A New Combinatorial Optimization Approach for Integrated Feature Selection Using Different Datasets: A Prostate Cancer Transcriptomic Study

Puthiyedth, Nisha; Riveros, Carlos; Berretta, Regina; Moscato, Pablo

doi:10.1371/journal.pone.0127702

Cited by 10 publications

(6 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have recently proposed a combinatorial optimisation based method called Coloured (α,β)- k Feature Set approach [ 48 ] that can handle the integration of datasets in a consistent manner and selects the minimum set of significant features that can differentiate sample pairs across multiple datasets.…”

Section: Methodsmentioning

confidence: 99%

“…The decision versions of the Coloured and Generalised (α,β)- k Feature Set problems are given in [ 48 ] and reproduced below for convenience. Let represent a set of binary values, i.e.…”

Section: Methodsmentioning

confidence: 99%

“…We used the Coloured (α,β)- k Feature Set and Generalised (α,β)- k Feature Set approach [ 48 ] to conduct the combined study. As a robust feature selection method, the Coloured (α,β)- k Feature Set approach can handle the integrated dataset to find the minimum common set of genes that are significant to explain AD across regions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Identification of Differentially Expressed Genes through Integrated Study of Alzheimer’s Disease Affected Brain Regions

et al. 2016

Self Cite

View full text Add to dashboard Cite

BackgroundAlzheimer’s disease (AD) is the most common form of dementia in older adults that damages the brain and results in impaired memory, thinking and behaviour. The identification of differentially expressed genes and related pathways among affected brain regions can provide more information on the mechanisms of AD. In the past decade, several studies have reported many genes that are associated with AD. This wealth of information has become difficult to follow and interpret as most of the results are conflicting. In that case, it is worth doing an integrated study of multiple datasets that helps to increase the total number of samples and the statistical power in detecting biomarkers. In this study, we present an integrated analysis of five different brain region datasets and introduce new genes that warrant further investigation.MethodsThe aim of our study is to apply a novel combinatorial optimisation based meta-analysis approach to identify differentially expressed genes that are associated to AD across brain regions. In this study, microarray gene expression data from 161 samples (74 non-demented controls, 87 AD) from the Entorhinal Cortex (EC), Hippocampus (HIP), Middle temporal gyrus (MTG), Posterior cingulate cortex (PC), Superior frontal gyrus (SFG) and visual cortex (VCX) brain regions were integrated and analysed using our method. The results are then compared to two popular meta-analysis methods, RankProd and GeneMeta, and to what can be obtained by analysing the individual datasets.ResultsWe find genes related with AD that are consistent with existing studies, and new candidate genes not previously related with AD. Our study confirms the up-regualtion of INFAR2 and PTMA along with the down regulation of GPHN, RAB2A, PSMD14 and FGF. Novel genes PSMB2, WNK1, RPL15, SEMA4C, RWDD2A and LARGE are found to be differentially expressed across all brain regions. Further investigation on these genes may provide new insights into the development of AD. In addition, we identified the presence of 23 non-coding features, including four miRNA precursors (miR-7, miR570, miR-1229 and miR-6821), dysregulated across the brain regions. Furthermore, we compared our results with two popular meta-analysis methods RankProd and GeneMeta to validate our findings and performed a sensitivity analysis by removing one dataset at a time to assess the robustness of our results. These new findings may provide new insights into the disease mechanisms and thus make a significant contribution in the near future towards understanding, prevention and cure of AD.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The decision versions of the Coloured and Generalised (α,β)- k Feature Set problems are given in [ 48 ] and reproduced below for convenience. Let represent a set of binary values, i.e.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Identification of Differentially Expressed Genes through Integrated Study of Alzheimer’s Disease Affected Brain Regions

