SU-CCE: A Novel Feature Selection Approach for Reducing High Dimensionality

High dimensionality is the serious issue in the preprocessing of data mining. Having large number of features in the dataset leads to several complications for classifying an unknown instance. In a initial dataspace there may be redundant and irrelevant features present, which leads to high memory consumption, and confuse the learning model created with those properties of features. Always it is advisable to select the best features and generate the classification model for better accuracy. In this research, we proposed a novel feature selection approach and Symmetrical uncertainty and Correlation Coefficient (SU-CCE) for reducing the high dimensional feature space and increasing the classification accuracy. The experiment is performed on colon cancer microarray dataset which has 2000 features. The proposed method derived 38 best features from it. To measure the strength of proposed method, top 38 features extracted by 4 traditional filter-based methods are compared with various classifiers. After careful investigation of result, the proposed approach is competing with most of the traditional methods.

A hybrid systems biology and systems pharmacology investigation of Zingerone’s effects on reconstructed human epidermal tissues

Background As individuals live longer, elderly populations can be expected to face issues. This pattern urges researchers to investigate the aging concept further to produce successful anti-aging agents. In the current study, the effects of Zingerone (a natural compound) on epidermal tissues were analyzed using a bioinformatics approach. Methods For this purpose, we chose the GEO dataset GSE133338 to carry out the systems biology and systems pharmacology approaches, ranging from identifying the differentially expressed genes to analyzing the gene ontology, determining similar structures of Zingerone and their features (i.e., anti-oxidant, anti-inflammatory, and skin disorders), constructing the gene–chemicals network, analyzing gene–disease relationships, and validating significant genes through the evidence presented in the literature. Results The post-processing of the microarray dataset identified thirteen essential genes among control and Zingerone-treated samples. The procedure revealed various structurally similar chemical and herbal compounds with possible skin-related effects. Additionally, we studied the relationships of differentially expressed genes with skin-related diseases and validated their direct connections with skin disorders the evidence available in the literature. Also, the analysis of the microarray profiling dataset revealed the critical role of interleukins as a part of the cytokines family on skin aging progress. Conclusions Zingerone, and potentially any constituents of Zingerone (e.g., their similar compound scan functionality), can be used as therapeutic agents in managing skin disorders such as skin aging. However, the beneficial effects of Zingerone should be assessed in other models (i.e., human or animal) in future studies.

Long non-coding RNA-associated competing endogenous RNA axes in the olfactory epithelium in schizophrenia: a bioinformatics analysis

The etiology of schizophrenia (SCZ), as a serious mental illness, is unknown. The significance of genetics in SCZ pathophysiology is yet unknown, and newly identified mechanisms involved in the regulation of gene transcription may be helpful in determining how these changes affect SCZ development and progression. In the current work, we used a bioinformatics approach to describe the role of long non-coding RNA (lncRNA)-associated competing endogenous RNAs (ceRNAs) in the olfactory epithelium (OE) samples in order to better understand the molecular regulatory processes implicated in SCZ disorders in living individuals. The Gene Expression Omnibus database was used to obtain the OE microarray dataset (GSE73129) from SCZ sufferers and control subjects, which contained information about both lncRNAs and mRNAs. The limma package of R software was used to identify the differentially expressed lncRNAs (DElncRNAs) and mRNAs (DEmRNAs). RNA interaction pairs were discovered using the Human MicroRNA Disease Database, DIANA-LncBase, and miRTarBase databases. In this study, the Pearson correlation coefficient was utilized to find positive correlations between DEmRNAs and DElncRNAs in the ceRNA network. Eventually, lncRNA-associated ceRNA axes were developed based on co-expression relations and DElncRNA-miRNA-DEmRNA interactions. This work found six potential DElncRNA-miRNA-DEmRNA loops in SCZ pathogenesis, including, SNTG2-AS1/hsa-miR-7-5p/SLC7A5, FLG-AS1/hsa-miR-34a-5p/FOSL1, LINC00960/hsa-miR-34a-5p/FOSL1, AQP4-AS1/hsa-miR-335-5p/FMN2, SOX2-OT/hsa-miR-24-3p/NOS3, and CASC2/hsa-miR-24-3p/NOS3. According to the findings, ceRNAs in OE might be promising research targets for studying SCZ molecular mechanisms. This could be a great opportunity to examine different aspects of neurodevelopment that may have been hampered early in SCZ patients.

