Cancer Microarray Datasets Research Articles

IMOABC: An efficient multi-objective filter–wrapper hybrid approach for high-dimensional feature selection

With the development of data science, the challenge of high-dimensional data has become increasingly prevalent. High-dimensional data contains a significant amount of redundant information, which can adversely affect the performance and effectiveness of machine learning algorithms. Therefore, it is necessary to select the most relevant features from the raw data and perform feature selection on high-dimensional data. In this paper, a novel filter–wrapper feature selection method based on an improved multi-objective artificial bee colony algorithm (IMOABC) is proposed to address the feature selection problem in high-dimensional data. This method simultaneously considers three objectives: feature error rate, feature subset ratio, and distance, effectively improving the efficiency of obtaining the optimal feature subset on high-dimensional data. Additionally, a novel Fisher Score-based initialization strategy is introduced, significantly enhancing the quality of solutions. Furthermore, a new dynamic adaptive strategy is designed, effectively improving the algorithm’s convergence speed and enhancing its global search capability. Comparative experimental results on microarray cancer datasets demonstrate that the proposed method significantly improves classification accuracy and effectively reduces the size of the feature subset when compared to various traditional and state-of-the-art multi-objective feature selection algorithms. IMOABC improves the classification accuracy by 2.27% on average compared to various multi-objective feature selection methods, while reducing the number of selected features by 88.76% on average. Meanwhile, IMOABC shows an average improvement of 4.24% in classification accuracy across all datasets, with an average reduction of 76.73% in the number of selected features compared to various traditional methods.

Considerations Regarding CHSY1 Knockdown and Its Influence on Gene Expression Profiles: A Perspective from Protein Interaction Network Analysis

Introduction: Knockdown of CHSY1 in ovarian cancer holds promise for monitoring tumorigenesis and the application of targeted therapies. Method: A comparison was made between microarray datasets of ovarian cancer with and without CHSY1 knockdown to identify differentially expressed genes (DEGs). Subsequently, the DEGs were analyzed using Cytoscape and its plug-ins. All key genes in the protein-protein interaction (PPI) network originated from the expression dataset which exhibiting significant differential expressions. Result: Particularly PTEN, STAT3, BRCA, CCND1, and HIST1H4I emerged as central hub-bottlenecks within the PPI network following CHSY1 knockdown. Conclusion: This compilation suggests that the candidate genes and their associated biological processes may have substantial connections to the effects of knockdown, inhibiting some cancer-related genes to prevent cancer progression.

A gene selection algorithm for microarray cancer classification using an improved particle swarm optimization

Gene selection is an essential step for the classification of microarray cancer data. Gene expression cancer data (deoxyribonucleic acid microarray] facilitates in computing the robust and concurrent expression of various genes. Particle swarm optimization (PSO) requires simple operators and less number of parameters for tuning the model in gene selection. The selection of a prognostic gene with small redundancy is a great challenge for the researcher as there are a few complications in PSO based selection method. In this research, a new variant of PSO (Self-inertia weight adaptive PSO) has been proposed. In the proposed algorithm, SIW-APSO-ELM is explored to achieve gene selection prediction accuracies. This novel algorithm establishes a balance between the exploitation and exploration capabilities of the improved inertia weight adaptive particle swarm optimization. The self-inertia weight adaptive particle swarm optimization (SIW-APSO) algorithm is employed for solution explorations. Each particle in the SIW-APSO increases its position and velocity iteratively through an evolutionary process. The extreme learning machine (ELM) has been designed for the selection procedure. The proposed method has been employed to identify several genes in the cancer dataset. The classification algorithm contains ELM, K-centroid nearest neighbor, and support vector machine to attain high forecast accuracy as compared to the start-of-the-art methods on microarray cancer datasets that show the effectiveness of the proposed method.

Hybrid whale algorithm with evolutionary strategies and filtering for high-dimensional optimization: Application to microarray cancer data.

