Involving FCGR method in multiclass cancer diseases classification with transfer learning models

Cancer, a widespread disease, can cause death if not diagnosed and treated in time. Any alteration of gene expression can be the cause of one or more cancers. In humans, the number of genes encoding proteins is estimated at 40,000 which presents a large data set. Analyzing these data helps in disease classification and identification. In this context, this paper will emphasize multi-class disease classification based on the gene expression alteration which is caused by miRNAs. The Frequency Chaos Game Representation technique (FCGR), which maps the occurrence frequency of words in the DNA sequence in the form of an image will define the gene’s features. Then, a transfer learning technique will be used to extract important features and classify our data in different disease types. The proposed approach achieved an overall accuracy of 0.96.