μHEM for identification of differentially expressed miRNAs using hypercuboid equivalence partition matrix
TL;DR: The results on several microarray data sets demonstrate that the proposed method can bring a remarkable improvement on miRNA selection problem and is a potentially useful tool for exploration of miRNA expression data and identification of differentially expressed miRNAs worth further investigation.
Abstract: The miRNAs, a class of short approximately 22‐nucleotide non‐coding RNAs, often act post‐transcriptionally to inhibit mRNA expression. In effect, they control gene expression by targeting mRNA. They also help in carrying out normal functioning of a cell as they play an important role in various cellular processes. However, dysregulation of miRNAs is found to be a major cause of a disease. It has been demonstrated that miRNA expression is altered in many human cancers, suggesting that they may play an important role as disease biomarkers. Multiple reports have also noted the utility of miRNAs for the diagnosis of cancer. Among the large number of miRNAs present in a microarray data, a modest number might be sufficient to classify human cancers. Hence, the identification of differentially expressed miRNAs is an important problem particularly for the data sets with large number of miRNAs and small number of samples. In this regard, a new miRNA selection algorithm, called μHEM, is presented based on rough hypercuboid approach. It selects a set of miRNAs from a microarray data by maximizing both relevance and significance of the selected miRNAs. The degree of dependency of sample categories on miRNAs is defined, based on the concept of hypercuboid equivalence partition matrix, to measure both relevance and significance of miRNAs. The effectiveness of the new approach is demonstrated on six publicly available miRNA expression data sets using support vector machine. The.632+ bootstrap error estimate is used to minimize the variability and biasedness of the derived results. An important finding is that the μHEM algorithm achieves lowest B.632+ error rate of support vector machine with a reduced set of differentially expressed miRNAs on four expression data sets compare to some existing machine learning and statistical methods, while for other two data sets, the error rate of the μHEM algorithm is comparable with the existing techniques. The results on several microarray data sets demonstrate that the proposed method can bring a remarkable improvement on miRNA selection problem. The method is a potentially useful tool for exploration of miRNA expression data and identification of differentially expressed miRNAs worth further investigation.
Citations
More filters
TL;DR: The proposed prediction model provides an effective tool for DLB classification and predicted candidate target genes from the miRNAs, including 6 functional genes included in the DHA signaling pathway associated with DLB pathology.
Abstract: Dementia with Lewy bodies (DLB) is the second most common subtype of neurodegenerative dementia in humans following Alzheimer’s disease (AD). Present clinical diagnosis of DLB has high specificity and low sensitivity and finding potential biomarkers of prodromal DLB is still challenging. MicroRNAs (miRNAs) have recently received a lot of attention as a source of novel biomarkers. In this study, using serum miRNA expression of 478 Japanese individuals, we investigated potential miRNA biomarkers and constructed an optimal risk prediction model based on several machine learning methods: penalized regression, random forest, support vector machine, and gradient boosting decision tree. The final risk prediction model, constructed via a gradient boosting decision tree using 180 miRNAs and two clinical features, achieved an accuracy of 0.829 on an independent test set. We further predicted candidate target genes from the miRNAs. Gene set enrichment analysis of the miRNA target genes revealed 6 functional genes included in the DHA signaling pathway associated with DLB pathology. Two of them were further supported by gene-based association studies using a large number of single nucleotide polymorphism markers (BCL2L1: P = 0.012, PIK3R2: P = 0.021). Our proposed prediction model provides an effective tool for DLB classification. Also, a gene-based association test of rare variants revealed that BCL2L1 and PIK3R2 were statistically significantly associated with DLB.
24 citations
Cites methods from "μHEM for identification of differen..."
...This final risk prediction model using μHEM algorithm achieved an accuracy of 0.803 on an independent test set when pre-selecting the top-ranked 330 miRNAs and three clinical features....
[...]
...Paul S, Maji P. muHEM for identification of differentially expressed miRNAs using hypercuboid equivalence partition matrix....
[...]
...We also constructed a GBDT risk prediction model using another feature selection algorithm, μHEM [23], publicly available at http://www....
