A self-organizing deep neuro-fuzzy system approach for classification of kidney cancer subtypes using miRNA genomics data

•The proposed deep neuro-fuzzy system with new topology is applicable in high dimension data, especially genomics data.•The proposed deep neuro-fuzzy system includes new topology in the fuzzification layer and rule layer.•The deep learning is used to create complex rules from simple rules in the rule layer.•The significant miRNAs are selected, by the proposed feature selection algorithm; and kidney cancer subtypes classification is performed, by the proposed deep neuro-fuzzy system.•The proposed model succeeded in classification with high accuracy.