The standard whale algorithm is prone to suboptimal results and inefficiencies in high-dimensional search spaces. Therefore, examining the whale optimization algorithm components is critical. The computer-generated initial populations often exhibit an uneven distribution in the solution space, leading to low diversity. We propose a fusion of this algorithm with a discrete recombinant evolutionary strategy to enhance initialization diversity. We conduct simulation experiments and compare the proposed algorithm with the original WOA on thirteen benchmark test functions. Simulation experiments on unimodal or multimodal benchmarks verified the better performance of the proposed RESHWOA, such as accuracy, minimum mean, and low standard deviation rate. Furthermore, we performed two data reduction techniques, Bhattacharya distance and signal-to-noise ratio. Support Vector Machine (SVM) excels in dealing with high-dimensional datasets and numerical features. When users optimize the parameters, they can significantly improve the SVM's performance, even though it already works well with its default settings. We applied RESHWOA and WOA methods on six microarray cancer datasets to optimize the SVM parameters. The exhaustive examination and detailed results demonstrate that the new structure has addressed WOA's main shortcomings. We conclude that the proposed RESHWOA performed significantly better than the WOA.

CFS‐MOES Ensemble Model on Metaheuristic Search‐Based Feature Selection

Cancer is one of the leading causes of death across the globe. There is a need for early diagnosis to improve the chance of successful treatment and reduce the mortality associated with cancer. Due to the availability of highly specialized cancer datasets, molecular classification of cancer by gene expression, machine learning, and deep learning, a part of artificial intelligence (AI) techniques is used in detecting the disease. The application of several classification and feature selection methods on microarray gene expression datasets helps learn models that are able to predict a given disease. However, the tremendous dimensionality of the microarray cancer dataset is the greatest challenge in interpreting the data. In this work, the optimal feature subsets are selected by combining the correlation‐based feature selection (CFS) technique with five distinct meta‐heuristic search methods: evolutionary search (ES), particle swarm optimization search (PSOS), genetic search (GS), harmony search (HS), and multiobject evolutionary search (MOES). Furthermore, a CFS‐MOES (correlation‐based feature selection—multiobject evolutionary search) ensemble model is proposed based on a majority voting mechanism to improve the classification performance. Six microarray cancer datasets are considered, and seven traditional classifiers are evaluated on those datasets. Three classifiers, namely, K‐nearest neighbour (KNN), multilayer perceptron (MLP), and random forest (RF), were chosen as the base classifiers based on their F‐measure score. The features chosen by our proposed CFS‐MOES method significantly improve the accuracy of the proposed model. Moreover, the proposed model has also been compared with the other ensemble models generated using CFS‐ES (correlation‐based feature selection —evolutionary search), CFS‐PSOS (correlation‐based feature selection—particle swarm optimization search), CFS‐GS (correlation‐based feature selection—genetic search), and CFS‐HS (correlation‐based feature selection—harmony search) feature selection methods, ensuring better classification accuracy with a reduced feature subset. This model is also evaluated using significant parameters such as precision, recall, F‐measure, accuracy, Matthews correlation coefficient (MCC), and mean absolute error (MAE). According to the experimental results, our proposed model has a remarkable accuracy of 98.83% for breast cancer and 98.79% for cervical cancer.

Targeting PEG10 as a novel therapeutic approach to overcome CDK4/6 inhibitor resistance in breast cancer

