Dataset Information

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

ABSTRACT:

Background

The joint study of multiple datasets has become a common technique for increasing statistical power in detecting biomarkers obtained from smaller studies. The approach generally followed is based on the fact that as the total number of samples increases, we expect to have greater power to detect associations of interest. This methodology has been applied to genome-wide association and transcriptomic studies due to the availability of datasets in the public domain. While this approach is well established in biostatistics, the introduction of new combinatorial optimization models to address this issue has not been explored in depth. In this study, we introduce a new model for the integration of multiple datasets and we show its application in transcriptomics.

Methods

We propose a new combinatorial optimization problem that addresses the core issue of biomarker detection in integrated datasets. Optimal solutions for this model deliver a feature selection from a panel of prospective biomarkers. The model we propose is a generalised version of the (?,?)-k-Feature Set problem. We illustrate the performance of this new methodology via a challenging meta-analysis task involving six prostate cancer microarray datasets. The results are then compared to the popular RankProd meta-analysis tool and to what can be obtained by analysing the individual datasets by statistical and combinatorial methods alone.

Results

Application of the integrated method resulted in a more informative signature than the rank-based meta-analysis or individual dataset results, and overcomes problems arising from real world datasets. The set of genes identified is highly significant in the context of prostate cancer. The method used does not rely on homogenisation or transformation of values to a common scale, and at the same time is able to capture markers associated with subgroups of the disease.

SUBMITTER: Puthiyedth N

PROVIDER: S-EPMC4480358 | biostudies-literature | 2015

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Puthiyedth Nisha N Riveros Carlos C Berretta Regina R Moscato Pablo P

PloS one 20150624 6

<h4>Background</h4>The joint study of multiple datasets has become a common technique for increasing statistical power in detecting biomarkers obtained from smaller studies. The approach generally followed is based on the fact that as the total number of samples increases, we expect to have greater power to detect associations of interest. This methodology has been applied to genome-wide association and transcriptomic studies due to the availability of datasets in the public domain. While this a ...[more]

PMID: 26106884

Similar Datasets

Project description:Existing feature selection methods typically do not consider prior knowledge in the form of structural relationships among features. In this study, the features are structured based on prior knowledge into groups. The problem addressed in this article is how to select one representative feature from each group such that the selected features are jointly discriminating the classes. The problem is formulated as a binary constrained optimization and the combinatorial optimization is relaxed as a convex-concave problem, which is then transformed into a sequence of convex optimization problems so that the problem can be solved by any standard optimization algorithm. Moreover, a block coordinate gradient descent optimization algorithm is proposed for high dimensional feature selection, which in our experiments was four times faster than using a standard optimization algorithm.In order to test the effectiveness of the proposed formulation, we used microarray analysis as a case study, where genes with similar expressions or similar molecular functions were grouped together. In particular, the proposed block coordinate gradient descent feature selection method is evaluated on five benchmark microarray gene expression datasets and evidence is provided that the proposed method gives more accurate results than the state-of-the-art gene selection methods. Out of 25 experiments, the proposed method achieved the highest average AUC in 13 experiments while the other methods achieved higher average AUC in no more than 6 experiments.A method is developed to select a feature from each group. When the features are grouped based on similarity in gene expression, we showed that the proposed algorithm is more accurate than state-of-the-art gene selection methods that are particularly developed to select highly discriminative and less redundant genes. In addition, the proposed method can exploit any grouping structure among features, while alternative methods are restricted to using similarity based grouping.

Project description:INTRODUCTION: Breast cancer is a complex heterogeneous disease for which a substantial resource of transcriptomic data is available. Gene expression data have facilitated the division of breast cancer into, at least, five molecular subtypes, namely luminal A, luminal B, HER2, normal-like and basal. Once identified, breast cancer subtypes can inform clinical decisions surrounding patient treatment and prognosis. Indeed, it is important to identify patients at risk of developing aggressive disease so as to tailor the level of clinical intervention. METHODS: We have developed a user-friendly, web-based system to allow the evaluation of genes/microRNAs (miRNAs) that are significantly associated with survival in breast cancer and its molecular subtypes. The algorithm combines gene expression data from multiple microarray experiments which frequently also contain miRNA expression information, and detailed clinical data to correlate outcome with gene/miRNA expression levels. This algorithm integrates gene expression and survival data from 26 datasets on 12 different microarray platforms corresponding to approximately 17,000 genes in up to 4,738 samples. In addition, the prognostic potential of 341 miRNAs can be analysed. RESULTS: We demonstrated the robustness of our approach in comparison to two commercially available prognostic tests, oncotype DX and MammaPrint. Our algorithm complements these prognostic tests and is consistent with their findings. In addition, BreastMark can act as a powerful reductionist approach to these more complex gene signatures, eliminating superfluous genes, potentially reducing the cost and complexity of these multi-index assays. Known miRNA prognostic markers, mir-205 and mir-93, were used to confirm the prognostic value of this tool in a miRNA setting. We also applied the algorithm to examine expression of 58 receptor tyrosine kinases in the basal-like subtype, identifying six receptor tyrosine kinases associated with poor disease-free survival and/or overall survival (EPHA5, FGFR1, FGFR3, VEGFR1, PDGFR?, and TIE1). A web application for using this algorithm is currently available. CONCLUSIONS: BreastMark is a powerful tool for examining putative gene/miRNA prognostic markers in breast cancer. The value of this tool will be in the preliminary assessment of putative biomarkers in breast cancer. It will be of particular use to research groups with limited bioinformatics facilities.

Dataset Information

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

Background

Methods

Results

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets