Abstract:Lung adenocarcinoma is a multifactorial disease. MicroRNA (miRNA) expression profiles are extensively used for discovering potential theranostic biomarkers of lung cancer. This work proposes an optimized support vector regression (SVR) method called SVR-LUAD to simultaneously identify a set of miRNAs referred to the miRNA signature for estimating the survival time of lung adenocarcinoma patients using their miRNA expression profiles. SVR-LUAD uses an inheritable bi-objective combinatorial genetic algorithm to … Show more
“…The feature selection algorithm IBCGA uses an intelligent evolutionary algorithm 82 to solve the large parameter optimization problem. IBCGA has been successfully applied in several bioinformatics problems, including the prediction of human ubiquitination sites 83 , the prediction of the regulatory roles of cyclic AMP receptor proteins 84 and the estimation of survival time for cancer patients 85 , 86 .…”
Breast cancer is a heterogeneous disease and one of the most common cancers among women. Recently, microRNAs (miRNAs) have been used as biomarkers due to their effective role in cancer diagnosis. This study proposes a support vector machine (SVM)-based classifier SVM-BRC to categorize patients with breast cancer into early and advanced stages. SVM-BRC uses an optimal feature selection method, inheritable bi-objective combinatorial genetic algorithm, to identify a miRNA signature which is a small set of informative miRNAs while maximizing prediction accuracy. MiRNA expression profiles of a 386-patient cohort of breast cancer were retrieved from The Cancer Genome Atlas. SVM-BRC identified 34 of 503 miRNAs as a signature and achieved a 10-fold cross-validation mean accuracy, sensitivity, specificity, and Matthews correlation coefficient of 80.38%, 0.79, 0.81, and 0.60, respectively. Functional enrichment of the 10 highest ranked miRNAs was analysed in terms of Kyoto Encyclopedia of Genes and Genomes and Gene Ontology annotations. Kaplan-Meier survival analysis of the highest ranked miRNAs revealed that four miRNAs, hsa-miR-503, hsa-miR-1307, hsa-miR-212 and hsa-miR-592, were significantly associated with the prognosis of patients with breast cancer.
“…The feature selection algorithm IBCGA uses an intelligent evolutionary algorithm 82 to solve the large parameter optimization problem. IBCGA has been successfully applied in several bioinformatics problems, including the prediction of human ubiquitination sites 83 , the prediction of the regulatory roles of cyclic AMP receptor proteins 84 and the estimation of survival time for cancer patients 85 , 86 .…”
Breast cancer is a heterogeneous disease and one of the most common cancers among women. Recently, microRNAs (miRNAs) have been used as biomarkers due to their effective role in cancer diagnosis. This study proposes a support vector machine (SVM)-based classifier SVM-BRC to categorize patients with breast cancer into early and advanced stages. SVM-BRC uses an optimal feature selection method, inheritable bi-objective combinatorial genetic algorithm, to identify a miRNA signature which is a small set of informative miRNAs while maximizing prediction accuracy. MiRNA expression profiles of a 386-patient cohort of breast cancer were retrieved from The Cancer Genome Atlas. SVM-BRC identified 34 of 503 miRNAs as a signature and achieved a 10-fold cross-validation mean accuracy, sensitivity, specificity, and Matthews correlation coefficient of 80.38%, 0.79, 0.81, and 0.60, respectively. Functional enrichment of the 10 highest ranked miRNAs was analysed in terms of Kyoto Encyclopedia of Genes and Genomes and Gene Ontology annotations. Kaplan-Meier survival analysis of the highest ranked miRNAs revealed that four miRNAs, hsa-miR-503, hsa-miR-1307, hsa-miR-212 and hsa-miR-592, were significantly associated with the prognosis of patients with breast cancer.
“…miR3934 is found upregulated in colon cancer and was suggested as a biomarker for lung cancer as its expression correlated with survival rate and prognosis of NSCLC [71,72]. Moreover, it has been reported that miR-3934-5p expression significantly increases in NSCLC cell line A549 [73]. It is also a SNP linked to TGF-β signalling and has been identified as downregulated in rectal carcinoma mucosa, compared with normal mucosa [74].…”
Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) is a member of the betacoronavirus family, which causes COVID-19 disease. SARS-CoV-2 pathogenicity in humans leads to increased mortality rates due to alterations of significant pathways, including some resulting in exacerbated inflammatory responses linked to the “cytokine storm” and extensive lung pathology, as well as being linked to a number of comorbidities. Our current study compared five SARS-CoV-2 sequences from different geographical regions to those from SARS, MERS and two cold viruses, OC43 and 229E, to identify the presence of miR-like sequences. We identified seven key miRs, which highlight considerable differences between the SARS-CoV-2 sequences, compared with the other viruses. The level of conservation between the five SARS-CoV-2 sequences was identical but poor compared with the other sequences, with SARS showing the highest degree of conservation. This decrease in similarity could result in reduced levels of transcriptional control, as well as a change in the physiological effect of the virus and associated host-pathogen responses. MERS and the milder symptom viruses showed greater differences and even significant sequence gaps. This divergence away from the SARS-CoV-2 sequences broadly mirrors the phylogenetic relationships obtained from the whole-genome alignments. Therefore, patterns of mutation, occurring during sequence divergence from the longer established human viruses to the more recent ones, may have led to the emergence of sequence motifs that can be related directly to the pathogenicity of SARS-CoV-2. Importantly, we identified 7 key-microRNAs (miRs 8066, 5197, 3611, 3934-3p, 1307-3p, 3691-3p, 1468-5p) with significant links to KEGG pathways linked to viral pathogenicity and host responses. According to Bioproject data (PRJNA615032), SARS-CoV-2 mediated transcriptomic alterations were similar to the target pathways of the selected 7 miRs identified in our study. This mechanism could have considerable significance in determining the symptom spectrum of future potential pandemics. KEGG pathway analysis revealed a number of critical pathways linked to the seven identified miRs that may provide insight into the interplay between the virus and comorbidities. Based on our reported findings, miRNAs may constitute potential and effective therapeutic approaches in COVID-19 and its pathological consequences.
“…Lung adenocarcinoma (LUAD) is the major type of NSCLC and the morbidity of LUAD has surpassed lung squamous carcinoma in recent years ( 5 ). Due to the deficiency of tumor diagnosis using the traditional bronchoscopy and computed tomography techniques, patients in the early stage of cancer are difficult to be detected ( 6 , 7 ). Therefore, it is imperative to find prognostic biomarkers that instruct the treatment of lung cancer.…”
Background
Recent research has shown that immune-related lncRNA plays a crucial part in the tumor immune microenvironment. This study tried to identify immune-related lncRNAs and construct a robust prediction model to increase the predicted value of lung adenocarcinoma (LUAD).
Methods
RNA expression data of LUAD were download from the Cancer Genome Atlas (TCGA) database. Immune genes were acquired from the Molecular Signatures Database (MSigDB). The immune gene related lncRNAs were acquired by the “limma R” package and Cytoscape3.7.1. Cox regression analysis was applied to construct this forecast model. The prognostic model was validated by the testing cohort which was acquired by the bootstrap method.
Results
A total of 551 lncRNA expression profiles including 497 LUAD tissues and 54 non-LUAD tissues were obtained. A total of 331 immune genes were acquired. The result of the Cox regression analysis showed that seven lncRNAs (AC022784-1, NKILA, AC026355-1, AC068338-3, LINC01843, SYNPR-AS1, and AC123595-1) can be performed to construct the prediction model to forecast the prognosis of LUAD. Kaplan–Meier curves indicated that our prediction model can distribute LUAD patients into two different risk groups (high and low) with significant statistical significance (
P
= 1.484e-07). Cox analysis and independent analysis illustrated that the seven-lncRNAs prediction model was an isolated factor by comparing it with other clinical variables. We validated the accuracy of our model in the testing dataset. Furthermore, the prognostic model also showed higher predictive efficiency than three other published prognostic models. The two different survival groups represented diverse immune features according to principal components analysis. GSEA analysis (gene set enrichment analysis) indicated that seven-lncRNAs signatures may be involved in the progression of tumorigenesis.
Conclusions
We have established a seven immune-related lncRNAs prediction model. This prognostic model had significant clinical significance that increased the predicted value and guided the personalized treatment for LUAD patients.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.