BackgroundBreast cancer is the global leading cancer burden in women and the hormone receptor-positive (HR+) subtype is a major part of breast cancer. Though cyclin-dependent kinase 4 and 6 (CDK4/6) inhibitors are highly effective therapy for HR+ subtype, acquired resistance is inevitable in most cases. Herein, we investigated the paternally expressed gene 10 (PEG10)-associated mechanism of acquired resistance to CDK4/6 inhibitors.MethodsPalbociclib-resistant cells were generated by exposing human HR+ breast cancer cell lines to palbociclib for 7–9 months. In vitro mechanistic study and in vivo xenograft assay were performed. For clinical relevance, public mRNA microarray data sets of early breast cancer were analyzed and PEG10 immunohistochemical staining was performed using pre-CDK4/6 inhibitor tumor samples.ResultsWe observed that PEG10 was significantly upregulated in palbociclib-resistant cells. Ectopic overexpression of PEG10 in parental cells caused CDK4/6 inhibitor resistance and enhanced epithelial–mesenchymal transition (EMT). On the contrary, PEG10-targeting siRNA or antisense oligonucleotides (ASOs) combined with palbociclib synergistically inhibited proliferation of palbociclib-resistant cells and growth of palbociclib-resistant xenograft in mice and suppressed EMT as well. The mechanistic study confirmed that high PEG10 expression suppressed p21, a natural CDK inhibitor, and SIAH1, a post-translational degrader of ZEB1, augmenting CDK4/6 inhibitor resistance. Then PEG10 siRNA combined with palbociclib suppressed cell cycle progression and EMT via activating p21 and SIAH1, respectively. Consequently, combined PEG10 inhibition and palbociclib overcame CDK4/6 inhibitor resistance. Furthermore, high PEG10 expression was significantly associated with a shorter recurrence-free survival (RFS) based on public mRNA expression data. In pre-CDK4/6 inhibitor treatment tissues, PEG10 positivity by IHC also showed a trend toward a shorter progression-free survival (PFS) with CDK4/6 inhibitor. These results support clinical relevance of PEG10 as a therapeutic target.ConclusionsWe demonstrated a novel PEG10-associated mechanism of CDK4/6 inhibitor resistance. We propose PEG10 as a promising therapeutic target for overcoming PEG10-associated resistance to CDK4/6 inhibitors.

The use of gene expression datasets in feature selection research: 20 years of inherent bias?

AbstractFeature selection algorithms are frequently employed in preprocessing machine learning pipelines applied to biological data to identify relevant features. The use of feature selection in gene expression studies began at the end of the 1990s with the analysis of human cancer microarray datasets. Since then, gene expression technology has been perfected, the Human Genome Project has been completed, new microarray platforms have been created and discontinued, and RNA‐seq has gradually replaced microarrays. However, most feature selection methods in the last two decades were designed, evaluated, and validated on the same datasets from the microarray technology's infancy. In this review of over 1200 publications regarding feature selection and gene expression, published between 2010 and 2020, we found that 57% of the publications used at least one outdated dataset, 23% used only outdated data, and 32% did not cite data sources. Other issues include referencing databases that are no longer available, the slow adoption of RNA‐seq datasets, and bias toward human cancer data, even for methods designed for a broader scope. In the most popular datasets, some being 23 years old, mislabeled samples, experimental biases, distribution shifts, and the absence of classification challenges are common. These problems are more predominant in publications with computer science backgrounds compared to publications from biology and can lead to inaccurate and misleading biological results.This article is categorized under: Algorithmic Development > Biological Data Mining Technologies > Machine Learning

Biological and clinical significance of the glypican-3 gene in human lung adenocarcinoma: An in silico analysis.

Glypican-3 (GPC3), a membrane-bound heparan sulfate proteoglycan, has long been found to be dysregulated in human lung adenocarcinomas (LUADs). Nevertheless, the function, mutational profile, epigenetic regulation, co-expression profile, and clinicopathological significance of the GPC3 gene in LUAD progression are not well understood. In this study, we analyzed cancer microarray datasets from publicly available databases using bioinformatics tools to elucidate the above parameters. We observed significant downregulation of GPC3 in LUAD tissues compared to their normal counterparts, and this downregulation was associated with shorter overall survival (OS) and relapse-free survival (RFS). Nevertheless, no significant differences in the methylation pattern of GPC3 were observed between LUAD and normal tissues, although lower promoter methylation was observed in male patients. GPC3 expression was also found to correlate significantly with infiltration of B cells, CD8+, CD4+, macrophages, neutrophils, and dendritic cells in LUAD. In addition, a total of 11 missense mutations were identified in LUAD patients, and ~1.4% to 2.2% of LUAD patients had copy number amplifications in GPC3. Seventeen genes, mainly involved in dopamine receptor-mediated signaling pathways, were frequently co-expressed with GPC3. We also found 11 TFs and 7 miRNAs interacting with GPC3 and contributing to disease progression. Finally, we identified 3 potential inhibitors of GPC3 in human LUAD, namely heparitin, gemcitabine and arbutin. In conclusion, GPC3 may play an important role in the development of LUAD and could serve as a promising biomarker in LUAD.

