ANFIS-based wrapper model gene selection for cancer classification on microarray gene expression data

Abstract

This paper proposes a gene selection framework, based on wrapper model with neuro-fuzzy approach for cancer classification. ANFIS as a classifier for selected genes from Particle Swarm Optimization (PSO) or Genetic Algorithm (GA) methods applies on six datasets of microarray gene expression data for different cancers. ANFIS is compared with three other classifiers which are Support Vector Machine (SVM), K-Nearest Neighbour (KNN) and Classification And Regression Trees (CART). ANFIS gives the best results for original data of all the datasets and the predictions for noisy data are adequate in comparison with three others classifiers. ANFIS is best for less number genes, clearly. Besides, good results of ANFIS, it can generate TSK type fuzzy if-then rules which are interpretable.

Comparison of Hierarchical and Non-hierarchical Fuzzy Models with Simulation and an Application on Hypertension Data Set

“…They reported that the ANFIS structure they created constituted 97.08% of the accuracy of allocating individuals to 'snoring', 'sleeping' or 'silent' classes. Mahmoudi et al (31) aimed to compare the performances of the ANFIS structure in classification of individuals into cancer types using a total of six microchip gene expression data sets for breast, blood, colon, prostate, lung and lymphoma cancers and the performance of the support vector machine, k-nearest neighborhood and classification and regression trees methods. They found that the highest classification performance among the models they created separately for all cancer data sets was mostly due to the non-hierarchical fuzzy logic method.…”