Optimization for Gene Selection and Cancer Classification

Başeğmez, Hülya; Sezer, Emrah; Erol, Çiğdem

doi:10.3390/proceedings2021074021

Cited by 3 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analysis of gene expression data is a great opportunity for individuals with the disease, as treatment becomes easier once the genes most likely cause the disease are identified (Ghosh et al, 2019). It is known from the studies in the literature that the remaining genes after the selection process have higher cancer descriptors (Başeğmez et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

An Application of the Feature Selection Method Based on Pairwise Correlation for Diagnosis of Ovarian Cancer with Machine Learning

Başeğmez

2023

BİİBFAD

View full text Add to dashboard Cite

Many machine learning classification problems have high dimensions, and efficient and effective feature selection algorithms are needed to determine the relatively essential features in the dataset. Gene data is often preferred in feature selection applications because it contains many features due to its structure. In addition, it is known from studies in the literature that gene selection plays a significant role in cancer detection. One of the cancer types with very high treatment success in the early period is ovarian cancer. For this purpose, it was aimed to select genes with high descriptiveness in cancer diagnosis by using the ovarian cancer dataset, which is a publicly available dataset. In this study, the feature selection method based on pairwise correlation, which is very new in the literature, was used for classification. Firstly, a feature selection application was made, and 38 genes with the highest cancer descriptors were determined. Then, the classification process was carried out using eight different classification algorithms. After the classification process, the lowest success was for the Extra Tree classification algorithm (with 96.44% accuracy), while the highest was for the Multi-Layer Perceptron, Stochastic Gradient Descent, Logistic Regression, and Support Vector Machine (with 100% accuracy). Although there are many studies on feature selection in the literature, this study is the first application of the current method. In this sense, it is thought that it will contribute to the literature.

show abstract

Section: Introductionmentioning

confidence: 99%

An Application of the Feature Selection Method Based on Pairwise Correlation for Diagnosis of Ovarian Cancer with Machine Learning

Başeğmez

2023

BİİBFAD

View full text Add to dashboard Cite

show abstract

“…For large biological datasets, Farid et al [52] considered the K-nearest neighbours and decision trees and suggested an adaptive rule classifier. Lyu et al [65] suggested a feature selection technique that uses filters and relies on the Gram-Schmidt orthogonalization approach and the maximum information coefficient. Li et al [66] created data-driven weights for lung cancer classification according to information theory and an overlapping grouping technique.…”

Section: Introductionmentioning

confidence: 99%

Microarray Cancer Data Classification using Deep LearningMethods

Sharath Kumar Y .H.

2023

tjjpt

View full text Add to dashboard Cite

A proposal is made in this paper regarding the deep feed-forward neural network for the microarray binary dataset’s classification. We have used eight binary class standard datasets of microarray cancer used the purpose of validating the suggested approach, specifically cancers of the brain, colon, prostate, leukemia, ovary, lung-Harvard2, lung-Michigan, and breast.In addition, six multiclass microarray datasets namely 3-class Leukemia, 4-class Leukemia,4-class SRBCT, 3-class MLL, 5-class Lung cancer and 11-class Tumor are alsoconsidered.To come out with curse of dimensionality, the method for reducing dimensionality is PCA in binary class dataset’s case. We have crafted architecture of neural network which is fully connected, configuring its parameters with sigmoid initialization for network's input and hidden layer. This includes specifying the number of epochs, batch sizes, and selecting appropriate activation functions. The suggested method's multiclass behavior is made possible by initializing the activation function SoftMax to the output layer. The min-max approach is used for featurescaling.To compute the magnitude of error of the method,binary cross-entropy, and categorical cross-entropy are used on the binary and multi-class datasets and the ADAM optimizer is for optimization.A study is conducted to compare the suggested approach with the most advanced techniques available. According to experimental findings on these common microarray datasets and comparisons with the most advanced technique, the suggested method's performance is quite respectable.

show abstract

A Machine Learning Pipeline for Cancer Detection on Microarray Data: The Role of Feature Discretization and Feature Selection

Nogueira,

Ferreira,

Figueiredo

2023

BioMedInformatics

View full text Add to dashboard Cite

Early disease detection using microarray data is vital for prompt and efficient treatment. However, the intricate nature of these data and the ongoing need for more precise interpretation techniques make it a persistently active research field. Numerous gene expression datasets are publicly available, containing microarray data that reflect the activation status of thousands of genes in patients who may have a specific disease. These datasets encompass a vast number of genes, resulting in high-dimensional feature vectors that present significant challenges for human analysis. Consequently, pinpointing the genes frequently associated with a particular disease becomes a crucial task. In this paper, we present a method capable of determining the frequency with which a gene (feature) is selected for the classification of a specific disease, by incorporating feature discretization and selection techniques into a machine learning pipeline. The experimental results demonstrate high accuracy and a low false negative rate, while significantly reducing the data’s dimensionality in the process. The resulting subsets of genes are manageable for clinical experts, enabling them to verify the presence of a given disease.

show abstract

Optimization for Gene Selection and Cancer Classification

Cited by 3 publications

References 8 publications

An Application of the Feature Selection Method Based on Pairwise Correlation for Diagnosis of Ovarian Cancer with Machine Learning

An Application of the Feature Selection Method Based on Pairwise Correlation for Diagnosis of Ovarian Cancer with Machine Learning

Microarray Cancer Data Classification using Deep LearningMethods

A Machine Learning Pipeline for Cancer Detection on Microarray Data: The Role of Feature Discretization and Feature Selection

Contact Info

Product

Resources

About