PMP-SVM: A Hybrid Approach for effective Cancer Diagnosis using Feature Selection and Optimization

Cancer disease is becoming a prominent factor in increasing the death ration over the world due to the late diagnosis. Machine Learning (ML) is playing a vital role in providing computer aided diagnosis models for early diagnosis of cancer. For the diagnosis process the microarray data has its own place. Microarray data contain the genetic information of a patient with a large number of dimensions such as genes with a small sample such as patient details. If the microarray is directly taken without reducing the dimension as the input to any ML model for classification, then Small Sample Size is the resulting issue. So, size of the microarray data needs to be reduces by using either of dimensionality reduction technique or the feature selection technique to increase the model’s performance. In this work, proposed a hybrid model using Principal Component Analysis (PCA), Maximum Relevance Minimum Redundancy (MRMR), Particle Swarm Optimization (PSO) and Support Vector Machine (SVM) for cancer diagnosis. PCA and MRMR is used for feature selection and PSO is applied to get the optimized feature set. Finally, SVM is applied as the classification model. The proposed model is evaluated against multiple cancer microarray datasets to measure the performance in terms of accuracy, precision, recall, and F1 score. Result shows that proposed model performs better than existing state of art model.

Development and validation of an individualized gene expression-based signature to predict overall survival of patients with high-grade serous ovarian carcinoma

BackgroundHigh-grade serious ovarian carcinoma (HGSOC) is a subtype of ovarian cancer with a different prognosis attributable to genetic heterogeneity. The prognosis of patients with advanced HGSOC requires prediction by genetic markers. This study systematically analyzed gene expression profile data to establish a genetic marker for predicting HGSOC prognosis.MethodsThe RNA-seq data set and information on clinical follow-up of HGSOC were retrieved from Gene Expression Omnibus (GEO) database, and the data were standardized by DESeq2 as a training set. On the other hand, HGSOC RNA sequence data and information on clinical follow-up were retrieved from The Cancer Genome Atlas (TCGA) as a test set. Additionally, ovarian cancer microarray data set was obtained from GEO as the external validation set. Prognostic genes were screened from the training set, and characteristic selection was performed using the least absolute shrinkage and selection operator (LASSO) with 80% re-sampling for 5000 times. Genes with a frequency of more than 2000 were selected as robust biomarkers. Finally, a gene-related prognostic model was validated in both the test and GEO validation sets.ResultsA total of 148 genes were found to be significantly correlated with HGSOC prognosis. The expression profile of these genes could stratify HGSOC prognosis and they were enriched to multiple tumor-related regulatory pathways such as tyrosine metabolism and AMPK signaling pathway. AKR1B10 and ANGPT4 were obtained after 5000-time re-sampling by LASSO regression. AKR1B10 was associated with the metastasis and progression of several tumors. In this study, Cox regression analysis was performed to create a 2-gene signature as an independent prognostic factor for HGSOC, which has the ability to stratify risk samples in all three data sets (p < 0.05). The Gene Set Enrichment Analysis (GSEA) discovered abnormally active REGULATION_OF_AUTOPHAGY and OLFACTORY_TRANSDUCTION pathways in the high-risk group samples.ConclusionThis study resulted in the creation of a 2-gene molecular prognostic classifier that distinguished clinical features and was a promising novel prognostic tool for assessing the prognosis of HGSOC. RiskScore was a novel prognostic model which might be effective in guiding accurate prognosis of HGSOC.

