Fast and Efficient Design of Deep Neural Networks for Predicting N7-Methylguanosine Sites Using autoBioSeqpy

N-7-Methylguanosine(m(7)G) is a crucial post-transcriptionalRNA modification that plays a pivotal role in regulating gene expression.Accurately identifying m(7)G sites is a fundamental stepin understanding the biological functions and regulatory mechanismsassociated with this modification. While whole-genome sequencing isthe gold standard for RNA modification site detection, it is a time-consuming,expensive, and intricate process. Recently, computational approaches,especially deep learning (DL) techniques, have gained popularity inachieving this objective. Convolutional neural networks and recurrentneural networks are examples of DL algorithms that have emerged asversatile tools for modeling biological sequence data. However, developingan efficient network architecture with superior performance remainsa challenging task, requiring significant expertise, time, and effort.To address this, we previously introduced a tool called autoBioSeqpy,which streamlines the design and implementation of DL networks forbiological sequence classification. In this study, we utilized autoBioSeqpyto develop, train, evaluate, and fine-tune sequence-level DL modelsfor predicting m(7)G sites. We provided detailed descriptionsof these models, along with a step-by-step guide on their execution.The same methodology can be applied to other systems dealing withsimilar biological questions. The benchmark data and code utilizedin this study can be accessed for free at http://github.com/jingry/autoBioSeeqpy/tree/2.0/examples/m7G.