Abstract
Protein structure and function prediction are instrumental areas in the bioinformatics field. They are important for a number of applications in rational drug discovery, disease analysis, and many others. Protein sequences and natural languages share some similarities. Therefore, many techniques derived from natural language processing (NLP) have been applied to the protein structure and function prediction. In this chapter, we discuss sequence-based predictors of protein structure and function that utilize techniques derived from NLP field. We include methods that target protein sequence analysis, fold recognition, identification of intrinsically disordered regions/proteins, and prediction of protein-nucleic acids binding. The concepts and computational methods discussed in this chapter will be especially useful for the researchers who are working in the related field. We also aim to bring new computational NLP techniques into the protein structure and function prediction area.
Original language | English |
---|---|
Title of host publication | Machine Learning in Bioinformatics of Protein Sequences |
Subtitle of host publication | Algorithms, Databases and Resources for Modern Protein Bioinformatics |
Publisher | World Scientific Publishing Co. |
Pages | 57-80 |
Number of pages | 24 |
ISBN (Electronic) | 9789811258589 |
ISBN (Print) | 9789811258572 |
DOIs | |
Publication status | Published - 1 Jan 2022 |