AUTHOR=Luo Yin , Jiang Jiulei , Zhu Jiajie , Huang Qiyi , Li Weimin , Wang Ying , Gao Yamin 

TITLE=A Caps-Ubi Model for Protein Ubiquitination Site Prediction

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.884903

DOI=10.3389/fpls.2022.884903

ISSN=1664-462X

ABSTRACT=Ubiquitination, as a widespread mechanism of regulating cellular responses in plants, is one of the most important post-translational modifications of proteins in many biological processes and is involved in the regulation of plant disease resistance responses. Ubiquitination prediction is an important technical means for plant protection. Traditional ubiquitination site determination methods are costly and time-consuming, while computational-based prediction methods can accurately and efficiently predict ubiquitination sites. At present, capsule network and deep learning are used alone for prediction, and the effect is not obvious. The capsule network can reflect the spatial position relationship of the internal features of the neural network, but it cannot encode long-distance dependencies, focus on amino acids in protein sequences, and the degree of importance. In this paper, we study the use of convolutional neural networks and capsule networks in deep learning to design a novel model "Caps-Ubi", first using one-of-K and amino acid continuous type hybrid encoding method to characterize the ubiquitination site. The sequence patterns, the dependencies between the encoded protein sequences and the important amino acids in the captured sequences, were then focused on the importance of amino acids in the sequences through the proposed Caps-Ubi model and used for multi-species ubiquitination site prediction. Through relevant experiments, the proposed method Caps-Ubi is superior to other similar methods in predicting ubiquitination sites.