Cancer Microarray Data Research Articles

Revealing a cancer-associated fibroblast-based risk signature for pancreatic adenocarcinoma through single-cell and bulk RNA-seq analysis.

Proliferation of stromal connective tissue is a hallmark of pancreatic adenocarcinoma (PAAD). The engagement of activated cancer-associated fibroblasts (CAFs) contributes to the progression of PAAD through their involvement in tumor fibrogenesis. However, the prognostic significance of CAF-based risk signature in PAAD has not been explored. The single-cell RNA sequencing (scRNA-seq) data sourced from GSE155698 within the Gene Expression Omnibus (GEO) database was supplemented by bulk RNA sequencing data from The Cancer Genome Atlas (TCGA) and microarray data retrieved from the GEO database. The scRNA-seq data underwent processing via the Seurat package to identify distinct CAF clusters utilizing specific CAF markers. Differential gene expression analysis between normal and tumor samples was conducted within the TCGA-PAAD cohort. Univariate Cox regression analysis pinpointed genes associated with CAF clusters, identifying prognostic CAF-related genes. These genes were utilized in LASSO regression to craft a predictive risk signature. Subsequently, integrating clinicopathological traits and the risk signature, a nomogram model was constructed. Our scRNA-seq analysis unveiled four distinct CAF clusters in PAAD, with two linked to PAAD prognosis. Among 207 identified DEGs, 148 exhibited significant correlation with these CAF clusters, forming the basis of a seven-gene risk signature. This signature emerged as an independent predictor in multivariate analysis for PAAD and demonstrated predictive efficacy in immunotherapeutic outcomes. Additionally, a novel nomogram, integrating age and the CAF-based risk signature, exhibited robust predictability and reliability in prognosticating PAAD. Moreover, the risk signature displayed substantial correlations with stromal and immune scores, as well as specific immune cell types. The prognosis of PAAD can be accurately predicted using the CAF-based risk signature, and a thorough analysis of the PAAD CAF signature may aid in deciphering the patient's immunotherapy response and presenting fresh cancer treatment options.

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.

Performance enhancement of classifiers through Bio inspired feature selection methods for early detection of lung cancer from microarray genes

Gene expression in the microarray is assimilated with redundant and high-dimensional information. Moreover, the information in the microarray genes mostly correlates with background noise. This paper uses dimensionality reduction and feature selection methods to employ a classification methodology for high-dimensional lung cancer microarray data. The approach is enforced in two phases; initially, the genes are dimensionally reduced through Hilbert Transform, Detrend Fluctuation Analysis and Least Square Linear Regression methods. The dimensionally reduced data is further optimized in the next phase using Elephant Herd optimization (EHO) and Cuckoo Search Feature selection methods. The classifiers used here are Bayesian Linear Discriminant, Naive Bayes, Random Forest, Decision Tree, SVM (Linear), SVM (Polynomial), and SVM (RBF). The classifier's performances are analysed with and without feature selection methods. The SVM (Linear) classifier with the DFA Dimensionality Reduction method and EHO feature selection achieved the highest accuracy of 92.26 % compared to other classifiers.

Efficient Gene Expression Data Analysis using ES-DBN For Microarray Cancer Data Classification

