ConGEMs: Condensed Gene Co-Expression Module Discovery Through Rule-Based Clustering and Its Application to Carcinogenesis

PPIGCF: A Protein-Protein Interaction-Based Gene Correlation Filter for Optimal Gene Selection

Biological data at the omics level are highly complex, requiring powerful computational approaches to identifying significant intrinsic characteristics to further search for informative markers involved in the studied phenotype. In this paper, we propose a novel dimension reduction technique, protein-protein interaction-based gene correlation filtration (PPIGCF), which builds on gene ontology (GO) and protein-protein interaction (PPI) structures to analyze microarray gene expression data. PPIGCF first extracts the gene symbols with their expression from the experimental dataset, and then, classifies them based on GO biological process (BP) and cellular component (CC) annotations. Every classification group inherits all the information on its CCs, corresponding to the BPs, to establish a PPI network. Then, the gene correlation filter (regarding gene rank and the proposed correlation coefficient) is computed on every network and eradicates a few weakly correlated genes connected with their corresponding networks. PPIGCF finds the information content (IC) of the other genes related to the PPI network and takes only the genes with the highest IC values. The satisfactory results of PPIGCF are used to prioritize significant genes. We performed a comparison with current methods to demonstrate our technique's efficiency. From the experiment, it can be concluded that PPIGCF needs fewer genes to reach reasonable accuracy (~99%) for cancer classification. This paper reduces the computational complexity and enhances the time complexity of biomarker discovery from datasets.

Comparison of five supervised feature selection algorithms leading to top features and gene signatures from multi-omics data in cancer

BACKGROUND

As many complex omics data have been generated during the last two decades, dimensionality reduction problem has been a challenging issue in better mining such data. The omics data typically consists of many features. Accordingly, many feature selection algorithms have been developed. The performance of those feature selection methods often varies by specific data, making the discovery and interpretation of results challenging.

METHODS AND RESULTS

In this study, we performed a comprehensive comparative study of five widely used supervised feature selection methods (mRMR, INMIFS, DFS, SVM-RFE-CBR and VWMRmR) for multi-omics datasets. Specifically, we used five representative datasets: gene expression (Exp), exon expression (ExpExon), DNA methylation (hMethyl27), copy number variation (Gistic2), and pathway activity dataset (Paradigm IPLs) from a multi-omics study of acute myeloid leukemia (LAML) from The Cancer Genome Atlas (TCGA). The different feature subsets selected by the aforesaid five different feature selection algorithms are assessed using three evaluation criteria: (1) classification accuracy (Acc), (2) representation entropy (RE) and (3) redundancy rate (RR). Four different classifiers, viz., C4.5, NaiveBayes, KNN, and AdaBoost, were used to measure the classification accuary (Acc) for each selected feature subset. The VWMRmR algorithm obtains the best Acc for three datasets (ExpExon, hMethyl27 and Paradigm IPLs). The VWMRmR algorithm offers the best RR (obtained using normalized mutual information) for three datasets (Exp, Gistic2 and Paradigm IPLs), while it gives the best RR (obtained using Pearson correlation coefficient) for two datasets (Gistic2 and Paradigm IPLs). It also obtains the best RE for three datasets (Exp, Gistic2 and Paradigm IPLs). Overall, the VWMRmR algorithm yields best performance for all three evaluation criteria for majority of the datasets. In addition, we identified signature genes using supervised learning collected from the overlapped top feature set among five feature selection methods. We obtained a 7-gene signature (ZMIZ1, ENG, FGFR1, PAWR, KRT17, MPO and LAT2) for EXP, a 9-gene signature for ExpExon, a 7-gene signature for hMethyl27, one single-gene signature (PIK3CG) for Gistic2 and a 3-gene signature for Paradigm IPLs.

CONCLUSION

We performed a comprehensive comparison of the performance evaluation of five well-known feature selection methods for mining features from various high-dimensional datasets. We identified signature genes using supervised learning for the specific omic data for the disease. The study will help incorporate higher order dependencies among features.

In silico ranking of phenolics for therapeutic effectiveness on cancer stem cells

BACKGROUND

Cancer stem cells (CSCs) have features such as the ability to self-renew, differentiate into defined progenies and initiate the tumor growth. Treatments of cancer include drugs, chemotherapy and radiotherapy or a combination. However, treatment of cancer by various therapeutic strategies often fail. One possible reason is that the nature of CSCs, which has stem-like properties, make it more dynamic and complex and may cause the therapeutic resistance. Another limitation is the side effects associated with the treatment of chemotherapy or radiotherapy. To explore better or alternative treatment options the current study aims to investigate the natural drug-like molecules that can be used as CSC-targeted therapy. Among various natural products, anticancer potential of phenolics is well established. We collected the 21 phytochemicals from phenolic group and their interacting CSC genes from the publicly available databases. Then a bipartite graph is constructed from the collected CSC genes along with their interacting phytochemicals from phenolic group as other. The bipartite graph is then transformed into weighted bipartite graph by considering the interaction strength between the phenolics and the CSC genes. The CSC genes are also weighted by two scores, namely, DSI (Disease Specificity Index) and DPI (Disease Pleiotropy Index). For each gene, its DSI score reflects the specific relationship with the disease and DPI score reflects the association with multiple diseases. Finally, a ranking technique is developed based on PageRank (PR) algorithm for ranking the phenolics.

RESULTS

We collected 21 phytochemicals from phenolic group and 1118 CSC genes. The top ranked phenolics were evaluated by their molecular and pharmacokinetics properties and disease association networks. We selected top five ranked phenolics (Resveratrol, Curcumin, Quercetin, Epigallocatechin Gallate, and Genistein) for further examination of their oral bioavailability through molecular properties, drug likeness through pharmacokinetic properties, and associated network with CSC genes.

CONCLUSION

Our PR ranking based approach is useful to rank the phenolics that are associated with CSC genes. Our results suggested some phenolics are potential molecules for CSC-related cancer treatment.

Detecting methylation signatures in neurodegenerative disease by density-based clustering of applications with reducing noise

There have been numerous genetic and epigenetic datasets generated for the study of complex disease including neurodegenerative disease. However, analysis of such data often suffers from detecting the outliers of the samples, which subsequently affects the extraction of the true biological signals involved in the disease. To address this critical issue, we developed a novel framework for identifying methylation signatures using consecutive adaptation of a well-known outlier detection algorithm, density based clustering of applications with reducing noise (DBSCAN) followed by hierarchical clustering. We applied the framework to two representative neurodegenerative diseases, Alzheimer's disease (AD) and Down syndrome (DS), using DNA methylation datasets from public sources (Gene Expression Omnibus, GEO accession ID: GSE74486). We first applied DBSCAN algorithm to eliminate outliers, and then used Limma statistical method to determine differentially methylated genes. Next, hierarchical clustering technique was applied to detect gene modules. Our analysis identified a methylation signature comprising 21 genes for AD and a methylation signature comprising 89 genes for DS, respectively. Our evaluation indicated that these two signatures could lead to high classification accuracy values (92% and 70%) for these two diseases. In summary, this framework will be useful to better detect outlier-free genetic and epigenetic signatures in various complex diseases and their developmental stages.

(Differential) Co-Expression Analysis of Gene Expression: A Survey of Best Practices

Analysis of gene expression data is widely used in transcriptomic studies to understand functions of molecules inside a cell and interactions among molecules. Differential co-expression analysis studies diseases and phenotypic variations by finding modules of genes whose co-expression patterns vary across conditions. We review the best practices in gene expression data analysis in terms of analysis of (differential) co-expression, co-expression network, differential networking, and differential connectivity considering both microarray and RNA-seq data along with comparisons. We highlight hurdles in RNA-seq data analysis using methods developed for microarrays. We include discussion of necessary tools for gene expression analysis throughout the paper. In addition, we shed light on scRNA-seq data analysis by including preprocessing and scRNA-seq in co-expression analysis along with useful tools specific to scRNA-seq. To get insights, biological interpretation and functional profiling is included. Finally, we provide guidelines for the analyst, along with research issues and challenges which should be addressed.

Graph- and rule-based learning algorithms: a comprehensive review of their applications for cancer type classification and prognosis using genomic data

Cancer is well recognized as a complex disease with dysregulated molecular networks or modules. Graph- and rule-based analytics have been applied extensively for cancer classification as well as prognosis using large genomic and other data over the past decade. This article provides a comprehensive review of various graph- and rule-based machine learning algorithms that have been applied to numerous genomics data to determine the cancer-specific gene modules, identify gene signature-based classifiers and carry out other related objectives of potential therapeutic value. This review focuses mainly on the methodological design and features of these algorithms to facilitate the application of these graph- and rule-based analytical approaches for cancer classification and prognosis. Based on the type of data integration, we divided all the algorithms into three categories: model-based integration, pre-processing integration and post-processing integration. Each category is further divided into four sub-categories (supervised, unsupervised, semi-supervised and survival-driven learning analyses) based on learning style. Therefore, a total of 11 categories of methods are summarized with their inputs, objectives and description, advantages and potential limitations. Next, we briefly demonstrate well-known and most recently developed algorithms for each sub-category along with salient information, such as data profiles, statistical or feature selection methods and outputs. Finally, we summarize the appropriate use and efficiency of all categories of graph- and rule mining-based learning methods when input data and specific objective are given. This review aims to help readers to select and use the appropriate algorithms for cancer classification and prognosis study.

Multi-Objective Optimized Fuzzy Clustering for Detecting Cell Clusters from Single-Cell Expression Profiles

Rapid advance in single-cell RNA sequencing (scRNA-seq) allows measurement of the expression of genes at single-cell resolution in complex disease or tissue. While many methods have been developed to detect cell clusters from the scRNA-seq data, this task currently remains a main challenge. We proposed a multi-objective optimization-based fuzzy clustering approach for detecting cell clusters from scRNA-seq data. First, we conducted initial filtering and SCnorm normalization. We considered various case studies by selecting different cluster numbers ( c l = 2 to a user-defined number), and applied fuzzy c-means clustering algorithm individually. From each case, we evaluated the scores of four cluster validity index measures, Partition Entropy ( P E ), Partition Coefficient ( P C ), Modified Partition Coefficient ( M P C ), and Fuzzy Silhouette Index ( F S I ). Next, we set the first measure as minimization objective (↓) and the remaining three as maximization objectives (↑), and then applied a multi-objective decision-making technique, TOPSIS, to identify the best optimal solution. The best optimal solution (case study) that had the highest TOPSIS score was selected as the final optimal clustering. Finally, we obtained differentially expressed genes (DEGs) using Limma through the comparison of expression of the samples between each resultant cluster and the remaining clusters. We applied our approach to a scRNA-seq dataset for the rare intestinal cell type in mice [GEO ID: GSE62270, 23,630 features (genes) and 288 cells]. The optimal cluster result (TOPSIS optimal score= 0.858) comprised two clusters, one with 115 cells and the other 91 cells. The evaluated scores of the four cluster validity indices, F S I , P E , P C , and M P C for the optimized fuzzy clustering were 0.482, 0.578, 0.607, and 0.215, respectively. The Limma analysis identified 1240 DEGs (cluster 1 vs. cluster 2). The top ten gene markers were Rps21, Slc5a1, Crip1, Rpl15, Rpl3, Rpl27a, Khk, Rps3a1, Aldob and Rps17. In this list, Khk (encoding ketohexokinase) is a novel marker for the rare intestinal cell type. In summary, this method is useful to detect cell clusters from scRNA-seq data.

Identification of gene signatures from RNA-seq data using Pareto-optimal cluster algorithm

Background

Gene signatures are important to represent the molecular changes in the disease genomes or the cells in specific conditions, and have been often used to separate samples into different groups for better research or clinical treatment. While many methods and applications have been available in literature, there still lack powerful ones that can take account of the complex data and detect the most informative signatures.

Methods

In this article, we present a new framework for identifying gene signatures using Pareto-optimal cluster size identification for RNA-seq data. We first performed pre-filtering steps and normalization, then utilized the empirical Bayes test in Limma package to identify the differentially expressed genes (DEGs). Next, we used a multi-objective optimization technique, “Multi-objective optimization for collecting cluster alternatives” (MOCCA in R package) on these DEGs to find Pareto-optimal cluster size, and then applied k-means clustering to the RNA-seq data based on the optimal cluster size. The best cluster was obtained through computing the average Spearman’s Correlation Score among all the genes in pair-wise manner belonging to the module. The best cluster is treated as the signature for the respective disease or cellular condition.

Results

We applied our framework to a cervical cancer RNA-seq dataset, which included 253 squamous cell carcinoma (SCC) samples and 22 adenocarcinoma (ADENO) samples. We identified a total of 582 DEGs by Limma analysis of SCC versus ADENO samples. Among them, 260 are up-regulated genes and 322 are down-regulated genes. Using MOCCA, we obtained seven Pareto-optimal clusters. The best cluster has a total of 35 DEGs consisting of all-upregulated genes. For validation, we ran PAMR (prediction analysis for microarrays) classifier on the selected best cluster, and assessed the classification performance. Our evaluation, measured by sensitivity, specificity, precision, and accuracy, showed high confidence.

Conclusions

Our framework identified a multi-objective based cluster that is treated as a signature that can classify the disease and control group of samples with higher classification performance (accuracy 0.935) for the corresponding disease. Our method is useful to find signature for any RNA-seq or microarray data.

An Introduction to Integrative Genomics and Systems Medicine in Cancer

In this Special Issue (SI), with a theme of "Integrative Genomics and Systems Medicine in Cancer", we have collected a total of 12 research and review articles from researchers in the field of genomics and systems medicine[...].