A feature selection method for classification within functional genomics experiments based on the proportional overlapping score

An intelligent dynamic cyber physical system threat detection system for ensuring secured communication in 6G autonomous vehicle networks

Smart cities have developed advanced technology that improves people's lives. A collaboration of smart cities with autonomous vehicles shows the development towards a more advanced future. Cyber-physical system (CPS) are used blend the cyber and physical world, combined with electronic and mechanical systems, Autonomous vehicles (AVs) provide an ideal model of CPS. The integration of 6G technology with Autonomous Vehicles (AVs) marks a significant advancement in Intelligent Transportation Systems (ITS), offering enhanced self-sufficiency, intelligence, and effectiveness. Autonomous vehicles rely on a complex network of sensors, cameras, and software to operate. A cyber-attack could interfere with these systems, leading to accidents, injuries, or fatalities. Autonomous vehicles are often connected to broader transportation networks and infrastructure. A successful cyber-attack could disrupt not only individual vehicles but also public transportation systems, causing widespread chaos and economic damage. Autonomous vehicles communicate with other vehicles (V2V) and infrastructure (V2I) for safe and efficient operation. If these communication channels are compromised, it could lead to collisions, traffic jams, or other dangerous situations. So we present a novel approach to mitigating these security risks by leveraging pre-trained Convolutional Neural Network (CNN) models for dynamic cyber-attack detection within the cyber-physical systems (CPS) framework of AVs. The proposed Intelligent Intrusion Detection System (IIDS) employs a combination of advanced learning techniques, including Data Fusion, One-Class Support Vector Machine, Random Forest, and k-Nearest Neighbor, to improve detection accuracy. The study demonstrates that the EfficientNet model achieves superior performance with an accuracy of up to 99.97%, highlighting its potential to significantly enhance the security of AV networks. This research contributes to the development of intelligent cyber-security models that align with 6G standards, ultimately supporting the safe and efficient integration of AVs into smart cities.

Tumor-suppressive function of EZH2 is through inhibiting glutaminase

Tumors can use metabolic reprogramming to survive nutrient stress. Epigenetic regulators play a critical role in metabolic adaptation. Here we screened a sgRNA library to identify epigenetic regulators responsible for the vulnerability of colorectal cancer (CRC) cells to glucose deprivation and found that more EZH2-knockout cells survived glucose deprivation. Then, we showed that EZH2 expression was significantly downregulated in response to glucose deprivation in a glucose-sensitive CRC cell line, and EZH2-knockdown cells were more resistant to glucose deprivation. Mechanistically, EZH2 deficiency upregulated the expression of glutaminase (GLS) and promoted the production of glutamate, which in turn led to increased synthesis of intracellular glutathione (GSH) and eventually attenuated the reactive oxygen species (ROS)-mediated cell death induced by glucose deprivation. Although EZH2 functioned as an oncogene in cancer progression and EZH2 knockout abolished colorectal cancer development in a mouse model, here we revealed a mechanistic link between EZH2 and metabolic reprogramming via the direct regulation of GLS expression and observed a negative correlation between EZH2 and GLS expression in colorectal cancer tissues. These findings further confirmed the importance of heterogeneity, provided an explanation for the clinical tolerance of cancer cells to EZH2 inhibitors from the perspective of metabolism, and proposed the possibility of combining EZH2 inhibitors and glutamine metabolism inhibitors for the treatment of cancer.

Prediction of Multidrug-Resistant Tuberculosis Using Machine Learning Algorithms in SWAT, Pakistan

In this paper, we have focused on machine learning (ML) feature selection (FS) algorithms for identifying and diagnosing multidrug-resistant (MDR) tuberculosis (TB). MDR-TB is a universal public health problem, and its early detection has been one of the burning issues. The present study has been conducted in the Malakand Division of Khyber Pakhtunkhwa, Pakistan, to further add to the knowledge on the disease and to deal with the issues of identification and early detection of MDR-TB by ML algorithms. These models also identify the most important factors causing MDR-TB infection whose study gives additional insights into the matter. ML algorithms such as random forest, k-nearest neighbors, support vector machine, logistic regression, leaset absolute shrinkage and selection operator (LASSO), artificial neural networks (ANNs), and decision trees are applied to analyse the case-control dataset. This study reveals that close contacts of MDR-TB patients, smoking, depression, previous TB history, improper treatment, and interruption in first-line TB treatment have a great impact on the status of MDR. Accordingly, weight loss, chest pain, hemoptysis, and fatigue are important symptoms. Based on accuracy, sensitivity, and specificity, SVM and RF are the suggested models to be used for patients' classifications.

