LSTMCNNsucc: A Bidirectional LSTM and CNN-Based Deep Learning Method for Predicting Lysine Succinylation Sites

Abstract

Lysine succinylation is a typical protein post-translational modification and plays a crucial role of regulation in the cellular process. Identifying succinylation sites is fundamental to explore its functions. Although many computational methods were developed to deal with this challenge, few considered semantic relationship between residues. We combined long short-term memory (LSTM) and convolutional neural network (CNN) into a deep learning method for predicting succinylation site. The proposed method obtained a Matthews correlation coefficient of 0.2508 on the independent test, outperforming state of the art methods. We also performed the enrichment analysis of succinylation proteins. The results showed that functions of succinylation were conserved across species but differed to a certain extent with species. On basis of the proposed method, we developed a user-friendly web server for predicting succinylation sites.

A parallel model of DenseCNN and ordered‐neuron LSTM for generic and species‐specific succinylation site prediction

“…However, when the window size was greater than 33, the AUC tended to decrease. The results demonstrated that short peptides would miss vital information, and long peptides would include noise or redundancies (G. Huang et al, 2021). To verify the rationality of the results, two‐sample Logos (Vacic et al, 2006) was used to analyze the differences between positive and negative samples with 33 residues (Figure S3 of the Supporting Information Material).…”

“…Combining CNN and LSTM compensates for information loss, which allows the acquisition of multiangle features and more promising results (Guo et al, 2019;. G. Huang et al (2021) proposed a CNN-LSTM model and verified its feasibility. However, CNN and LSTM still have several deficiencies.…”

Mini-review: Recent advances in post-translational modification site prediction based on deep learning

“…In addition to those discussed, deep learning can also be applied for other PTMs’ predictions, including methylation [110] , S-nitrosylation [111] , succinylation [112] , [113] , malonylation [114] , [115] , S-sulphenylation [116] , [117] , crotonylation [118] , [119] , [120] , [121] , 2- hydroxyisobutyrylation [122] , glutarylation [123] , N-palmitoylation [124] carbonylation [125] , and SUMOylation [126] . In particular, crotonylation prediction has demonstrated highly accurate results based on deep-learning methods.…”

pSuc-FFSEA: Predicting Lysine Succinylation Sites in Proteins Based on Feature Fusion and Stacking Ensemble Algorithm

“…In the same year, Thapa et al developed DeepSuccinylSite which used deep learning methods to identify succinylation sites through embedding and a thermal encoding ( Thapa et al, 2020 ). In 2021, Huang et al combined a long short-term memory (LSTM) and convolutional neural network (CNN) into a deep learning method for predicting lysine succinylation sites ( Huang et al, 2021 ). Although existing deep learning-based methods can effectively predict the succinylation sites, most of them suffer from the time-consuming training process because of a number of hyperparameters and complicated structures.…”