Identification of transcription factors and construction of a novel miRNA regulatory network in primary osteoarthritis by integrated analysis

Backgrounds As osteoarthritis (OA) disease-modifying therapies are not available, novel therapeutic targets need to be discovered and prioritized. Here, we aim to identify miRNA signatures in patients to fully elucidate regulatory mechanism of OA pathogenesis and advance in basic understanding of the genetic etiology of OA. Methods Six participants (3 OA and 3 controls) were recruited and serum samples were assayed through RNA sequencing (RNA-seq). And, RNA-seq dataset was analysed to identify genes, pathways and regulatory networks dysregulated in OA. The overlapped differentially expressed microRNAs (DEMs) were further screened in combination with the microarray dataset GSE143514. The expression levels of candidate miRNAs were further validated by quantitative real-time PCR (qRT-PCR) based on the GEO dataset (GSE114007). Results Serum samples were sequenced interrogating 382 miRNAs. After screening of independent samples and GEO database, the two comparison datasets shared 19 overlapped candidate micRNAs. Of these, 9 up-regulated DEMs and 10 down-regulated DEMs were detected, respectively. There were 236 target genes for up-regulated DEMs and 400 target genes for those down-regulated DEMs. For up-regulated DEMs, the top 10 hub genes were KRAS, NRAS, CDC42, GDNF, SOS1, PIK3R3, GSK3B, IRS2, GNG12, and PRKCA; for down-regulated DEMs, the top 10 hub genes were NR3C1, PPARGC1A, SUMO1, MEF2C, FOXO3, PPP1CB, MAP2K1, RARA, RHOC, CDC23, and CREB3L2. Mir-584-5p-KRAS, mir-183-5p-NRAS, mir-4435-PIK3R3, and mir-4435-SOS1 were identified as four potential regulatory pathways by integrated analysis. Conclusions We have integrated differential expression data to reveal putative genes and detected four potential miRNA-target gene pathways through bioinformatics analysis that represent new mediators of abnormal gene expression and promising therapeutic targets in OA.

Identification of crucial genes involved in pathogenesis of regional weakening of the aortic wall

Background The diameter of the abdominal aortic aneurysm (AAA) is the most commonly used parameter for the prediction of occurrence of AAA rupture. However, the most vulnerable region of the aortic wall may be different from the most dilated region of AAA under pressure. The present study is the first to use weighted gene coexpression network analysis (WGCNA) to detect the coexpressed genes that result in regional weakening of the aortic wall. Methods The GSE165470 raw microarray dataset was used in the present study. Differentially expressed genes (DEGs) were filtered using the “limma” R package. DEGs were assessed by Gene Ontology biological process (GO-BP) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses. WGCNA was used to construct the coexpression networks in the samples with regional weakening of the AAA wall and in the control group to detect the gene modules. The hub genes were defined in the significant functional modules, and a hub differentially expressed gene (hDEG) coexpression network was constructed with the highest confidence based on protein–protein interactions (PPIs). Molecular compound detection (MCODE) was used to identify crucial genes in the hDEG coexpression network. Crucial genes in the hDEG coexpression network were validated using the GSE7084 and GSE57691 microarray gene expression datasets. Result A total of 350 DEGs were identified, including 62 upregulated and 288 downregulated DEGs. The pathways were involved in immune responses, vascular smooth muscle contraction and cell–matrix adhesion of DEGs in the samples with regional weakening in AAA. Antiquewhite3 was the most significant module and was used to identify downregulated hDEGs based on the result of the most significant modules negatively related to the trait of weakened aneurysm walls. Seven crucial genes were identified and validated: ACTG2, CALD1, LMOD1, MYH11, MYL9, MYLK, and TPM2. These crucial genes were associated with the mechanisms of AAA progression. Conclusion We identified crucial genes that may play a significant role in weakening of the AAA wall and may be potential targets for medical therapies and diagnostic biomarkers. Further studies are required to more comprehensively elucidate the functions of crucial genes in the pathogenesis of regional weakening in AAA.

Genetic Algorithm for Variable Selection and Parameter Optimization in SVM and Fuzzy SVM for Colon Cancer Microarray Classification

Colon cancer is the second leading cause of cancer-related deaths in the world, hence research on that topic needs to be undertaken with improvement. Recent advanced in microarray technology allows the monitoring of the expression level of a large set of genes simultaneously. Microarray data is a type of high-dimensional data with hundreds or even thousands number of genes (features), while usually the number of patients observed (observations) is much smaller than the number of features. This study uses a colon cancer microarray dataset contains two class of genes, normal and tumor. The aims of this study is to develop a classification model using fuzzy support vector machines (FSVM) hybridized with genetic algorithm (GA) for classifying individuals based on gene expression. Fuzzy memberships was used in SVM in order to deal with the case of imbalanced microarray data. Meanwhile, the role of genetic algorithm is, firstly, to select the relevant genes as the features and, secondly, to optimize the parameter of FSVM as GA is able to handle the problem of nonlinear optimization that has a high dimension, adaptable, and easily combined with other methods. The classification using FCBF selection has a higher accuracy value than the ones without the selection. The results also show that FSVM that has been optimized using GA has the highest accuracy value compared to other classification methods used in this study.

