An Effective Deep Learning-Based Architecture for Prediction of N7-Methylguanosine Sites in Health Systems

Abstract

N7-methylguanosine (m7G) is one of the most important epigenetic modifications found in rRNA, mRNA, and tRNA, and performs a promising role in gene expression regulation. Owing to its significance, well-equipped traditional laboratory-based techniques have been performed for the identification of N7-methylguanosine (m7G). Consequently, these approaches were found to be time-consuming and cost-ineffective. To move on from these traditional approaches to predict N7-methylguanosine sites with high precision, the concept of artificial intelligence has been adopted. In this study, an intelligent computational model called N7-methylguanosine-Long short-term memory (m7G-LSTM) is introduced for the prediction of N7-methylguanosine sites. One-hot encoding and word2vec feature schemes are used to express the biological sequences while the LSTM and CNN algorithms have been employed for classification. The proposed “m7G-LSTM” model obtained an accuracy value of 95.95%, a specificity value of 95.94%, a sensitivity value of 95.97%, and Matthew’s correlation coefficient (MCC) value of 0.919. The proposed predictive m7G-LSTM model has significantly achieved better outcomes than previous models in terms of all evaluation parameters. The proposed m7G-LSTM computational system aims to support the drug industry and help researchers in the fields of bioinformatics to enhance innovation for the prediction of the behavior of N7-methylguanosine sites.

Unveiling the Potential Pattern Representation of RNA 5-Methyluridine Modification Sites Through a Novel Feature Fusion Model Leveraging Convolutional Neural Network and Tetranucleotide Composition

“…It consists of multiple convolutional units, and their parameters are optimized through the backpropagation process. While, as an activation function for the convolution layer, the Rectified Linear Unit (ReLU) is utilized, which is widely adopted in deep learning architectures due to its ability to introduce non-linearity and alleviate the vanishing gradient problem[53]. After the convolution layer, a group normalization layer is applied, which serves as an effective alternative to batch normalization, especially when dealing with small batch sizes, as it normalizes the activations within each group, promoting stable and efficient training[54].…”