Feature Subset Selection for Cancer Classification Using Weight Local Modularity

Zhao, Guodong; Wu, Yan

doi:10.1038/srep34759

Cited by 19 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, our numerical experiments revealed that the prediction performance of RF strongly depended on the input variables ( Figure S4), indicating that feature selection before the RF should be designed carefully. SVM can be used for feature selection 30 . An SVM has been used for breast cancer diagnosis 31 and used with feature selection, such as the use of k-mean clustering, before training of a model 32 .…”

Section: Discussionmentioning

confidence: 99%

Correlation-centred variable selection of a gene expression signature to predict breast cancer metastasis

Hikichi

Sugimoto

Tomita

2020

Sci Rep

View full text Add to dashboard Cite

predictions of distant cancer metastasis based on gene signatures are studied intensively to realise precise diagnosis and treatments. Gene selection i.e. feature selection is a cornerstone to both establish accurate predictions and understand underlying pathologies. Here, we developed a simple but robust feature selection method using a correlation-centred approach to select minimal gene sets that have both high predictive and generalisation abilities. A multiple logistic regression model was used to predict 5-year metastases of patients with breast cancer. Gene expression data obtained from tumour samples of lymph node-negative breast cancer patients were randomly split into training and validation data. Our method selected 12 genes using training data and this showed a higher area under the receiver operating characteristic curve of 0.730 compared with 0.579 yielded by previously reported 76 genes. The signature with the predictive model was validated in an independent dataset, and its higher generalization ability was observed. Gene ontology analyses revealed that our method consistently selected genes with identical functions which frequently selected by the 76 genes. Taken together, our method identifies fewer gene sets bearing high predictive abilities, which would be versatile and applicable to predict other factors such as the outcomes of medical treatments and prognoses of other cancer types. Breast cancer is the most common cancer in women worldwide 1. It is a heterogeneous disease that causes difficulties for its diagnosis and treatment. Thus, multiple clinicopathological factors, such as the tumour size and lymph node metastasis, and established biomarkers, such as the estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2), and progesterone receptor, have been used to characterise specific features of breast cancer, including its subtypes. To realise more accurate characterisation of breast cancer, gene expression has been introduced to understand molecular-level pathology and prediction of treatment outcomes of breast cancer, which would contribute to the design of treatments 2,3. Currently, MammaPrint 4 , Oncotype DX 5 , and MapQuant Dx 6 are commercially available diagnostic tests to accurately estimate the recurrence of breast cancer. These tests employ relatively large numbers of genes, that is, 70, 21, and 97, respectively. Gene expression is also used for metastasis prediction and subtype identification of breast cancers 7-9. The use of gene expression in combination with known biomarkers and clinicopathological factors is considered as a critical issue for precision medicine. There are three processes in the establishment of a prediction model using microarray data: (1) feature selection, (2) development of a mathematical model, and (3) validation of the developed model. The purpose of feature selection is to identify a minimal predictive gene set by removing redundant and irrelevant features 10-12. This process is important because the subsequent analyses depend on the selec...

show abstract

Section: Discussionmentioning

confidence: 99%

Correlation-centred variable selection of a gene expression signature to predict breast cancer metastasis

Hikichi

Sugimoto

Tomita

2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…(i) F-test [72], which is a traditional filter-based gene selection method, it uses the statistical hypothesis testing (ii) RLR [73], which is based on linear discriminant analysis criterion. The class centroid is estimated to define both the between-class separability and the within-class compactness (iii) WLMGS (Weight Local Modularity based Gene Selection) [74], which uses the weight local modularity of a weighted sample graph to evaluate the discriminative power of gene subset (iv) LNNFW [75], which uses the k-nearest neighbors rule to minimize the within-class distances and maximize the between-class distances [20], which is based on subspace learning and manifold regularization (vi) AHEDL [22], which is based on dictionary learning theory with adaptive hypergraph learning and regularization…”

Section: Experimental Settingsmentioning

confidence: 99%

Gene Correlation Guided Gene Selection for Microarray Data Classification

Yang

Zhu

2021

BioMed Research International

View full text Add to dashboard Cite

The microarray cancer data obtained by DNA microarray technology play an important role for cancer prevention, diagnosis, and treatment. However, predicting the different types of tumors is a challenging task since the sample size in microarray data is often small but the dimensionality is very high. Gene selection, which is an effective means, is aimed at mitigating the curse of dimensionality problem and can boost the classification accuracy of microarray data. However, many of previous gene selection methods focus on model design, but neglect the correlation between different genes. In this paper, we introduce a novel unsupervised gene selection method by taking the gene correlation into consideration, named gene correlation guided gene selection (G3CS). Specifically, we calculate the covariance of different gene dimension pairs and embed it into our unsupervised gene selection model to regularize the gene selection coefficient matrix. In such a manner, redundant genes can be effectively excluded. In addition, we utilize a matrix factorization term to exploit the cluster structure of original microarray data to assist the learning process. We design an iterative updating algorithm with convergence guarantee to solve the resultant optimization problem. Experimental results on six publicly available microarray datasets are conducted to validate the efficacy of our proposed method.

show abstract

“…In case of [ 16 ], the genetic algorithm-based feature selection method was applied to improve the decision-making process considering the tissue image of breast cancer patients. To find the set of genes for cancer classification, the quantum-behaved binary particle swarm optimization (BPSO) [ 17 ], the forward search method considering the weight local modularity [ 18 ], and the kernel-based clustering method for gene selection using double radial basis function kernels [ 19 ] were suggested. On the other hand, the identification methods of cancer-driving variants were developed by considering mutation timing of variants [ 20 ] and utilizing the gradient tree boosting and iterative search method [ 21 ].…”

Section: Introductionmentioning

confidence: 99%

Feature selection algorithm based on dual correlation filters for cancer-associated somatic variants

Seo

Cho

2020

BMC Bioinformatics

View full text Add to dashboard Cite

Background Since the development of sequencing technology, an enormous amount of genetic information has been generated, and human cancer analysis using this information is drawing attention. As the effects of variants on human cancer become known, it is important to find cancer-associated variants among countless variants. Results We propose a new filter-based feature selection method applicable for extracting cancer-associated somatic variants considering correlations of data. Both variants associated with the activation and deactivation of cancer’s characteristics are analyzed using dual correlation filters. The multiobjective optimization is utilized to consider two types of variants simultaneously without redundancy. To overcome high computational complexity problem, we calculate the correlation-based weight to select significant variants instead of directly searching for the optimal subset of variants. The proposed algorithm is applied to the identification of melanoma metastasis or breast cancer stage, and the classification results of the proposed method are compared with those of conventional single correlation filter-based method. Conclusions We verified that the proposed dual correlation filter-based method can extract cancer-associated variants related to the characteristics of human cancer.

show abstract

Feature Subset Selection for Cancer Classification Using Weight Local Modularity

Cited by 19 publications

References 42 publications

Correlation-centred variable selection of a gene expression signature to predict breast cancer metastasis

Correlation-centred variable selection of a gene expression signature to predict breast cancer metastasis

Gene Correlation Guided Gene Selection for Microarray Data Classification

Feature selection algorithm based on dual correlation filters for cancer-associated somatic variants

Contact Info

Product

Resources

About