Over the past decades, research on biomolecules including DNA, RNA, and protein has experienced explosive growth, reshaping previous understanding and providing deeper insights into biological processes and disease pathology. The recent increase in biomedical data resulting from sequencing technologies has inevitably necessitated machine intelligence approaches to address problems in genome-wide DNA, RNA, and protein research, which costs less time and money than traditional biological experiments. Advances in computational models mainly derived from machine learning, deep learning, and various types of mathematical models to address various tasks pertaining to DNA, RNA, and protein profiles.

The existing tools in these tasks are far from perfect and rely heavily on hand-crafted features and parameter optimization processes. Recently, artificial intelligence algorithms have been utilized to extract the latent information in a self-supervised manner and enable to automaticly select the optimal hyperparameters and model architecture, alleviating the need for careful and time-consuming hand-tuning. Importantly, a trained model can also be applied to find biological relevance that can affect gene regulation.

This Research Topic welcomes the submission of Original Research articles, Review, Mini Review, Perspective articles, Editorial, Brief Research Report, and Method articles. We aim to bring state-of-the-art research contributions in computational models to address new problems and improve existing tasks around DNA, RNA, and protein research including, but not limited to:

• Prediction of molecule interaction mechanism using computational models (e.g. RNA-protein interactions, protein-protein interactions)

• Prediction of molecule structure (e.g. RNA second structure)

• Advances in molecular markers

• Gene expression analysis

• Detection, and identification of protein post-translational modifications

Submit your idea

Impact

Frontiers in Molecular Biosciences

Submit your idea

Impact