Robust integrated framework for effective feature selection and sample classification and its application to gene expression data analysis

Gao, Shang; Addam, Omar; Qabaja, Ala; ElSheikh, Abdallah M.; Zarour, Omar; Nagi, Mohamad; Triant, Flouris; Almansoori, Wadhah; Ozyer, Omer Sair Tansel; Zeng, Jia; Rokne, Jon G.; Alhajja, Reda

doi:10.1109/cibcb.2012.6217219

Cited by 5 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, SVM with a polynomial kernal

(γ = \frac{1}{number of classes}, degree = 3)

achieved a higher classification accuracy than k-nearest neighbor and Naïve Bayes classifiers [46]. Similarly, classification based on SVM with radial basis ( γ = 0.02, penalty parameter C = 50) and linear (penalty parameter C = 50) kernels has demonstrated to achieve high classification accuracy on many different (leukemia, colon, prostate, lung, and breast) cancer datasets [47, 48]. Finally, ensemble of SVMs has also been applied to classify cancer samples.…”

Section: Classification Methodsmentioning

confidence: 99%

A Classification Framework Applied to Cancer Gene Expression Profiles

Hijazi

Chan

2013

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Classification of cancer based on gene expression has provided insight into possible treatment strategies. Thus, developing machine learning methods that can successfully distinguish among cancer subtypes or normal versus cancer samples is important. This work discusses supervised learning techniques that have been employed to classify cancers. Furthermore, a two-step feature selection method based on an attribute estimation method (e.g., ReliefF) and a genetic algorithm was employed to find a set of genes that can best differentiate between cancer subtypes or normal versus cancer samples. The application of different classification methods (e.g., decision tree, k-nearest neighbor, support vector machine (SVM), bagging, and random forest) on 5 cancer datasets shows that no classification method universally outperforms all the others. However, k-nearest neighbor and linear SVM generally improve the classification performance over other classifiers. Finally, incorporating diverse types of genomic data (e.g., protein-protein interaction data and gene expression) increase the prediction accuracy as compared to using gene expression alone.

show abstract

“…Additionally, SVM with a polynomial kernal

(γ = \frac{1}{number of classes}, degree = 3)

Section: Classification Methodsmentioning

confidence: 99%

A Classification Framework Applied to Cancer Gene Expression Profiles

Hijazi

Chan

2013

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…Shang Gao, Omar Addam and colleagues in [10] proposed these two feature reduction techniques. The proposed clustering based method uses Genetic Algorithm (GA) based clustering approach.…”

Section: Clustering Based and Network Analysis Based Methodsmentioning

confidence: 99%

A Comparative Study of Microarray Data Analysis for Cancer Classification

Chitode¹,

Nagori²

2013

IJCA

View full text Add to dashboard Cite

Cancer is most deadly human disease. According to WHO 7.6 million deaths (around 13% of all deaths) in 2008 were caused by cancer. A Cancer diagnosis can be achieved with gene expression microarray data. Microarray allows monitoring of thousands of genes of a sample simultaneously. But all the genes in gene expression data are not informative. The relevant gene selection/extraction is the main challenge in microarray data analysis. Microarray data classification is two stage process i.e. features selection and classification. Feature selection techniques are used to extract a small subset of relevant genes without degrading the performance of classifier. The classifier uses these extracted relevant genes for cancer classification. In this review paper there is a comparative study of the feature selection and classification techniques. The evaluation criteria are applied to find out the best combination of feature selection and classification technique for accurate cancer classification General TermsCancer classification

show abstract

Color-based Fuzzy Classifier for automated detection of cancerous cells in histopathological analysis

Qidwai

Sadia

2014

2014 IEEE Conference on Biomedical Engineering and Sciences (IECBES)

View full text Add to dashboard Cite

Robust integrated framework for effective feature selection and sample classification and its application to gene expression data analysis

Cited by 5 publications

References 31 publications

A Classification Framework Applied to Cancer Gene Expression Profiles

A Classification Framework Applied to Cancer Gene Expression Profiles

A Comparative Study of Microarray Data Analysis for Cancer Classification

Color-based Fuzzy Classifier for automated detection of cancerous cells in histopathological analysis

Contact Info

Product

Resources

About