Research about feature genes selection for cancer type identification based on gene expression profiles

The domestication of animals has generated a set of phenotypic modifications, affecting behaviour, appearance, physiology and reproduction, which are consistent across a range of species. We hypothesized that some of these phenotypes could have evolved because of genetic correlation to tameness, an essential trait for successful domestication. Starting from an outbred population of red junglefowl, ancestor of all domestic chickens, we selected birds for either high or low fear of humans for five generations. Birds from the fifth selected generation (S 5 ) showed a divergent pattern of growth and reproduction, where low fear chickens grew larger and produced larger offspring. To examine underlying genetic mechanisms, we used microarrays to study gene expression in thalamus/hypothalamus, a brain region involved in fear and stress, in both the parental generation and the S 5 . While parents of the selection lines did not show any differentially expressed genes, there were a total of 33 genes with adjusted p -values below 0.1 in S 5 . These were mainly related to sperm-function, immunological functions, with only a few known to be relevant to behaviour. Hence, five generations of divergent selection for fear of humans produced changes in hypothalamic gene expression profiles related to pathways associated with male reproduction and to immunology. This may be linked to the effects seen on growth and size of offspring. These results support the hypothesis that domesticated phenotypes may evolve because of correlated effects related to reduced fear of humans.

Download Full-text

Breast and Colon Cancer Classification from Gene Expression Profiles Using Data Mining Techniques

10.20944/preprints202002.0324.v1 ◽

2020 ◽

Cited By ~ 1

Author(s):

Mohamed Loey ◽

Mohammed Wajeeh Jasim ◽

Hazem M. EL-Bakry ◽

Mohamed Hamed N. Taha ◽

Nour Eldeen M. Khalifa

Keyword(s):

Gene Expression ◽

Classification Accuracy ◽

Information Gain ◽

Expression Profiles ◽

Gene Expression Profiles ◽

Disease Diagnosis ◽

Performance Measure ◽

Support Vector ◽

Svm Classifier ◽

Cancer Type

Early detection of cancer increases the probability of recovery. This paper presents an intelligent decision support system (IDSS) for the early diagnosis of cancer based on gene expression profiles collected using DNA microarrays. Such datasets pose a challenge because of the small number of samples (no more than a few hundred) relative to the large number of genes (on the order of thousands). Therefore, a method of reducing the number of features (genes) that are not relevant to the disease of interest is necessary to avoid overfitting. The proposed methodology uses the information gain (IG) to select the most important features from the input patterns. Then, the selected features (genes) are reduced by applying the grey wolf optimization (GWO) algorithm. Finally, the methodology employs a support vector machine (SVM) classifier for cancer type classification. The proposed methodology was applied to two datasets (Breast and Colon) and was evaluated based on its classification accuracy, which is the most important performance measure in disease diagnosis. The experimental results indicate that the proposed methodology is able to enhance the stability of the classification accuracy as well as the feature selection

Download Full-text

Chaotic Harmony Search based Multi-objective Feature Selection for Classification of Gene Expression Profiles

2021 IEEE 9th International Conference on Bioinformatics and Computational Biology (ICBCB) ◽

10.1109/icbcb52223.2021.9459222 ◽

2021 ◽

Author(s):

Aiguo Wang ◽

Huancheng Liu ◽

Guilin Chen

Keyword(s):

Gene Expression ◽

Feature Selection ◽

Expression Profiles ◽

Harmony Search ◽

Gene Expression Profiles ◽

Multi Objective ◽

Selection For

Download Full-text

Breast and Colon Cancer Classification from Gene Expression Profiles Using Data Mining Techniques

Symmetry ◽

10.3390/sym12030408 ◽

2020 ◽

Vol 12 (3) ◽

pp. 408 ◽

Cited By ~ 3

Author(s):

Mohamed Loey Ramadan AbdElNabi ◽

Mohammed Wajeeh Jasim ◽

Hazem M. EL-Bakry ◽

Mohamed Hamed N. Taha ◽

Nour Eldeen M. Khalifa

Keyword(s):

Gene Expression ◽

Classification Accuracy ◽

Information Gain ◽

Expression Profiles ◽

Gene Expression Profiles ◽

Disease Diagnosis ◽

Performance Measure ◽

Support Vector ◽

Svm Classifier ◽

Cancer Type

Early detection of cancer increases the probability of recovery. This paper presents an intelligent decision support system (IDSS) for the early diagnosis of cancer based on gene expression profiles collected using DNA microarrays. Such datasets pose a challenge because of the small number of samples (no more than a few hundred) relative to the large number of genes (in the order of thousands). Therefore, a method of reducing the number of features (genes) that are not relevant to the disease of interest is necessary to avoid overfitting. The proposed methodology uses the information gain (IG) to select the most important features from the input patterns. Then, the selected features (genes) are reduced by applying the grey wolf optimization (GWO) algorithm. Finally, the methodology employs a support vector machine (SVM) classifier for cancer type classification. The proposed methodology was applied to two datasets (Breast and Colon) and was evaluated based on its classification accuracy, which is the most important performance measure in disease diagnosis. The experimental results indicate that the proposed methodology is able to enhance the stability of the classification accuracy as well as the feature selection.

Download Full-text