Proteomic analysis of cancers' stages has provided new opportunities for the development of novel, highly sensitive diagnostic tools which helps early detection of cancer. This paper introduces a new feature ranking approach called FRMT. FRMT is based on the Technique for Order of Preference by Similarity to Ideal Solution method (TOPSIS) which select the most discriminative proteins from proteomics data for cancer staging. In this approach, outcomes of 10 feature selection techniques were combined by TOPSIS method, to select the final discriminative proteins from seven different proteomic databases of protein expression profiles. In the proposed workflow, feature selection methods and protein expressions have been considered as criteria and alternatives in TOPSIS, respectively. The proposed method is tested on seven various classifier models in a 10-fold cross validation procedure that repeated 30 times on the seven cancer datasets. The obtained results proved the higher stability and superior classification performance of method in comparison with other methods, and it is less sensitive to the applied classifier. Moreover, the final introduced proteins are informative and have the potential for application in the real medical practice.
1 November 2020 in Journal of Biomedical Informatics
Hybrid algorithms are effective methods for solving optimization problems that rarely have been used in the gene selection procedure. This paper introduces a novel modified model for microarray data classification using an optimized gene subset selection method. The proposed approach consists of ensemble feature selection based on wrapper methods using five criteria, which reduces the data dimensions and time complexity. Five feature ranking procedures, including receiver operating characteristic curve, two-sample T-test, Wilcoxon, Bhattacharyya distance, and entropy, are used in the soft weighting method. Besides, we proposed a classification method that used the support vector machine (SVM) and metaheuristic algorithm. The optimization of the SVM hyper-parameters for the radial basis function (RBF) kernel function is performed using a modified Water Cycle Algorithm (mWCA). The results indicate that the ensemble performance of genes-mWCA SVM (EGmWS) is considered an efficient method compared to similar approaches in terms of accuracy and solving the uncertainty problem. Five benchmark microarray datasets, including leukemia, MicroRNA-Breast, diffuse large B-cell lymphoma, prostate, and colon, are employed for experiments. The highest and lowest numbers of genes are related to prostate with 12 533 genes and MicroRNA-Breast with 1926 genes, respectively. Besides, the highest and lowest numbers of samples are MicroRNA-Breast with 132 samples and colon with 62 samples, respectively. The results of classifying all data by applying effective genes of the EF-WS yielded high accuracies in microarray data classification. In addition to the robustness and simplicity of the proposed method, the model’s generalizability is another crucial aspect of the method that can be further developed to increase the accuracy while reducing classification error.
2 March 2015 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
In this experiment, a gene selection technique was proposed to select a robust gene signature from microarray data for prediction of breast cancer recurrence. In this regard, a hybrid scoring criterion was designed as linear combinations of the scores that were determined in the mutual information (MI) domain and protein-protein interactions network. Whereas, the MI-based score represents the complementary information between the selected genes for outcome prediction; and the number of connections in the PPI network between the selected genes builds the PPI-based score. All genes were scored by using the proposed function in a hybrid forward-backward gene-set selection process to select the optimum biomarker-set from the gene expression microarray data. The accuracy and stability of the finally selected biomarkers were evaluated by using five-fold cross-validation (CV) to classify available data on breast cancer patients into two cohorts of poor and good prognosis. The results showed an appealing improvement in the cross-dataset accuracy in comparison with similar studies whenever we applied a primary signature, which was selected from one dataset, to predict survival in other independent datasets. Moreover, the proposed method demonstrated 58-92 percent overlap between 50-genes signatures, which were selected from seven independent datasets individually.