A comparative analysis of deep learning-based techniques for miRNA prediction associated with mRNA sequences

MicroRNAs (miRNAs) are short sequences of nucleotides, typically consisting of 21–25 base pairs, which play a crucial role in the regulation of genes throughout several biological processes. The identification of these miRNAs is challenging and intricate owing to their short read duration. Hence, the use of modern computational methodologies may provide significant benefits in accurately discerning these sequences. In recent years, there has been a growing use of computer methodologies for the categorization of diverse biological datasets. This work used publicly accessible miRNA sequences for the purpose of binary classification. Additionally, a dictionary was employed to numerically represent the nucleotide sequences, which were of a consistent length of 22 nucleotides. Various deep learning approaches, including Bidirectional Gated Recurrent Unit (Bi-GRU), Convolutional Neural Network (CNN), a mix of CNN and Long Short-Term Memory (LSTM), and LSTM, were used in the research investigation. All of the models exhibited much higher efficiency in comparison to the models documented in existing literature. Additionally, it was noted that the hybrid model combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) has superior performance compared to the other models, with the maximum classification accuracy of 92.8% on the testing dataset. This hybrid model presented in this study represents the first development of a classification model specifically designed for the categorization of miRNA sequences derived from either plant or animal sources. Our developed hybrid model efficiently classify the data as it uses two different algorithms in model building.