A Distributed Feature Selection Algorithm Based on Distance Correlation with an Application to Microarrays

Cancer classification in high dimensional microarray gene expressions by feature selection using eagle prey optimization

Microarray gene expression data have emerged as powerful tools in cancer classification and diagnosis. However, the high dimensionality of these datasets presents significant challenges for feature selection, leading to the development of various computational methods. In this paper, we utilized the Eagle Prey Optimization (EPO), a novel genetically inspired approach for microarray gene selection in cancer classification. EPO draws inspiration from the remarkable hunting strategies of eagles, which exhibit unparalleled precision and efficiency in capturing prey. Similarly, our algorithm aims to identify a small subset of informative genes that can discriminate between cancer subtypes with high accuracy and minimal redundancy. To achieve this, EPO employs a combination of genetic mutation operator with EPO fitness function, to evolve a population of potential gene subsets over multiple generations. The key innovation of EPO lies in its incorporation of a fitness function specifically designed for cancer classification tasks. This function considers not only the discriminative power of selected genes but also their diversity and redundancy, ensuring the creation of compact and informative gene subsets. Moreover, EPO incorporates a mechanism for adaptive mutation rates, allowing the algorithm to explore the search space efficiently. To validate the effectiveness of EPO, extensive experiments were conducted on several publicly available microarray datasets representing different cancer types. Comparative analysis with state-of-the-art gene selection algorithms demonstrates that EPO consistently outperforms these methods in terms of classification accuracy, dimensionality reduction, and robustness to noise.

The γ-OMP Algorithm for Feature Selection With Application to Gene Expression Data

Feature selection for predictive analytics is the problem of identifying a minimal-size subset of features that is maximally predictive of an outcome of interest. To apply to molecular data, feature selection algorithms need to be scalable to tens of thousands of features. In this paper, we propose γ-OMP, a generalisation of the highly-scalable Orthogonal Matching Pursuit feature selection algorithm. γ-OMP can handle (a)various types of outcomes, such as continuous, binary, nominal, time-to-event, (b)discrete (categorical)features, (c)different statistical-based stopping criteria, (d)several predictive models (e.g., linear or logistic regression), (e)various types of residuals, and (f)different types of association. We compare γ-OMP against LASSO, a prototypical, widely used algorithm for high-dimensional data. On both simulated data and several real gene expression datasets, γ-OMP is on par, or outperforms LASSO in binary classification (case-control data), regression (quantified outcomes), and time-to-event data (censored survival times). γ-OMP is based on simple statistical ideas, it is easy to implement and to extend, and our extensive evaluation shows that it is also effective in bioinformatics analysis settings.

Use of radiomics based on 18F-FDG PET/CT and machine learning methods to aid clinical decision-making in the classification of solitary pulmonary lesions: an innovative approach

PURPOSE

This study was designed and performed to assess the ability of ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography (PET) and computed tomography (CT) radiomics features combined with machine learning methods to differentiate between primary and metastatic lung lesions and to classify histological subtypes. Moreover, we identified the optimal machine learning method.

METHODS

A total of 769 patients pathologically diagnosed with primary or metastatic lung cancers were enrolled. We used the LIFEx package to extract radiological features from semiautomatically segmented PET and CT images within the same volume of interest. Patients were randomly distributed in training and validation sets. Through the evaluation of five feature selection methods and nine classification methods, discriminant models were established. The robustness of the procedure was controlled by tenfold cross-validation. The model's performance was evaluated using the area under the receiver operating characteristic curve (AUC).

RESULTS

Based on the radiomics features extracted from PET and CT images, forty-five discriminative models were established. Combined with appropriate feature selection methods, most classifiers showed excellent discriminative ability with AUCs greater than 0.75. In the differentiation between primary and metastatic lung lesions, the feature selection method gradient boosting decision tree (GBDT) combined with the classifier GBDT achieved the highest classification AUC of 0.983 in the PET dataset. In contrast, the feature selection method eXtreme gradient boosting combined with the classifier random forest (RF) achieved the highest AUC of 0.828 in the CT dataset. In the discrimination between squamous cell carcinoma and adenocarcinoma, the combination of GBDT feature selection method with GBDT classification had the highest AUC of 0.897 in the PET dataset. In contrast, the combination of the GBDT feature selection method with the RF classification had the highest AUC of 0.839 in the CT dataset. Most of the decision tree (DT)-based models were overfitted, suggesting that the classification method was not appropriate for practical application.

CONCLUSION

¹⁸F-FDG PET/CT radiomics features combined with machine learning methods can distinguish between primary and metastatic lung lesions and identify histological subtypes in lung cancer. GBDT and RF were considered optimal classification methods for the PET and CT datasets, respectively, and GBDT was considered the optimal feature selection method in our analysis.

Paperboard Coating Detection Based on Full-Stokes Imaging Polarimetry

The manufacturing of high-quality extruded low-density polyethylene (PE) paperboard intended for the food packaging industry relies on manual, intrusive, and destructive off-line inspection by the process operators to assess the overall quality and functionality of the product. Defects such as cracks, pinholes, and local thickness variations in the coating can occur at any location in the reel, affecting the sealable property of the product. To detect these defects locally, imaging systems must discriminate between the substrate and the coating. We propose an active full-Stokes imaging polarimetry for the classification of the PE-coated paperboard and its substrate (before applying the PE coating) from industrially manufactured samples. The optical system is based on vertically polarized illumination and a novel full-Stokes imaging polarimetry camera system. From the various parameters obtained by polarimetry measurements, we propose implementing feature selection based on the distance correlation statistical method and, subsequently, the implementation of a support vector machine algorithm that uses a nonlinear Gaussian kernel function. Our implementation achieves 99.74% classification accuracy. An imaging polarimetry system with high spatial resolution and pixel-wise metrological characteristics to provide polarization information, capable of material classification, can be used for in-process control of manufacturing coated paperboard.

An Efficient hybrid filter-wrapper metaheuristic-based gene selection method for high dimensional datasets

Feature selection problem is one of the most significant issues in data classification. The purpose of feature selection is selection of the least number of features in order to increase accuracy and decrease the cost of data classification. In recent years, due to appearance of high-dimensional datasets with low number of samples, classification models have encountered over-fitting problem. Therefore, the need for feature selection methods that are used to remove the extensions and irrelevant features is felt. Recently, although, various methods have been proposed for selecting the optimal subset of features with high precision, these methods have encountered some problems such as instability, high convergence time, selection of a semi-optimal solution as the final result. In other words, they have not been able to fully extract the effective features. In this paper, a hybrid method based on the IWSSr method and Shuffled Frog Leaping Algorithm (SFLA) is proposed to select effective features in a large-scale gene dataset. The proposed algorithm is implemented in two phases: filtering and wrapping. In the filter phase, the Relief method is used for weighting features. Then, in the wrapping phase, by using the SFLA and the IWSSr algorithms, the search for effective features in a feature-rich area is performed. The proposed method is evaluated by using some standard gene expression datasets. The experimental results approve that the proposed approach in comparison to similar methods, has been achieved a more compact set of features along with high accuracy. The source code and testing datasets are available at https://github.com/jimy2020/SFLA_IWSSr-Feature-Selection.