An improved multi-objective marine predator algorithm for gene selection in classification of cancer microarray data

Gene selection (GS) is an important branch of interest within the field of feature selection, which is widely used in cancer classification. It provides essential insights into the pathogenesis of cancer and enables a deeper understanding of cancer data. In cancer classification, GS is essentially a multi-objective optimization problem, which aims to simultaneously optimize the two objectives of classification accuracy and the size of the gene subset. The marine predator algorithm (MPA) has been successfully employed in practical applications, however, its random initialization can lead to blindness, which may adversely affect the convergence of the algorithm. Furthermore, the elite individuals in guiding evolution are randomly chosen from the Pareto solutions, which may degrade the good exploration performance of the population. To overcome these limitations, a multi-objective improved MPA with continuous mapping initialization and leader selection strategies is proposed. In this work, a new continuous mapping initialization with ReliefF overwhelms the defects with less information in late evolution. Moreover, an improved elite selection mechanism with Gaussian distribution guides the population to evolve towards a better Pareto front. Finally, an efficient mutation method is adopted to prevent evolutionary stagnation. To evaluate its effectiveness, the proposed algorithm was compared with 9 famous algorithms. The experimental results on 16 datasets demonstrate that the proposed algorithm can significantly reduce the data dimension and obtain the highest classification accuracy on most of high-dimension cancer microarray datasets.

A gravity inspired clustering algorithm for gene selection from high-dimensional microarray data

ABSTRACT The problem of selecting a subset of genes relevant to a particular disease classification task from high-dimensional gene microarray data has been an area of active research in the scientific community. A wide variety of methods ranging from assigning scores to genes based on their interactions with the output to the Gravity inspired clustering algorithm with the hybrid approach have been proposed. The feature sets selected by this approach have been evaluated by using the Support Vector Machine (SVM) with Leave One Out Cross Validation (LOOCV). The method has been evaluated on twelve different publicly available microarray cancer datasets and the proposed method provided good accuracy of 90.16% to the colon dataset, 98.59% to the ALL-AML dataset, 97.03% to the lung cancer dataset, 93.07% to the prostate cancer dataset, 98.41% to the meningioma dataset, 83.72% to the brain tumour dataset and has been shown to compete with existing methods.

On a nonlinear extension of the principal fitted component model

We propose a nonlinear sufficient dimension reduction method called the kernel principal fitted component model using the kernel method under a reproducing kernel Hilbert space. The kernel principal fitted component is a nonlinear extension of the principal fitted component model, and it is found in the theory of mapping low dimensional input space to the higher dimensional feature space so that we can apply well-developed linear methods to the nonlinear dataset. We derive our method coincides with the generalized sliced inverse regression under some mild assumptions and show the dimension reduction subspace extracted from the kernel principal fitted component model is contained in the central class. In the numerical experiments, we present the kernel principal fitted component model with the Gaussian kernel can extract the linear and nonlinear features well for the models from both forward and inverse regression settings. By applying our method to ovarian cancer microarray dataset, we demonstrate the kernel principal fitted component can provide a competitive prediction accuracy and computational efficiency in the high-dimensional classification problem.

Characterization of the gene signature correlated with favorable response to chemoradiotherapy in rectal cancer: A hypothesis-generating study.

This study aimed to define the gene signature associated with response to neoadjuvant chemoradiotherapy (nCRT), or chemoradiosensitivity (CRS) signature, in rectal cancer, and investigate the correlation between the CRS signature and characteristics of tumor. Three public microarray datasets of pre-nCRT rectal cancer were used to discover and validate the CRS signature, and the pathway analysis of the CRS signature was performed. Patients in The Cancer Genome Atlas (TCGA) dataset were stratified according to the CRS signature enrichment score, and mutational profile and proportions of infiltrated immune cells were compared. In the discovery dataset (GSE53781), 95 genes were upregulated in complete responders compared to non-complete responders and defined as the CRS signature. Pathways regarding DNA replication and repair processes as well as inflammatory response were enriched in the CRS signature. In the validation datasets (GSE35452 and GSE45404), patients with favorable response to nCRT exhibited higher enrichment score of the CRS. In TCGA-READ cohort, patients with high CRS signature harbored KRAS mutation in lower frequency than those with low CRS signature. In addition, proportions of proinflammatory immune cells were higher, but proportion of immunosuppressive M2 macrophages was lower in patients with high CRS signature than those with low CRS signature. The current integrative bioinformatic analysis suggests the CRS signature and showed that the CRS signature is associated with dissimilar mutational profile and increased immune response. The discovered CRS signature and related characteristics may serve as candidate of stratification factor in upcoming studies for rectal cancer.