Robust proportional overlapping analysis for feature selection in binary classification within functional genomic experiments

In this paper, a novel feature selection method called Robust Proportional Overlapping Score (RPOS), for microarray gene expression datasets has been proposed, by utilizing the robust measure of dispersion, i.e., Median Absolute Deviation (MAD). This method robustly identifies the most discriminative genes by considering the overlapping scores of the gene expression values for binary class problems. Genes with a high degree of overlap between classes are discarded and the ones that discriminate between the classes are selected. The results of the proposed method are compared with five state-of-the-art gene selection methods based on classification error, Brier score, and sensitivity, by considering eleven gene expression datasets. Classification of observations for different sets of selected genes by the proposed method is carried out by three different classifiers, i.e., random forest, k-nearest neighbors (k-NN), and support vector machine (SVM). Box-plots and stability scores of the results are also shown in this paper. The results reveal that in most of the cases the proposed method outperforms the other methods.

A Robust and Efficient Feature Selection Algorithm for Microarray Data

In the past decades, a few synergistic feature selection algorithms have been published, which includes Cooperative Index (CI) and K-Top Scoring Pair (k-TSP). These algorithms consider the synergistic behavior of features when they are included in a feature panel. Although promising results have been shown for these algorithms, there is lack of a comprehensive and fair comparison with other feature selection algorithms across a large number of microarray datasets in terms of classification accuracy and computational complexity. There is a need in evaluating their performance and reducing the complexity of such algorithms. We compared the performance of synergistic feature selection algorithms with 11 other commonly used algorithms based on 22 microarray gene expression binary class datasets. The evaluation confirms that synergistic algorithms such as CI and k-TSP will gradually increase the classification performance as more features are used in the classifiers. Also, in order to cut down computational cost, we proposed a new feature selection ranking score called Positive Synergy Index (PSI). Testing results show that features selected using PSI as well as synergistic feature selection algorithms provide better performance compared to with all other methods, while PSI has a computational complexity significantly lower than that of other synergistic algorithms.

Data on clinical significance of GAS2 in colorectal cancer cells

The growth arrest-specific 2 (GAS2) was cloned and found to be upregulated in the feces of recurrent CRC patients. This overexpressed GAS2 induced different patterns of gene expressions in CRC cells. Briefly, one cell proliferation marker, Ki-67 antigen (Ki-67), was upregulated in the cells with overexpressed GAS2, "Correlation between proliferation markers: PCNA, Ki-67, MCM-2 and antiapoptotic protein Bcl-2 in colorectal cancer" [1]. Whereas, the expression of another cell proliferation marker, proliferating cell nuclear antigen (PCNA), changed insignificantly [1]. In addition, the mRNA level of one cyclin involving in both cell cycle G1/S and G2/M transitions was also not affected by GAS2 overexpression, "Cdc20 and Cks direct the spindle checkpoint-independent destruction of cyclin A" [2]. The experimental design and procedures in this article can be helpful for understanding the molecular significance of GAS2 in SW480 and SW620 CRC cells.

Ensemble of a subset of kNN classifiers

Combining multiple classifiers, known as ensemble methods, can give substantial improvement in prediction performance of learning algorithms especially in the presence of non-informative features in the data sets. We propose an ensemble of subset of kNN classifiers, ESkNN, for classification task in two steps. Firstly, we choose classifiers based upon their individual performance using the out-of-sample accuracy. The selected classifiers are then combined sequentially starting from the best model and assessed for collective performance on a validation data set. We use bench mark data sets with their original and some added non-informative features for the evaluation of our method. The results are compared with usual kNN, bagged kNN, random kNN, multiple feature subset method, random forest and support vector machines. Our experimental comparisons on benchmark classification problems and simulated data sets reveal that the proposed ensemble gives better classification performance than the usual kNN and its ensembles, and performs comparable to random forest and support vector machines.