[...]
...We also constructed a GBDT risk prediction model using another feature selection algorithm, μHEM [23], publicly available at http://www.isical.ac.in/~bibl/results/ mihem/mihem.html, and investigated whether this feature selection methodology can further improve the predictive ability of our model....
[...]
...Hyperparameter values in the final GBDT model when using μHEM algorithm....
[...]
TL;DR: The formulation enables the proposed method to extract required number of correlated features sequentially with lesser computational cost as compared to existing methods, and provides an efficient way to find optimum regularization parameters employed in CCA.
Abstract: One of the main problems associated with high dimensional multimodal real life data sets is how to extract relevant and significant features. In this regard, a fast and robust feature extraction algorithm, termed as FaRoC, is proposed, integrating judiciously the merits of canonical correlation analysis (CCA) and rough sets. The proposed method extracts new features sequentially from two multidimensional data sets by maximizing their relevance with respect to class label and significance with respect to already-extracted features. To generate canonical variables sequentially, an analytical formulation is introduced to establish the relation between regularization parameters and CCA. The formulation enables the proposed method to extract required number of correlated features sequentially with lesser computational cost as compared to existing methods. To compute both significance and relevance measures of a feature, the concept of hypercuboid equivalence partition matrix of rough hypercuboid approach is used. It also provides an efficient way to find optimum regularization parameters employed in CCA. The efficacy of the proposed FaRoC algorithm, along with a comparison with other existing methods, is extensively established on several real life data sets.
23 citations
Cites methods from "μHEM for identification of differen..."
...It has been applied successfully for analyzing omics data [34], [45], [46]....
[...]
TL;DR: Results indicate that the integrated method presented is quite promising and may become a useful tool for identifying disease genes.
Abstract: One of the most important and challenging problems in functional genomics is how to select the disease genes. In this regard, the paper presents a new computational method to identify disease genes. It judiciously integrates the information of gene expression profiles and shortest path analysis of protein---protein interaction networks. While the $$f$$f-information based maximum relevance-maximum significance framework is used to select differentially expressed genes as disease genes using gene expression profiles, the functional protein association network is used to study the mechanism of diseases. An important finding is that some $$f$$f-information measures are shown to be effective for selecting relevant and significant genes from microarray data. Extensive experimental study on colorectal cancer establishes the fact that the genes identified by the integrated method have more colorectal cancer genes than the genes identified from the gene expression profiles alone, irrespective of any gene selection algorithm. Also, these genes have greater functional similarity with the reported colorectal cancer genes than the genes identified from the gene expression profiles alone. The enrichment analysis of the obtained genes reveals to be associated with some of the important KEGG pathways. All these results indicate that the integrated method is quite promising and may become a useful tool for identifying disease genes.
12 citations
Cites methods from "μHEM for identification of differen..."
...The f -MRMS algorithm judiciously integrates the merits of maximum relevancemaximum significance (MRMS) criterion (Maji and Paul 2011; Paul and Maji 2013a, b) and f -information measures....
[...]
TL;DR: This study presents an application of the RH-SAC algorithm on miRNA and mRNA expression data for identification of potential miRNA-mRNA modules and identified novel miRNA/mRNA interactions in colorectal cancer.
Abstract: Differences in the expression profiles of miRNAs and mRNAs have been reported in colorectal cancer. Nevertheless, information on important miRNA-mRNA regulatory modules in colorectal cancer is still lacking. In this regard, this study presents an application of the RH-SAC algorithm on miRNA and mRNA expression data for identification of potential miRNA-mRNA modules. First, a set of miRNA rules was generated using the RH-SAC algorithm. The mRNA targets of the selected miRNAs were identified using the miRTarBase database. Next, the expression values of target mRNAs were used to generate mRNA rules using the RH-SAC. Then all miRNA-mRNA rules have been integrated for generating networks. The RH-SAC algorithm unlike other existing methods selects a group of co-expressed miRNAs and mRNAs that are also differentially expressed. In total 17 miRNAs and 141 mRNAs were selected. The enrichment analysis of selected mRNAs revealed that our method selected mRNAs that are significantly associated with colorectal cancer. We identified novel miRNA/mRNA interactions in colorectal cancer. Through experiment, we could confirm that one of our discovered miRNAs, hsa-miR-93-5p, was significantly up-regulated in 75.8% CRC in comparison to their corresponding non-tumor samples. It could have the potential to examine colorectal cancer subtype specific unique miRNA/mRNA interactions.
9 citations
TL;DR: A novel supervised regularized canonical correlation analysis, termed as CuRSaR, to extract relevant and significant features from multimodal high dimensional omics datasets by maximizing the relevance of extracted features with respect to sample categories and significance among them.
Abstract: Objective: This paper presents a novel supervised regularized canonical correlation analysis, termed as CuRSaR, to extract relevant and significant features from multimodal high dimensional omics datasets. Methods: The proposed method extracts a new set of features from two multidimensional datasets by maximizing the relevance of extracted features with respect to sample categories and significance among them. It integrates judiciously the merits of regularized canonical correlation analysis (RCCA) and rough hypercuboid approach. An analytical formulation, based on spectral decomposition, is introduced to establish the relation between canonical correlation analysis (CCA) and RCCA. The concept of hypercuboid equivalence partition matrix of rough hypercuboid is used to compute both relevance and significance of a feature. Significance: The analytical formulation makes the computational complexity of the proposed algorithm significantly lower than existing methods. The equivalence partition matrix offers an efficient way to find optimum regularization parameters employed in CCA. Results: The superiority of the proposed algorithm over other existing methods, in terms of computational complexity and classification accuracy, is established extensively on real life data.
9 citations
Cites methods from "μHEM for identification of differen..."
...It has been applied successfully to feature selection and clustering [27] as well as to omics data analysis [26]–[30]....
[...]
References
More filters
TL;DR: The proposed algorithm is robust in the sense that it can find overlapping and vaguely defined clusters with arbitrary shapes in noisy environment and is demonstrated on synthetic as well as coding and non-coding RNA expression data sets using some cluster validity indices.
Abstract: Cluster analysis is a technique that divides a given data set into a set of clusters in such a way that two objects from the same cluster are as similar as possible and the objects from different clusters are as dissimilar as possible. In this background, different rough-fuzzy clustering algorithms have been shown to be successful for finding overlapping and vaguely defined clusters. However, the crisp lower approximation of a cluster in existing rough-fuzzy clustering algorithms is usually assumed to be spherical in shape, which restricts to find arbitrary shapes of clusters. In this regard, this paper presents a new rough-fuzzy clustering algorithm, termed as robust rough-fuzzy c-means. Each cluster in the proposed clustering algorithm is represented by a set of three parameters, namely, cluster prototype, a possibilistic fuzzy lower approximation, and a probabilistic fuzzy boundary. The possibilistic lower approximation helps in discovering clusters of various shapes. The cluster prototype depends on the weighting average of the possibilistic lower approximation and probabilistic boundary. The proposed algorithm is robust in the sense that it can find overlapping and vaguely defined clusters with arbitrary shapes in noisy environment. An efficient method is presented, based on Pearson's correlation coefficient, to select initial prototypes of different clusters. A method is also introduced based on cluster validity index to identify optimum values of different parameters of the initialization method and the proposed clustering algorithm. The effectiveness of the proposed algorithm, along with a comparison with other clustering algorithms, is demonstrated on synthetic as well as coding and non-coding RNA expression data sets using some cluster validity indices.
17 citations
"μHEM for identification of differen..." refers methods in this paper
...The theory of rough sets has also been successfully applied to microarray data analysis in [9,24-35]....
[...]
TL;DR: A neural based classifier is applied, Default ARTMAP, to classify broad types of cancers based on their miRNA expression fingerprints and particle swarm optimization (PSO) is used for selecting important miRNAs that contribute to the discrimination of different cancer types.