Re-Analysis of Non-Small Cell Lung Cancer and Drug Resistance Microarray Datasets with Machine Learning

Non-small cell lung cancer is the most common type of lung cancer. Identification of genes associated with this disease may contribute to the treatment of the disease. Therefore, a lot of work is being done. In some of these studies, genetic data is obtained by microarray analysis and shared publicly in databases such as NCBI Gene Expression Omnibus. In today’s big data era, machine learning algorithms are frequently used to access valuable information from data stacks. Within the scope of this study, all (6 pieces) microarray datasets related to NSCLC and drug resistance in the NCBI GEO database were analyzed by R Studio. With support vector machine, k nearest neighbor, naïve Bayes, random forest, C5.0 decision tree, multilayer perceptron, and artificial neural network algorithms with principal component step, the datasets were analyzed separately and related genes were determined through the caret package, and the top 10 genes for each algorithm were given in the findings section in order of importance. In this resulting gene table, ELOVL7, HMGA2, SAT1, RRM1, IER3, SLC7A11, and U2AF1 genes are included in at least 2 different datasets. These identified genes are recommended to researchers working in a wet laboratory environment to be validated experimentally.

Feature selection in high‐dimensional microarray cancer datasets using an improved equilibrium optimization approach

SummaryOptimal feature selection of a high‐dimensional micro‐array datasets has gained a significant importance in medical applications for early detection and prevention of disease. Traditional Optimal feature selection percolates through a population‐based meta‐heuristic optimization technique, a Machine Learning classifier and traditional wrapper method for transforming the original feature set into a better feature set. These techniques require a number of iterations for the convergence of random solutions to the global optimum with high‐dimensionality issues such as over‐fitting, memory constraints, computational costs, and low accuracy. In this article, an efficient equilibrium optimization technique is proposed for an optimized feature selection that increases the diversity of the population in the search space through Random Opposition based learning and classify the best features using a 10‐fold cross‐validation‐based wrapper method. The proposed method is tested with six standard micro‐array datasets and compared with the conventional algorithms such as Marine Predators Algorithm, Harris Hawks Optimization, Whale Optimization Algorithm, and conventional Equilibrium Optimization. From the statistical results using the standard metrics, it is interpreted that the proposed method converges to the global minimum in a few iterations through optimized feature selection, fitness value and higher classification accuracy. This proves its efficacy in exploring and finding a better solution as compared to the counterpart algorithms. In addition to complexity analysis, these results indicate a global optimum solution, an effective representation of least amount of data‐high dimensionality reduction and an avoidance of over‐fitting problems. The source code is available at https://github.com/balasv/ROBL‐EOA/blob/main/ROBL_EOA.ipynb

Up-Regulated Proteins Have More Protein-Protein Interactions than Down-Regulated Proteins.

Microarray technology has been successfully used in many biology studies to solve the protein–protein interaction (PPI) prediction computationally. For normal tissue, the cell regulation process begins with transcription and ends with the translation process. However, when cell regulation activity goes wrong, cancer occurs. Microarray data can precisely give high accuracy expression levels at normal and cancer-affected cells, which can be useful for the identification of disease-related genes. First, the differentially expressed genes (DEGs) are extracted from the cancer microarray dataset in order to identify the genes that are up-regulated and down-regulated during cancer progression in the human body. Then, proteins corresponding to these genes are collected from NCBI, and then the STRING web server is used to build the PPI network of these proteins. Interestingly, up-regulated proteins have always a higher number of PPIs compared to down-regulated proteins, although, in most of the datasets, the majority of these DEGs are down-regulated. We hope this study will help to build a relevant model to analyze the process of cancer progression in the human body.Supplementary InformationThe online version contains supplementary material available at 10.1007/s10930-022-10081-6.

Expression and the Prognostic Value of Biglycan in Gastric Cancer.

Background Biglycan (BGN) is a family member of small leucine-rich repeat proteoglycans. High expression of BGN might enhance the invasion and metastasis in some types of tumors. Here, the prognostic significance of BGN was evaluated in gastric cancer. Material and Methods. Two independent Gene Expression Omnibus (GEO) gastric cancer microarray datasets (n = 64 and n = 432) were collected for this study. Kaplan-Meier analysis was applied to evaluate if BGN impacts the outcomes of gastric cancer. Protein-protein interaction (PPI) analysis was performed on gastric cancer-related genes and BGN targets, and those interactions with confidence interval (CI) ≥ 0.7 were chosen to construct a PPI network. The gene set enrichment analysis (GSEA) was used to explore BGN and cancer-related gene signatures. Gene Transcription Regulation Database (GTRD) and ALGGEN-PROMO predicted the transcription factor binding sites (TFBSs) of the BGN promoter. BGN protein level in gastric cancer tissue was determined by immunohistochemistry (IHC). Bioinformatic analysis predicted the putative TFs of BGN. Results For gastric cancer, the mRNA expression level of BGN in tumor tissue was significantly higher than that in normal tissue. Kaplan-Meier analysis showed that higher expression of BGN mRNA was significantly associated with more reduced recurrence-free survival (RFS). GSEA results suggested that BGN was significantly enriched in gene signatures related to metastasis and poor prognosis, revealing that BGN might be associated with cell proliferation, poor differentiation, and high invasiveness of gastric cancer. Meanwhile, the putative TFs, including AR, E2F1, and TCF4, were predicted by bioinformatic analysis and also significantly correlated with expression of BGN in mRNA levels. Conclusion High expression of BGN mRNA was significantly related to poor prognosis, which suggested that BGN was a potential prognostic biomarker and therapeutic target of gastric cancer.

Feature selection and computational optimization in high-dimensional microarray cancer datasets via InfoGain-modified bat algorithm

Feature selection and computational optimization in high-dimensional microarray cancer datasets via InfoGain-modified bat algorithm

Integrative analysis of LncRNA-mRNA signature reveals a functional LincRNA in triple-negative breast cancer

PurposeTriple-negative breast cancer (TNBC) is an aggressive subtype of breast cancer. It is still unclear that the mechanisms by which long non-coding RNA (lncRNA) regulates tumorigenesis of TNBC. In this study, we explored the function and regulation of lncRNA in TNBC.MethodsThe differentially expressed and overlapped lncRNAs were obtained from two microarray datasets of breast cancer. The cancer genome atlas (TCGA) data was applied to validate the roles of top differentially expressed lncRNAs. The potential relationship among lncRNAs, miRNAs, and mRNAs and the effects of them on the TNBC tumorigenesis were further explored through multiple bioinformatic methods.ResultsLong intergenic non-protein coding RNA 1351 (LINC01351) was first discovered to play an oncogenic role in TNBC. The highly expressed LINC01351 was significantly related to aggressive subtypes, advanced stages and metastasis of breast cancer. The overexpressed LINC01351 was associated with adverse prognosis of patients with TNBC. LINC01351 was found to negatively regulate ELK4 which was involved in the transcriptional regulation in cancer. The high expression of ELK4 showed favorable prognosis of patients with basal-like 1 subtype and luminal androgen receptor subtype of TNBC.ConclusionThe dysregulation of LINC01351 played an important role in triple-negative breast cancer. LINC01351 could be a poor prognostic marker and a potential target for patients with TNBC.