A stable gene selection in microarray data analysis

Yang, Kun; Cai, Zhipeng; Li, Jianzhong; Lin, Guohui

doi:10.1186/1471-2105-7-228

Cited by 150 publications

(36 citation statements)

References 15 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data for colon, SRBCT, leukemia and melanoma were used as they were. For other datasets, we adopted the technique suggested by Yang et al [15] and Ramaswamy et al [33]. For prostate dataset, floor value of 100 and a ceiling value of 16000 with a variation of the Max / Min ratio as 5 and Max-Min difference of 50 were used to filter the values.…”

Section: Experimental Setup and Datasetmentioning

confidence: 99%

“…Using the filter feature selection approach, many algorithms were proposed such as Relief [11], Relief-F [12], FOCUS, FOCUS-2 [13], Correlation based feature selection (CFS) [14], Fast Correlation based feature selection FCBS [8], FAST [6]. Algorithm by Yang et al [15] removes irrelevant features based on gene ranking methods of GS1 and GS2.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Feature Selection Approach Based on GRASP for Cancer Microarray Data

Nagpal

Gaur

2017

CIT

View full text Add to dashboard Cite

Microarray data usually contain a large number of genes, but a small number of samples. Feature subset selection for microarray data aims at reducing the number of genes so that useful information can be extracted from the samples. Reducing the dimension of data sets further helps in improving the computational efficiency of the learning model. In this paper, we propose a modified algorithm based on the tabu search as local search procedures to a Greedy Randomized Adaptive Search Procedure (GRASP) for high dimensional microarray data sets. The proposed Tabu based Greedy Randomized Adaptive Search Procedure algorithm is named as TGRASP. In TGRASP, a new parameter has been introduced named as Tabu Tenure and the existing parameters, NumIter and size have been modified. We observed that different parameter settings affect the quality of the optimum. The second proposed algorithm known as FFGRASP (Firefly Greedy Randomized Adaptive Search Procedure) uses a firefly optimization algorithm in the local search optimization phase of the greedy randomized adaptive search procedure (GRASP). Firefly algorithm is one of the powerful algorithms for optimization of multimodal applications. Experimental results show that the proposed TGRASP and FFGRASP algorithms are much better than existing algorithm with respect to three performance parameters viz. accuracy, run time, number of a selected subset of features. We have also compared both the approaches with a unified metric (Extended Adjusted Ratio of Ratios) which has shown that TGRASP approach outperforms existing approach for six out of nine cancer microarray datasets and FF-GRASP performs better on seven out of nine datasets.

show abstract

Section: Experimental Setup and Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hybrid Feature Selection Approach Based on GRASP for Cancer Microarray Data

Nagpal

Gaur

2017

CIT

View full text Add to dashboard Cite

show abstract

“…Many recent works have been conducted in identifying the discriminatory subset of genes. For example, Cho et al [24] apply the mean and standard deviation of the distances from each sample to the class center as criteria for classification; Yang et al [25] improve the method in [24] and bring inter-class variations into the algorithm; Cai et al [26] propose the clustered gene selection, which groups the genes via k -means clustering and picks up the top genes in each group that are closest to the centroid locations. These methods are simple and effective in some cases, but their heuristics are designed for continuous gene expression data, and are not directly applicable to discrete, and especially binary point mutation data.…”

Section: Introductionmentioning

confidence: 99%

DeepGene: an advanced cancer type classifier based on deep learning and somatic point mutations

et al. 2016

View full text Add to dashboard Cite

BackgroundWith the developments of DNA sequencing technology, large amounts of sequencing data have become available in recent years and provide unprecedented opportunities for advanced association studies between somatic point mutations and cancer types/subtypes, which may contribute to more accurate somatic point mutation based cancer classification (SMCC). However in existing SMCC methods, issues like high data sparsity, small volume of sample size, and the application of simple linear classifiers, are major obstacles in improving the classification performance.ResultsTo address the obstacles in existing SMCC studies, we propose DeepGene, an advanced deep neural network (DNN) based classifier, that consists of three steps: firstly, the clustered gene filtering (CGF) concentrates the gene data by mutation occurrence frequency, filtering out the majority of irrelevant genes; secondly, the indexed sparsity reduction (ISR) converts the gene data into indexes of its non-zero elements, thereby significantly suppressing the impact of data sparsity; finally, the data after CGF and ISR is fed into a DNN classifier, which extracts high-level features for accurate classification. Experimental results on our curated TCGA-DeepGene dataset, which is a reformulated subset of the TCGA dataset containing 12 selected types of cancer, show that CGF, ISR and DNN all contribute in improving the overall classification performance. We further compare DeepGene with three widely adopted classifiers and demonstrate that DeepGene has at least 24% performance improvement in terms of testing accuracy.ConclusionsBased on deep learning and somatic point mutation data, we devise DeepGene, an advanced cancer type classifier, which addresses the obstacles in existing SMCC studies. Experiments indicate that DeepGene outperforms three widely adopted existing classifiers, which is mainly attributed to its deep learning module that is able to extract the high level features between combinatorial somatic point mutations and cancer types.

show abstract

“…For application purposes, these gene expression data must then be classified into various categories [2]. Together with classification methods, microarray technology has successfully guided clinical management decisions for individual patients, such as oncology [3, 4]. However, the sample size of the genetic dataset is usually much smaller than the number of genes, which extends into thousands or even tens of thousands [5].…”

Section: Introductionmentioning

confidence: 99%

Optimal combination of feature selection and classification via local hyperplane based learning strategy

et al. 2015

View full text Add to dashboard Cite

BackgroundClassifying cancers by gene selection is among the most important and challenging procedures in biomedicine. A major challenge is to design an effective method that eliminates irrelevant, redundant, or noisy genes from the classification, while retaining all of the highly discriminative genes.ResultsWe propose a gene selection method, called local hyperplane-based discriminant analysis (LHDA). LHDA adopts two central ideas. First, it uses a local approximation rather than global measurement; second, it embeds a recently reported classification model, K-Local Hyperplane Distance Nearest Neighbor(HKNN) classifier, into its discriminator. Through classification accuracy-based iterations, LHDA obtains the feature weight vector and finally extracts the optimal feature subset. The performance of the proposed method is evaluated in extensive experiments on synthetic and real microarray benchmark datasets. Eight classical feature selection methods, four classification models and two popular embedded learning schemes, including k-nearest neighbor (KNN), hyperplane k-nearest neighbor (HKNN), Support Vector Machine (SVM) and Random Forest are employed for comparisons.ConclusionThe proposed method yielded comparable to or superior performances to seven state-of-the-art models. The nice performance demonstrate the superiority of combining feature weighting with model learning into an unified framework to achieve the two tasks simultaneously.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-015-0629-6) contains supplementary material, which is available to authorized users.

show abstract

A stable gene selection in microarray data analysis

Cited by 150 publications

References 15 publications

Hybrid Feature Selection Approach Based on GRASP for Cancer Microarray Data

Hybrid Feature Selection Approach Based on GRASP for Cancer Microarray Data

DeepGene: an advanced cancer type classifier based on deep learning and somatic point mutations

Optimal combination of feature selection and classification via local hyperplane based learning strategy

Contact Info

Product

Resources

About