INTRODUCTION: DNA microarray has become a promising means for classification of various cancer types via the creation of various Gene Expression (GE) profiles, with the advancement of technologies. But, it is challenging to classify the GE profile since not all genes contribute to the presence of cancer and might lead to incorrect diagnoses. Thus an efficient GE data analysis for microarray cancer data classification using Exponential Sigmoid-Deep Belief Network (ES-DBN) is proposed in this work.OBJECTIVES: The study aims to develop an efficient GE data analysis using Exponential Sigmoid-Deep Belief Network (ES-DBN) for microarray cancer data classification.METHODS: The proposed methodology starts with pre-processing to compact data. Afterward, by utilizing Min-Max feature scaling technique, the pre-processed data is normalized. The normalized data is further encoded and feature ranking is performed. The subset values are selected using Cauchy Mutation-Coral Reefs Optimization (CM-CRO) in feature ranking. The feature vector is calculated by Pearson Correlation Coefficient based GloVe (PCC-GloVe) algorithm since different subsets return the same fitness value. Statistical and Biological validations take place after feature vector calculation. Lastly, for effective classification of the type of cancer, the vector features obtained are fed to ES-DBN.RESULTS: The outcomes of the proposed technique are evaluated with various datasets, which exhibited that the proposed technique performed well with the Ovarian cancer dataset and outperforms other conventional approaches.CONCLUSION: This study presents a comprehensive methodology for efficiently classifying cancer types using GE profile. The proposed GE data analysis using ES-DBN shows promising results, highlighting its potential as a valuable tool for cancer diagnosis and classification.

An efficient feature selection and classification system for microarray cancer data using genetic algorithm and deep belief networks

An efficient feature selection and classification system for microarray cancer data using genetic algorithm and deep belief networks

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.

Classification of Cancer Microarray Data Based on Deep Learning: A Review

This review article delves into applying deep learning methodologies in conjunction with microarray data for cancer classification. The study provides a comprehensive overview of recent advancements in utilizing deep learning techniques to accurately categorize cancer types based on intricate patterns discerned from microarray datasets. Various aspects are covered, including integrating deep learning algorithms, exploring diverse cancer types, and analyzing microarray data to enhance classification accuracy. The review synthesizes findings from recent research, highlighting the efficacy of deep learning in uncovering subtle and complex relationships within microarray data that contribute to improved classification outcomes. Key insights into the strengths and limitations of employing deep learning in this context are discussed, offering a critical appraisal of the field's current state. This review aims to provide a valuable resource for researchers, clinicians, and practitioners interested in cutting-edge developments in cancer classification methodologies by exploring the intersection of deep learning and microarray technology. The synthesis of knowledge presented herein contributes to a deeper understanding of the potential and challenges associated with harnessing deep learning for enhanced classification accuracy in the realm of cancer research.

Identification and validation of mitophagy-related signatures as a novel prognostic model for colorectal cancer.

Colorectal cancer (CRC) is one of the most commonly diagnosed cancers in the world. Mitophagy is associated with tumorigenesis and development of malignancy. However, the specific role of mitophagy has yet not been systematically explored in CRC. The RNA-sequencing dataset of CRC from The Cancer Genome Atlas (TCGA) and microarray data of gene expression profiles of CRC from Gene Expression Omnibus (GEO) were downloaded. Mitophagy-related gene sets were obtained from the Pathway Unification database. The package "limma" was used for differential gene expression analysis. Kaplan-Meier (KM) survival analyses were utilized to evaluate the prognostic value of the mitophagy regulators. Single-sample gene set enrichment analysis (ssGSEA) was used to estimate the infiltrating immune cells and the activity of immune response. The ConsensusClusterPlus algorithm was used to determine mitophagy-related subtypes. Principal component analysis (PCA) was used to create composite measurement of mitophagy scores. The R packages "survminer" and "ReGlot" were used to plot the nomogram and calibration curves. Integrated analysis of the GEO and TCGA databases revealed some common differentially expressed genes (DEGs) in CRC. MFN2, UBB, PINK1, and PRKN were significantly downregulated in CRC samples as compared to normal samples, and other genes were significantly upregulated in CRC samples. KM survival analyses showed that high expression of ATG12 and MAP1LC3B predicted a poor prognosis, whereas high expression of TOMM22 and TOMM40 predicted a better prognosis. Mitophagy showed significant correlation with immune-related pathways in CRC samples. We identified 2 distinct CRC subtypes with different mitophagy accumulation, of which subtype B had better prognosis and immune activity. The mitophagy score may be employed as a new and efficient clinical predictor in conjunction with other clinical indicators to predict the prognosis of CRC patients. We systematically investigated the CRC heterogeneity with reference to mitophagy based on bioinformatics analyses, and the findings of this study might provide some guidance for future research into potential biomarkers for diagnosis and prognosis prediction of CRC patients.

