Document details

The development of high throughput sequencing technologies, such as RNA-Seq, has enabled the generation of large volumes of biological data. Thus, it is necessary to develop computational methods to interpret this massive volume of data and contribute to knowledge discovery. RNA sequences are products of the transcription of genomic DNA sequences, and represent the gene expression process that organisms use to synthesize protein or RNA molecules. These RNA sequences can be compared between organisms of the same or different species to demonstrate similar functional proteins. The RNA sequences have different biological functions, such as mRNAs, rRNAs, tRNAs and ncRNA, to name a few. The correct identification of each class of RNA sequences is important because of the huge volume of unlabeled data available. In this context, this study proposes an approach based on the Resonant Recognition Model for feature extraction and classification regarding the ncRNA and mRNA classes. To assess the proposed approach, it was adopted the dataset from the PLEK method. Despite the reduction of the input data size achieved using the RMM method, the results show high accuracy, indicating the potential of the proposed approach.