Classification of human cancer diseases by gene expression profiles

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@Article{Salem:2017:ASC,

• author = "Hanaa Salem and Gamal Attiya and Nawal El-Fishawy",
• title = "Classification of human cancer diseases by gene expression profiles",
• journal = "Applied Soft Computing",
• volume = "50",
• pages = "124--134",
• year = "2017",
• ISSN = "1568-4946",
• DOI = "doi:10.1016/j.asoc.2016.11.026",
• URL = "http://www.sciencedirect.com/science/article/pii/S1568494616305956",
• abstract = "A cancers disease in virtually any of its types presents a significant reason behind death surrounding the world. In cancer analysis, classification of varied tumor types is of the greatest importance. Microarray gene expressions datasets investigation has been seemed to provide a successful framework for revising tumor and genetic diseases. Despite the fact that standard machine learning ML strategies have effectively been valuable to realize significant genes and classify category type for new cases, regular limitations of DNA microarray data analysis, for example, the small size of an instance, an incredible feature number, yet reason for limitation its investigative, medical and logical uses. Extending the interpretability of expectation and forecast approaches while holding a great precision would help to analysis genes expression profiles information in DNA microarray dataset all the most reasonable and proficiently. This paper presents a new methodology based on the gene expression profiles to classify human cancer diseases. The proposed methodology combines both Information Gain (IG) and Standard Genetic Algorithm (SGA). It first uses Information Gain for feature selection, then uses Genetic Algorithm (GA) for feature reduction and finally uses Genetic Programming (GP) for cancer types' classification. The suggested system is evaluated by classifying cancer diseases in seven cancer datasets and the results are compared with most latest approaches. The use of proposed system on cancers datasets matching with other machine learning methodologies shows that no classification technique commonly outperforms all the others, however, Genetic Algorithm improve the classification performance of other classifiers generally.",
• keywords = "genetic algorithms, genetic programming, Cancer diagnosis/classification, DNA microarray, Feature selection, Gene expression, Information gain, Machine learning",

}

Genetic Programming entries for Hanaa Salem Gamal Mahrous Ali Attiya Nawal Ahmed El-Fishawy

Citations