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.

Enhancing the prediction of IDC breast cancer staging from gene expression profiles using hybrid feature selection methods and deep learning architecture.

Prediction of the stage of cancer plays an important role in planning the course of treatment and has been largely reliant on imaging tools which do not capture molecular events that cause cancer progression. Gene-expression data-based analyses are able to identify these events, allowing RNA-sequence and microarray cancer data to be used for cancer analyses. Breast cancer is the most common cancer worldwide, and is classified into four stages - stages 1, 2, 3, and 4 [2]. While machine learning models have previously been explored to perform stage classification with limited success, multi-class stage classification has not had significant progress. There is a need for improved multi-class classification models, such as by investigating deep learning models. Gene-expression-based cancer data is characterised by the small size of available datasets, class imbalance, and high dimensionality. Class balancing methods must be applied to the dataset. Since all the genes are not necessary for stage prediction, retaining only the necessary genes can improve classification accuracy. The breast cancer samples are to be classified into 4 classes of stages 1 to 4. Invasive ductal carcinoma breast cancer samples are obtained from The Cancer Genome Atlas (TCGA) and Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) datasets and combined. Two class balancing techniques are explored, synthetic minority oversampling technique (SMOTE) and SMOTE followed by random undersampling. A hybrid feature selection pipeline is proposed, with three pipelines explored involving combinations of filter and embedded feature selection methods: Pipeline 1 - minimum-redundancy maximum-relevancy (mRMR) and correlation feature selection (CFS), Pipeline 2 - mRMR, mutual information (MI) and CFS, and Pipeline 3 - mRMR and support vector machine-recursive feature elimination (SVM-RFE). The classification is done using deep learning models, namely deep neural network, convolutional neural network, recurrent neural network, a modified deep neural network, and an AutoKeras generated model. Classification performance post class-balancing and various feature selection techniques show marked improvement over classification prior to feature selection. The best multiclass classification was found to be by a deep neural network post SMOTE and random undersampling, and feature selection using mRMR and recursive feature elimination, with a Cohen-Kappa score of 0.303 and a classification accuracy of 53.1%. For binary classification into early and late-stage cancer, the best performance is obtained by a modified deep neural network (DNN) post SMOTE and random undersampling, and feature selection using mRMR and recursive feature elimination, with an accuracy of 81.0% and a Cohen-Kappa score (CKS) of 0.280. This pipeline also showed improved multiclass classification performance on neuroblastoma cancer data, with a best area under the receiver operating characteristic (auROC) curve score of 0.872, as compared to 0.71 obtained in previous work, an improvement of 22.81%. The results and analysis reveal that feature selection techniques play a vital role in gene-expression data-based classification, and the proposed hybrid feature selection pipeline improves classification performance. Multi-class classification is possible using deep learning models, though further improvement particularly in late-stage classification is necessary and should be explored further.

Comparison of Feature Selection Methods in Breast Cancer Microarray Data

Aim: We aim to predict metastasis in breast cancer patients with tree-based conventional machine learning algorithms and to observe which feature selection methods is more effective in machine learning methods related to microarray breast cancer data reducing the number of features. Material and Methods: Feature selection methods, least squares absolute shrinkage (LASSO), Boruta and maximum relevance-minimum redundancy (MRMR) and statistical preprocessing steps were first applied before the tree-based learning conventional machine learning methods like Decision-tree, Extremely randomized trees and Gradient Boosting Tree applied on the microarray breast cancer data. Results: Microarray data with 54675 features (202 (101/101 breast cancer patients with/without metastases)) was first reduced to 235 features, then the feature selection algorithms were applied and the most important features were found with tree-based machine learning algorithms. It was observed that the highest recall and F-measure values were obtained from the XGBoost method and the highest precision value was received from the Extra-tree method. The 10 arrays out of 54675 with the highest variable importance were listed. Conclusion: The most accurate results were obtained from the statistical preprocessed data for the XGBoost and Extra-trees machine learning algorithms. Statistical and microarray preprocessing steps would be enough in machine learning analysis of microarray data in breast cancer metastases predictions.

