A hybrid of clustering and quantum genetic algorithm for relevant genes selection for cancer microarray data

Sardana, Manju; Agrawal, R. K.; Kaur, Baljeet

doi:10.3233/kes-160341

Cited by 7 publications

(3 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One or more features from each clusters are eventually chosen to form the final subset. Various clustering methods and diverse techniques that studies the outcomes (features) of each clusters were proposed (Nguyen, Xue, Liu, & Zhang, 2014;Sardana, Agrawal, & Kaur, 2016).…”

Section: Feature Clusteringmentioning

confidence: 99%

Feature Clustering for Pso-Based Feature Construction on High-Dimensional Data

Swesi

Bakar²

2019

Journal of Information and Communication Technology

View full text Add to dashboard Cite

Feature construction (FC) refers to a process that uses the original features to construct new features with better discrimination ability. Particle Swarm Optimisation (PSO) is an effective search technique that has been successfully utilised in FC. However, the application of PSO for feature construction using high dimensional data has been a challenge due to its large search space and high computational cost. Moreover, unnecessary features that were irrelevant, redundant and contained noise were constructed when PSO was applied to the whole feature. Therefore, the main purpose of this paper is to select the most informative features and construct new features from the selected features for a better classification performance. The feature clustering methods were used to aggregate similar features into clusters, whereby the dimensionality of the data was lowered by choosing representative features from every cluster to form the final feature subset. The clustering of each features are proven to be accurate in feature selection (FS), however, only one study investigated its application in FC for classification. The study identified some limitations, such as the implementation of only two binary classes and the decreasing accuracy of the data. This paper proposes a cluster based PSO feature construction approach called ClusPSOFC. The Redundancy-Based Feature Clustering (RFC) algorithm was applied to choose the most informative

show abstract

Section: Feature Clusteringmentioning

confidence: 99%

Feature Clustering for Pso-Based Feature Construction on High-Dimensional Data

Swesi

Bakar²

2019

Journal of Information and Communication Technology

View full text Add to dashboard Cite

show abstract

“…In 2011, Zhang [20] proposed a quantum clone GA which introduced quantum whole interference crossover and the information was spread in the whole population. In 2016, Sardana et al [21] proposed a hybrid approach, cluster QGA, that used clustering to select a small set of non-redundant representative genes and then applied QGA to determine a minimal set of relevant and non-redundant genes. Also a new fitness function was proposed to reduce number of genes without sacrificing the classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

An improved multiple populations quantum genetic algorithm

Niu¹,

Ma²

2022

Laser Phys. Lett.

View full text Add to dashboard Cite

With the in-depth study of quantum genetic algorithm (QGA), the defect of premature convergence limits its development more and more. In order to further improve QGA, we propose an improved QGA based on multi population (IQGA). In the process of population initialization in IQGA, we generate multiple populations to avoid a single population falling into a local optimal value. We also abandon the fixed angle used by the traditional quantum revolving gate, and design a strategy to adjust the angle adaptively according to the difference from the optimal solution. In addition, we introduce a population catastrophe strategy to deal with the premature convergence of each population. The populations are connected based on migration operation, and the optimal solution of each population obtained by each iteration is collected in the elite group. A series of simulation experiments show that our improvement strategies of IQGA are effective.

show abstract

“…Since the high-dimensional gene expression data is difficult to handle, feature extraction [28] lies at the core of supervised learning approaches dealing with gene expression data. Several researchers have used statistical measures such as variance analysis, Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), T-distributed Stochastic Neighbor Embedding (T-SNE), decision tree, and pathways based analysis for the dimensionality reduction.…”

Section: Introductionmentioning

confidence: 99%

Triphasic DeepBRCA-A Deep Learning-Based Framework for Identification of Biomarkers for Breast Cancer Stratification

et al. 2021

View full text Add to dashboard Cite

Breast cancer being major death-leading cancer demands utmost attention. Recently, the nextgeneration sequencing techniques capable of capturing gene expression data have been used successfully for the detection of breast cancer. The proposed work identifies a small set of biomarker genes for molecular stratification of breast cancer subtypes. In this work, we have proposed Triphasic DeepBRCA -a novel deep learning framework, for breast cancer subtype detection and biomarker discovery. In the first phase, an autoencoder is used for extracting a compact representation of the gene expression data which is provided as an input to a supervised feed-forward neural network for classification of breast cancer subtypes in the second phase. In the third phase, the proposed Biomarker Gene Discovery Algorithm (BGDA) leverages the neural network classifier of the second phase to estimate the relevance of various genes. Next, Wilcoxon rank-sum test with False Discovery Rate (FDR) Correction is applied to identify the most differentiating genes. Using the TCGA BRCA RNASeq data, the proposed framework enabled us to discover a set of 54 most-variant genes. Using 10-fold cross-validation, we obtained a mean accuracy of 0.899 ± 0.04 at 95% confidence interval. We also validated our results on METABRIC dataset. Gene Set Analysis revealed statistically enriched pathways. Heatmap of the expression levels and t-SNE visualization reveals that these genes have an aggregated capability to distinguish amongst the different breast cancer subtypes. Further, the prognostic evaluation using 54 biomarkers revealed that over 30 genes out of 54 are significantly linked to the prognostic outcome.

show abstract

A hybrid of clustering and quantum genetic algorithm for relevant genes selection for cancer microarray data

Cited by 7 publications

References 48 publications

Feature Clustering for Pso-Based Feature Construction on High-Dimensional Data

Feature Clustering for Pso-Based Feature Construction on High-Dimensional Data

An improved multiple populations quantum genetic algorithm

Triphasic DeepBRCA-A Deep Learning-Based Framework for Identification of Biomarkers for Breast Cancer Stratification

Contact Info

Product

Resources

About