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…Prostate cancer is the second most common cancer among men and it is currently diagnosed around 10,000 men each year and accounts for approximately 2,500 deaths per year. Men with advanced prostate cancer have symptoms like poor stream, lymphoedema, bone pain, etc., and also have systematic advanced cancer prostate symptoms like lethargy, cachexia, and weight loss [1][2]. The main staging and diagnostic investigations utilized for prostate cancer are magnetic resonance imaging, prostate-specific antigen elevation, computed tomography, digital rectal examination, transrectal ultrasonic sound, X-rays, etc.…”

Section: Introductionmentioning

confidence: 99%

Detection of Prostate Cancer Related Genes using Modified Ford-Fulkerson Algorithm in Protein-to-Protein Interaction Network

2019

ijeat

View full text Add to dashboard Cite

Prostate cancer is a malignancy cancer that affects prostate epithelial cells. Presently, prostate cancer is the second leading cause of cancer-related death in men. In this research, a new computational system was proposed for determining the prostate cancer related genes with the shortest path methodology in a Protein to Protein Interaction (PPI) network. Here, a weighted PPI network was constructed on the basis of PPI data from Search Tool for the Retrieval of Interacting Genes/Proteins (STRING) database. Totally, eighteen prostate related genes were extracted from the STRING database by using Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway. Then, the shortest path between eighteen genes was identified using modified Ford-Fulkerson algorithm. Generally, the conventional Ford-Fulkerson algorithm was very effective in detecting the shortest path between the prostate cancer-related genes, but the elapsed time was high when the PPI network has more number of genes. In order to reduce the elapsed time, the modified Ford Fulkerson algorithm was developed by eliminating the invalid path in gene connection. In the experimental section, the proposed shortest path approach reduced the elapsed time up to 0.025-0.002 seconds compared to the existing shortest path methodologies.

show abstract

“…As genomics data, metabolomics data and proteomics data usually contain many features, it has been critical to accurately measure the feature importance and select the most discriminative feature subset. Puthiyedth et al [4] presented a combinatorial optimization approach for integrated feature selection and applied it to analyzing the data about prostate cancer. They have identified potential novel prostate cancer associated pathways and genes.…”

Section: Introductionmentioning

confidence: 99%

Selecting Feature Subsets Based on SVM-RFE and the Overlapping Ratio with Applications in Bioinformatics

Lin

Zhang

et al. 2017

Molecules

View full text Add to dashboard Cite

Feature selection is an important topic in bioinformatics. Defining informative features from complex high dimensional biological data is critical in disease study, drug development, etc. Support vector machine-recursive feature elimination (SVM-RFE) is an efficient feature selection technique that has shown its power in many applications. It ranks the features according to the recursive feature deletion sequence based on SVM. In this study, we propose a method, SVM-RFE-OA, which combines the classification accuracy rate and the average overlapping ratio of the samples to determine the number of features to be selected from the feature rank of SVM-RFE. Meanwhile, to measure the feature weights more accurately, we propose a modified SVM-RFE-OA (M-SVM-RFE-OA) algorithm that temporally screens out the samples lying in a heavy overlapping area in each iteration. The experiments on the eight public biological datasets show that the discriminative ability of the feature subset could be measured more accurately by combining the classification accuracy rate with the average overlapping degree of the samples compared with using the classification accuracy rate alone, and shielding the samples in the overlapping area made the calculation of the feature weights more stable and accurate. The methods proposed in this study can also be used with other RFE techniques to define potential biomarkers from big biological data.

show abstract

A New Combinatorial Optimization Approach for Integrated Feature Selection Using Different Datasets: A Prostate Cancer Transcriptomic Study

Cited by 10 publications

References 98 publications

Identification of Differentially Expressed Genes through Integrated Study of Alzheimer’s Disease Affected Brain Regions

Identification of Differentially Expressed Genes through Integrated Study of Alzheimer’s Disease Affected Brain Regions

Detection of Prostate Cancer Related Genes using Modified Ford-Fulkerson Algorithm in Protein-to-Protein Interaction Network

Selecting Feature Subsets Based on SVM-RFE and the Overlapping Ratio with Applications in Bioinformatics

Contact Info

Product

Resources

About