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.

71P MicroRNA (miRNA) a putative biomarker to better define the molecular apocrine breast cancer (MABC) subtype

Breast cancer (BC), is a heterogeneous disease, divided into molecular subtypes based on gene expression and clinical outcomes. MABC is a poorly diagnosed subtype, characterized by estrogen (ER), progesterone receptor (PR) negativity, and HER-2-amplification in most cases; yet it overexpresses androgen receptor (AR) and activates its pathway. Its improper diagnosis demands the adoption of complementary tools to refine classification; miRNA, key players in regulating cell behavior, AR, and tumorigenic processes of BC hold promise in defining and studying the behavior of MABC. 539 breast cancer microarray data were downloaded from The Cancer Genome Atlas (TCGA-BRCA). Cases with available miRNA data were retained and classified using citbcmst R package (PMID: 30289602). Differential expression analysis identified deregulated miRNAs using DEseq2. A validation set of 131 ER-neg samples was constituted and MABC tumors were characterized apart of triple-negative (TN)BC by the previously described molecular signature (AR, FOXA1 and AR-related genes, PMID: 23663520) on fresh tissue sections. Using miRCURY LNATM miRNA PCR assay, miRNA profiling was done for a panel of 6 differentially expressed miRNAs. Finally, expression of in silico predicted target genes of these miRNAs was assessed by RT-qPCR in MABC and TNBC cell lines after transfection with miRNA mimics. TCGA data analysis indicated MABC as a separate entity based on gene signature. MiRNA-seq data analysis depicted a set of 6 significantly deregulated miRNA with absolute value of log2 fold change> 1 and P-adjusted value <0.05 between MABC and TNBC. We validated on 78 MABC (27 HER2-/ 51 HER2+), and 53 TN samples, by miRNA profiling, significant upregulation of miR-2115-3p and miR-187-3p in MABC compared to TNBC. Preliminary data, showed that the overexpression of these miRNAs significantly downregulates in silico predicted target genes (FGF2, HMGCS1, and ADAM12) implicated in carcinogenesis differently in each of the models used. MABC has a unique signature of miRNA compared to TNBC. The identified miRNAs regulate a set of genes implicated in tumorigenic processes and can potentially serve as biomarkers to effectively diagnose, prognose and treat MABC

A case study of microarray breast cancer classification using machine learning algorithms with grid search cross validation

Breast cancer is one of the leading causes of death and most frequently diagnosed cancer amongst women. Annually, almost half a million women do not survive the disease and die from breast cancer. Machine learning is a subfield of artificial intelligence (AI) and computer science that uses data and algorithms to mimic how humans learn, and gradually improving its accuracy. In this work, simple machine learning methods are used to classify breast cancer microarray data to normal and relapse. The data is from the gene expression omnibus (GEO) website namely GSE45255 and GSE15852. These two datasets are integrated and combined to form a single dataset. The study involved three machine learning algorithms, random forest (RF), extra tree (ET), and support vector machine (SVM). Grid search cross validation (CV) is applied for hyperparameter tuning of the algorithms. The result shows that the tuned SVM is best among the tested algorithms with accuracy of 97.78%. In the future it is recommended to include feature selection method to get the optimal features and better classification accuracies.

Predictive Value of Gene Databases in Discovering New Biomarkers and New Therapeutic Targets in Lung Cancer

Background and Objectives: The molecular mechanisms of lung cancer are still unclear. Investigation of immune cell infiltration (ICI) and the hub gene will facilitate the identification of specific biomarkers. Materials and Methods: Key modules of ICI and immune cell-associated differential genes, as well as ICI profiles, were identified using lung cancer microarray data from the single sample gene set enrichment analysis (ssGSEA) and weighted gene co-expression network analysis (WGCNA) in the gene expression omnibus (GEO) database. Protein-protein interaction networks were used to identify hub genes. The receiver operating characteristic (ROC) curve was used to assess the diagnostic significance of the hub genes, and survival analysis was performed using gene expression profiling interactive analysis (GEPIA). Results: Significant changes in ICI were found in lung cancer tissues versus adjacent normal tissues. WGCNA results showed the highest correlation of yellow and blue modules with ICI. Protein-protein interaction networks identified four hub genes, namely CENPF, AURKA, PBK, and CCNB1. The lung adenocarcinoma patients in the low hub gene expression group showed higher overall survival and longer median survival than the high expression group. They were associated with a decreased risk of lung cancer in patients, indicating their potential role as cancer suppressor genes and potential targets for future therapeutic development. Conclusions: CENPF, AURKA, PBK, and CCNB1 show great potential as biomarkers and immunotherapeutic targets specific to lung cancer. Lung cancer patients' prognoses are often foreseen using matched prognostic models, and genes CENPF, AURKA, PBK, and CCNB1 in lung cancer may serve as therapeutic targets, which require further investigations.

Gene Data Analysis for Disease Detection Using Data Mining Algorithms

As a result of these promising results, researchers believe that gene expression tests are more important in creating more accurate and efficient diagnostic and classification tools for cancer. In the deoxyribonucleic acid (DNA) system, a gene is transcribed over ribonucleic acid (RNA) during transcription, which is a process known as gene expression (RNA). The study of gene expression data for cancer categorization has recently emerged as an active research subject. This research uses genetic algorithms (GA) to pick a subset of cancer microarray data that contains a meaningful set of genes. Then, standard classifiers like One-R, Bayesian Network, logistic regression, and Support Vector Machine (SVM) are developed based on these specific genes. Gene expression data sets are used to test the performance of these classifiers. According to the results of experiments, combining the confluence of GA and SVM is the most effective approach. In addition, the GA selection process is repeatable.

Multilevel Feature Selection Method for Improving Classification of Microarray Gene Expression Data

Microarray gene expression profiles provide valuable answers to a variety of problems, and contributes to advances in clinical medicine. Gene expression data typically has a high dimension and a small sample size. Gene selection from microarray gene expression data is a challenge due to high dimensionality of the data. The number of samples in the microarray dataset is much smaller compared to the number of genes as features. To extract useful gene information from cancer microarray data and reduce dimensionality, selection of significant genes is necessary. An effective method of gene feature selection helps in dimensionality reduction and improves the classification performance. Experimental results suggest that appropriate combination of filter gene selection methods is more effective than individual techniques for microarray data classification. In this paper, we propose a two-layered feature selection method. In the first layer, t-test statistical method is used to remove the features that have little correlation with the classification results. In the second layer, line segment approximation method is used to transform the feature subset into a less dimensional feature space. Four well known classifiers kNN, SVM, NBC, DT were used to verify the performance of the proposed feature selection algorithm on binary class microarray data. The experimental results show that the proposed method can effectively select relevant gene subsets, and achieves higher classification accuracy.

Wnt signaling pathway-derived score for predicting therapeutic resistance and tumor microenvironment in lung adenocarcinoma.