Identification of the antibacterial mechanism of cryptotanshinone on methicillin-resistant Staphylococcus aureus using bioinformatics analysis

Cryptotanshinone (CT) is an extract from the traditional Chinese medicine Salvia miltiorrhiza, which inhibits the growth of methicillin-resistant Staphylococcus aureus (MRSA) in vitro. This study aims to determine the antibacterial mechanisms of CT by integrating bioinformatics analysis and microbiology assay. The microarray data of GSE13203 was retrieved from the Gene Expression Omnibus (GEO) database to screen the differentially expressed genes (DEGs) of S. aureus strains that were treated with CT treatment. Gene ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were used to identify the potential target of CT. Data mining on the microarray dataset indicated that pyruvate kinase (PK) might be involved in the antimicrobial activities of CT. The minimum inhibition concentrations (MICs) of CT or vancomycin against the MRSA strain ATCC43300 and seven other clinical strains were determined using the broth dilution method. The effects of CT on the activity of PK were further measured. In vitro tests verified that CT inhibited the growth of an MRSA reference strain and seven other clinical strains. CT hampered the activity of the PK of ATCC43300 and five clinical MRSA strains. CT might hinder bacterial energy metabolism by inhibiting the activity of PK.

Bioinformatics analysis of differentially expressed genes and their potentially interacting miRNAs in oral lichen planus

Background Oral lichen planus (OLP) was a common oral mucosal disease. However, the etiology and pathogenesis of OLP were still limited. This research was designed to identify the differentially expressed genes and relative miRNAs in OLP. Methods and Results The OLP microarray dataset (GSE52130) was download from the Gene Expression Omnibus (GEO) database. R software was used to identify differentially expressed genes between the OLP samples and normal oral mucosa. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway conducted. Protein–protein interaction (PPI) network analysis was performed in the STRING database. CytoHubba in the Cytoscape software was applied to determining the top 10 hub genes, whose relative miRNA was identified through RNA Interactome Database. Overall, 627 DEGs was identified in OLP samples, including 351 highly expressed genes and 276 lowly expressed genes. GO analysis indicated that the epidermal differentiation was mostly enriched. For the KEGG pathway, the DEGs in OLP samples were mostly involved in Staphylococcus aureus infection. Top 10 hub genes were identified from the PPI network. The miRNA (hsa-miR-98-5p) was regarded as the mostly possible miRNA involved in OLP. Conclusions The epidermal differentiation complex and functional miRNAs (hsa-miR-98-5p, hsa-let-7e-5p, hsa-let-7f-5p) were potential biomarkers of OLP

Survivin’ Acute Myeloid Leukaemia—A Personalised Target for inv(16) Patients

Despite recent advances in therapies including immunotherapy, patients with acute myeloid leukaemia (AML) still experience relatively poor survival rates. The Inhibition of Apoptosis (IAP) family member, survivin, also known by its gene and protein name, Baculoviral IAP Repeat Containing 5 (BIRC5), remains one of the most frequently expressed antigens across AML subtypes. To better understand its potential to act as a target for immunotherapy and a biomarker for AML survival, we examined the protein and pathways that BIRC5 interacts with using the Kyoto Encyclopedia of Genes and Genomes (KEGG), search tool for recurring instances of neighbouring genes (STRING), WEB-based Gene Set Analysis Toolkit, Bloodspot and performed a comprehensive literature review. We then analysed data from gene expression studies. These included 312 AML samples in the Microarray Innovations In Leukemia (MILE) dataset. We found a trend between above median levels of BIRC5 being associated with improved overall survival (OS) but this did not reach statistical significance (p = 0.077, Log-Rank). There was some evidence of a beneficial effect in adjusted analyses where above median levels of BIRC5 were shown to be associated with improved OS (p = 0.001) including in Core Binding Factor (CBF) patients (p = 0.03). Above median levels of BIRC5 transcript were associated with improved relapse free survival (p < 0.0001). Utilisation of a second large cDNA microarray dataset including 306 AML cases, again showed no correlation between BIRC5 levels and OS, but high expression levels of BIRC5 correlated with worse survival in inv(16) patients (p = 0.077) which was highly significant when datasets A and B were combined (p = 0.001). In addition, decreased BIRC5 expression was associated with better clinical outcome (p = 0.004) in AML patients exhibiting CBF mainly due to patients with inv(16) (p = 0.007). This study has shown that BIRC5 expression plays a role in the survival of AML patients, this association is not apparent when we examine CBF patients as a cohort, but when those with inv(16) independently indicating that those patients with inv(16) would provide interesting candidates for immunotherapies that target BIRC5.