15 citations
"μHEM for identification of differen..." refers methods in this paper
...[21] used particle swarm optimization technique for selecting important miRNAs that contribute to the discrimination of different cancer types....
[...]
Proceedings Article•
01 Jan 2009TL;DR: In this article, a neural based classifier, Default ARTMAP, was applied to classify broad types of cancers based on their miRNA expression fingerprints, and particle swarm optimization (PSO) was used for selecting important miRNAs that contribute to the discrimination of different cancer types.
Abstract: High-throughput messenger RNA (mRNA) expression profiling with microarray has been demonstrated as a more effective method of cancer diagnosis and treatment than the traditional morphology or clinical parameter based methods. Recently, the discovery of a category of small non-coding RNAs, named microRNAs (miRNAs), provides another promising method of cancer classification. miRNAs play a critical role in the tumorigenic process by functioning either as oncogenes or as tumor suppressors. Here, we apply a neural based classifier, Default ARTMAP, to classify broad types of cancers based on their miRNA expression fingerprints. As the miRNA expression data usually have high dimensionalities, particle swarm optimization (PSO) is used for selecting important miRNAs that contribute to the discrimination of different cancer types. Experimental results on the multiple human cancers show that Default ARTMAP performs consistently well on all the data, and the classification accuracy is better than or comparable to that of the other popular classifiers. Also, the selection of informative miRNAs can further improve the performance of classifiers and provide meaningful insights into cancer researchers.
12 citations
01 Nov 2009
TL;DR: This research combines validated miRNA expression values with imaging features to separate NSCLC brain mets from non-brain mets and identify biomarkers that may indicate possibility of brain mETS.
Abstract: MicroRNAs are small non-coding RNAs of 21-25 nucleotides that might impact regulatory mechanisms in cancer. Due to their influence on cell physiology, alteration of miRNA regulation can be implicated in carcinogenesis and disease progression. In general, one miRNA is predicted to regulate several hundred genes, and as a result, miRNA profiling could serve as a better classifier than gene expression profiling.More than 50% of brain metastasis (brain mets) are associated with non-small cell lung cancer (NSCLC). As miRNAs can regulate certain genes, the presence or absence of certain miRNA could lead to oncogene potential for brain mets. In this study, we combine validated miRNA expression values with imaging features to separate NSCLC brain mets from non-brain mets and identify biomarkers that may indicate possibility of brain mets. This research involves comprehensive miRNA expression profiling, validation of miRNA with qRT-PCR, correlation of miRNA with imaging features such as PET/CT and CT Scan. Eleven statistically significant miRNA were identified and matched with imaging features to yield a class separation of brain mets and non-brain mets.
10 citations
"μHEM for identification of differen..." refers methods in this paper
...The method called significance analysis of microarrays is used in several works [11-16] to identify differentially expressed miRNAs....
[...]
TL;DR: This work focuses on the identification of transcription factor binding sites in promoter regions of potential TF target genes using Gibbs sampling, or heuristics to extend seed oligos, to identify single, relatively well-conserved binding sites.
Abstract: Motivation: Understanding transcriptional regulation is one of the main challenges in computational biology. An important problem is the identification of transcription factor (TF) binding sites in promoter regions of potential TF target genes. It is typically approached by position weight matrix-based motif identification algorithms using Gibbs sampling, or heuristics to extend seed oligos. Such algorithms succeed in identifying single, relatively well-conserved binding sites, but tend to fail when it comes to the identification of combinations of several degenerate binding sites, as those often found in cis-regulatory modules.
Results: We propose a new algorithm that combines the benefits of existing motif finding with the ones of support vector machines (SVMs) to find degenerate motifs in order to improve the modeling of regulatory modules. In experiments on microarray data from Arabidopsis thaliana, we were able to show that the newly developed strategy significantly improves the recognition of TF targets.
Availability: The python source code (open source-licensed under GPL), the data for the experiments and a Galaxy-based web service are available at http://www.fml.mpg.de/raetsch/suppl/kirmes/
Contact: ed.gpm.negnibeut@ibes
Supplementary information: Supplementary data are available at Bioinformatics online.
8 citations