Sequential Feature Maps with LSTM Recurrent Neural Networks for Robust Tumor Classification

Abstract

In the field of biomedicine, applications of the identification of biomarkers require a robust gene selection mechanism. For identifying the characteristic marker of an observed event, the selection of attributes becomes important. The robustness of gene selection methods affects detecting biologically meaningful genes in tumor diagnosis. For mapping, sequential features Long-short-term memory (LSTM) was used with Artificial Immune Recognition Systems (AIRS) to remember gene sequences and effectively recall of learned sequential patterns. An attempt was made to improve AIRS with LSTM which is a type of RNNs to produce discriminative gene subsets for finding biologically meaningful genes in tumor diagnosis. The algorithms were evaluated using six common cancer microarray datasets. By converging to the intrinsic information of the microarray datasets, specific groups like functions of the co-regulated groups were observed. The results showed that the LSTM based AIRS model can successfully identify biologically significant genes from the microarray datasets. Also the predictive genes for biological sequences areimportant in gene expression microarrays.This study confirms that different genes can be found in the same pathways. It was also found that the gene subsets selected by the algorithms were involved in important biological pathways.In this work we try an LSTM on our learning problem. We suspected that recurrent neural networks would be a good architecture for making predictions.The results show that the optimal gene subsets were based on the suggested framework, so they should have rich biomedical interpretability.