Background: Lung adenocarcinoma (LUAD) is the most common subtype of lung cancer. Due to tumor heterogeneity, understanding the pathological mechanism of tumor progression helps to improve the diagnosis process and clinical treatment strategies of LUAD patients. Methods: The transcriptome pattern, mutant expression and complete clinical information were obtained from the cancer genome atlas (TCGA) database and microarray data from gene expression omnibus (GEO) database. Firstly, we used single sample Gene Set Enrichment Analysis (ssGSEA) to estimate the activation of Wnt signaling pathway in each sample. Consensus clustering algorithm was used to classify LUAD samples into different subgroups according to the transcription patterns of 152 Wnt signaling pathway related genes. Then, ESTIMATE, ssGSEA and Gene Set Variation Analysis (GSVA) algorithms were used to assess the biological pathways and immunocytes infiltration between different subtypes. LASSO-COX algorithm was conducted to construct prognostic model. Kaplan-Meier and multivariate Cox analysis were performed to evaluate the predictive performance of risk model. Gene features were further confirmed using external datasets. Finally, we conducted vitro assay for validating hub gene (LEF1). Results: Based on the transcription patterns of 152 Wnt signaling pathway related genes, four different subtypes of LUAD patients were screened out by consensus clustering algorithm. Subsequently, it was found that patients with cluster A and B had massive immunocytes infiltration, and the survival rate of patients with cluster B was better than that of other subgroups. According to the coefficients in the LASSO- Cox model and the transcriptome patterns of these 18 genes, the risk score was constructed for each sample. The degree of malignancy of LUAD patients with high-risk subgroup was remarkable higher than that of patients with low-risk subgroup (p < 0.001). Subsequently, five top prognostic genes (AXIN1, CTNNB1, LEF1, FZD2, FZD4.) were screened, and their expression values were different between cancer and normal tissues. FZD2 and LEF1 were negatively related to ImmunoScore, and AXIN1 was negatively related to ImmunoScore. The significant correlation between LUAD patient risk score and overall survival (OS) was verified in external datasets. In the A549 cell line, knockdown of LEF1 can reduce the invasive and proliferation ability of LUAD cells. Conclusion: A innovative 18 genes predictive feature based on transcriptome pattern was found in patients with lung adenocarcinoma. These investigations further promote the insight of the prognosis of lung adenocarcinoma and may contribute to disease management at risk stratification.

Memetic micro-genetic algorithms for cancer data classification

Fast and precise medical diagnosis of human cancer is crucial for treatment decisions. Gene selection consists of identifying a set of informative genes from microarray data to allow high predictive accuracy in human cancer classification. This task is a combinatorial search problem, and optimisation methods can be applied for its resolution. In this paper, two memetic micro-genetic algorithms (MμV1 and MμV2) with different hybridisation approaches are proposed for feature selection of cancer microarray data. Seven gene expression datasets are used for experimentation. The comparison with stochastic state-of-the-art optimisation techniques concludes that problem-dependent local search methods combined with micro-genetic algorithms improve feature selection of cancer microarray data.

LncRNA/miRNA/mRNA Network Introduces Novel Biomarkers in Prostate Cancer

The construction of a competing endogenous RNA (ceRNA) network is an important step in the identification of the role of differentially expressed genes in cancers. In the current research, we used a number of bioinformatics tools to construct the ceRNA network in prostate cancer and identify the importance of these modules in predicting the survival of patients with this type of cancer. An assessment of microarray data of prostate cancer and normal samples using the Limma package led to the identification of differential expressed (DE) RNAs that we stratified into mRNA, lncRNA, and miRNAs, resulting in 684 DEmRNAs, including 437 downregulated DEmRNAs (such as TGM4 and SCGB1A1) and 241 upregulated DEmRNAs (such as TDRD1 and CRISP3); 6 DElncRNAs, including 1 downregulated DElncRNA (H19) and 5 upregulated DElncRNAs (such as PCA3 and PCGEM1); and 59 DEmiRNAs, including 30 downregulated DEmiRNAs (such as hsa-miR-1274a and hsa-miR-1274b) and 29 upregulated DEmiRNAs (such as hsa-miR-1268 and hsa-miR-1207-5p). The ceRNA network contained a total of 5 miRNAs, 5 lncRNAs, and 17 mRNAs. We identified hsa-miR-17, hsa-miR-93, hsa-miR-150, hsa-miR-25, PART1, hsa-miR-125b, PCA3, H19, RND3, and ITGB8 as the 10 hub genes in the ceRNA network. According to the ROC analysis, the expression levels of 19 hub genes showed a high diagnostic value. Taken together, we introduce a number of novel promising diagnostic biomarkers for prostate cancer.