With the rapid growth of biological sequence data, machine learning has become an essential tool for analyzing these sequences and extracting useful information. There are many different areas of biological sequence classification research, such as understanding the biological functions of DNA (e.g., epigenetic modification sites, replication origin, enhancer, and promoter), RNA (e.g., subcellular localization and post-transcriptional modifications), proteins (e.g., hormone binding proteins, thermophilic/mesophilic), and peptides (e.g., anticancer, antihypertensive, and antimicrobial).
In recent years, the field of bioinformatics or computational biology has made significant progress due to the development of new computational frameworks that combine conventional and deep learning algorithms with rigorous feature optimization methodologies.
This special thematic collection focuses on the application of machine learning, including deep learning, to biological sequence analysis. We are particularly interested in showcasing novel and sophisticated deep learning methodologies that can extract and interpret biological function information from sequence data.
In addition to original research papers, we also welcome review papers that evaluate current AI strategies for sequence-based biological functional studies.