It has been a grand challenge to make an accurate prediction without any structural information in computational biophysics for decades 1, 2, as there are mainly two difficulties in the prediction: (1) efficient sampling methods to search an astronomically larger conformation space 3, and (2) accurate free energy determination to find the most stable shape 1. Predicting protein three-dimensional structures is an alternative way to narrow the gap. Moreover, with the rapid large-scale sequencing technologies, a gap between the huge number of protein sequences and a small number of known structures is being enlarged. However, it is difficult and expensive to experimentally determine protein tertiary structures. Proteins play important roles in biological activities, and their functional significance is determined by their three-dimensional structure. The source code and data are available at the website. Moreover, the proposed features would pave the way to improve machine learning-based methods in protein folding and structure prediction, as well as function prediction. As demonstrated in the present study, the predicted angles can be used as structural constraints to accurately infer protein tertiary structures. On four widely used benchmark datasets, the ESIDEN significantly improves the accuracy in predicting the torsion angles by comparison to the best-so-far methods. On the other hand, compared to widely used classic features, the new features, especially the Ramachandran basin potential, provide statistical and evolutionary information to improve prediction accuracy. Here we first time propose evolutionary signatures computed from protein sequence profiles, and a novel recurrent architecture, termed ESIDEN, that adopts a straightforward architecture of recurrent neural networks with a small number of learnable parameters. The ESIDEN can capture efficient information from both the classic and new features benefiting from different recurrent architectures in processing information. The backbone torsion angles play a critical role in protein structure prediction, and accurately predicting the angles can considerably advance the tertiary structure prediction by accelerating efficient sampling of the large conformational space for low energy structures. However, it is challenging and expensive to experimentally determine the three-dimensional structure of proteins. The amino acid sequence of a protein contains all the necessary information to specify its shape, which dictates its biological activities.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |