tested in the studies of various diseases, including cancer, schizophrenia, and postpartum hemorrhage 16 – 20 . Regarding UC, the characteristics of high stability and prediction accuracy of the SVM method have also been proven in previous reports 21 , 22 . Another method of ML, the Least Absolute Shrinkage and Selection Operator (LASSO) analysis, is commonly used in the biomarker identification of various carcinoma diseases 23 – 25 .…”

Section: Introductionsupporting

confidence: 54%

Identification of useful genes from multiple microarrays for ulcerative colitis diagnosis based on machine learning methods

Zhang

Mao

Lau

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Ulcerative colitis (UC) is a chronic relapsing inflammatory bowel disease with an increasing incidence and prevalence worldwide. The diagnosis for UC mainly relies on clinical symptoms and laboratory examinations. As some previous studies have revealed that there is an association between gene expression signature and disease severity, we thereby aim to assess whether genes can help to diagnose UC and predict its correlation with immune regulation. A total of ten eligible microarrays (including 387 UC patients and 139 healthy subjects) were included in this study, specifically with six microarrays (GSE48634, GSE6731, GSE114527, GSE13367, GSE36807, and GSE3629) in the training group and four microarrays (GSE53306, GSE87473, GSE74265, and GSE96665) in the testing group. After the data processing, we found 87 differently expressed genes. Furthermore, a total of six machine learning methods, including support vector machine, least absolute shrinkage and selection operator, random forest, gradient boosting machine, principal component analysis, and neural network were adopted to identify potentially useful genes. The synthetic minority oversampling (SMOTE) was used to adjust the imbalanced sample size for two groups (if any). Consequently, six genes were selected for model establishment. According to the receiver operating characteristic, two genes of OLFM4 and C4BPB were finally identified. The average values of area under curve for these two genes are higher than 0.8, either in the original datasets or SMOTE-adjusted datasets. Besides, these two genes also significantly correlated to six immune cells, namely Macrophages M1, Macrophages M2, Mast cells activated, Mast cells resting, Monocytes, and NK cells activated (P < 0.05). OLFM4 and C4BPB may be conducive to identifying patients with UC. Further verification studies could be conducted.

show abstract

Section: Introductionsupporting

confidence: 54%

Identification of useful genes from multiple microarrays for ulcerative colitis diagnosis based on machine learning methods

Zhang

Mao

Lau

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Indeed, the previous studies, including our own, reported that the multiomics approach may increase the robustness and reliability of biomarkers associated with complex diseases, including cancer (Miao et al, 2014;Aldosary et al, 2020;Das et al, 2020;Al-Harazi et al, 2021a;Baloni et al, 2021;Kaya et al, 2022;Ruan et al, 2022). Additionally, it has been reported that networkbased approaches have high efficacy in identifying biomarkers for many complex diseases, including several different types of cancer (Wang et al, 2017;Chen et al, 2019;Liu et al, 2019;Uddin et al, 2019;Khan et al, 2020;Al-Harazi et al, 2021b). However, most biomarkers identified thus far require invasive procedures.…”

Section: Introductionmentioning

confidence: 94%

“…First, we used the GSE23878 dataset for building the classification model, and then tested the classification performance on an indepedent dataset (TCGA dataset) to confirm if the 17-gene-classifier can distinguish patients from normal controls. We evaluated the performance of the classifier for its accuracy, specificity, sensitivity, and area under curve (AUC), as described previously (Al-Harazi et al, 2021a;Al-Harazi et al, 2021b). The analyses were performed using PARTEK Genomics Suite (Partek Inc., St. Lois, MO, United States).…”

Section: Colorectal Cancer Classifier Model and Performance Evaluationmentioning

confidence: 99%

Transcriptomic data analysis coupled with copy number aberrations reveals a blood-based 17-gene signature for diagnosis and prognosis of patients with colorectal cancer

2023

Self Cite

View full text Add to dashboard Cite

Background: Colorectal cancer (CRC) is the third most common cancer and third leading cause of cancer-associated deaths worldwide. Diagnosing CRC patients reliably at an early and curable stage is of utmost importance to reduce the risk of mortality.Methods: We identified global differentially expressed genes with copy number alterations in patients with CRC. We then identified genes that are also expressed in blood, which resulted in a blood-based gene signature. We validated the gene signature’s diagnostic and prognostic potential using independent datasets of gene expression profiling from over 800 CRC patients with detailed clinical data. Functional enrichment, gene interaction networks and pathway analyses were also performed.Results: The analysis revealed a 17-gene signature that is expressed in blood and demonstrated that it has diagnostic potential. The 17-gene SVM classifier displayed 99 percent accuracy in predicting the patients with CRC. Moreover, we developed a prognostic model and defined a risk-score using 17-gene and validated that high risk score is strongly associated with poor disease outcome. The 17-gene signature predicted disease outcome independent of other clinical factors in the multivariate analysis (HR = 2.7, 95% CI = 1.3–5.3, p = 0.005). In addition, our gene network and pathway analyses revealed alterations in oxidative stress, STAT3, ERK/MAPK, interleukin and cytokine signaling pathways as well as potentially important hub genes, including BCL2, MS4A1, SLC7A11, AURKA, IL6R, TP53, NUPR1, DICER1, DUSP5, SMAD3, and CCND1.Conclusion: Our results revealed alterations in various genes and cancer-related pathways that may be essential for CRC transformation. Moreover, our study highlights diagnostic and prognostic value of our gene signature as well as its potential use as a blood biomarker as a non-invasive diagnostic method. Integrated analysis transcriptomic data coupled with copy number aberrations may provide a reliable method to identify key biological programs associated with CRC and lead to improved diagnosis and therapeutic options.

show abstract

“…Thus, protein interactions and their networks are very important in most biological functions and processes [ 5 ]. Protein interaction networks can help us better understand the disease process, which is of great significance in the identification of disease proteins/gene [ 6 , 7 ]. Roudi et al identified differentially expressed genes (DEGs) at each stage of lung adenocarcinoma in four datasets from the Gene Expression Omnibus (GEO) database.…”

Section: Introductionmentioning

confidence: 99%

Integrating Expression Data-Based Deep Neural Network Models with Biological Networks to Identify Regulatory Modules for Lung Adenocarcinoma

Luo

Liu

et al. 2022

Biology

View full text Add to dashboard Cite

Lung adenocarcinoma is the most common type of primary lung cancer, but the regulatory mechanisms during carcinogenesis remain unclear. The identification of regulatory modules for lung adenocarcinoma has become one of the hotspots of bioinformatics. In this paper, multiple deep neural network (DNN) models were constructed using the expression data to identify regulatory modules for lung adenocarcinoma in biological networks. First, the mRNAs, lncRNAs and miRNAs with significant differences in the expression levels between tumor and non-tumor tissues were obtained. MRNA DNN models were established and optimized to mine candidate mRNAs that significantly contributed to the DNN models and were in the center of an interaction network. Another DNN model was then constructed and potential ceRNAs were screened out based on the contribution of each RNA to the model. Finally, three modules comprised of miRNAs and their regulated mRNAs and lncRNAs with the same regulation direction were identified as regulatory modules that regulated the initiation of lung adenocarcinoma through ceRNAs relationships. They were validated by literature and functional enrichment analysis. The effectiveness of these regulatory modules was evaluated in an independent lung adenocarcinoma dataset. Regulatory modules for lung adenocarcinoma identified in this study provided a reference for regulatory mechanisms during carcinogenesis.

show abstract

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

Cited by 16 publications

References 84 publications

Identification of useful genes from multiple microarrays for ulcerative colitis diagnosis based on machine learning methods

Identification of useful genes from multiple microarrays for ulcerative colitis diagnosis based on machine learning methods

Transcriptomic data analysis coupled with copy number aberrations reveals a blood-based 17-gene signature for diagnosis and prognosis of patients with colorectal cancer

Integrating Expression Data-Based Deep Neural Network Models with Biological Networks to Identify Regulatory Modules for Lung Adenocarcinoma

Contact Info

Product

Resources

About