DeepSuccinylSite: a deep learning based approach for protein succinylation site prediction

Abstract

Background: Protein succinylation has recently emerged as an important and common post-translation modification (PTM) that occurs on lysine residues. Succinylation is notable both in its size (e.g., at 100 Da, it is one of the larger chemical PTMs) and in its ability to modify the net charge of the modified lysine residue from + 1 to − 1 at physiological pH. The gross local changes that occur in proteins upon succinylation have been shown to correspond with changes in gene activity and to be perturbed by defects in the citric acid cycle. These observations, together with the fact that succinate is generated as a metabolic intermediate during cellular respiration, have led to suggestions that protein succinylation may play a role in the interaction between cellular metabolism and important cellular functions. For instance, succinylation likely represents an important aspect of genomic regulation and repair and may have important consequences in the etiology of a number of disease states. In this study, we developed DeepSuccinylSite, a novel prediction tool that uses deep learning methodology along with embedding to identify succinylation sites in proteins based on their primary structure. Results: Using an independent test set of experimentally identified succinylation sites, our method achieved efficiency scores of 79%, 68.7% and 0.48 for sensitivity, specificity and MCC respectively, with an area under the receiver operator characteristic (ROC) curve of 0.8. In side-by-side comparisons with previously described succinylation predictors, DeepSuccinylSite represents a significant improvement in overall accuracy for prediction of succinylation sites. Conclusion: Together, these results suggest that our method represents a robust and complementary technique for advanced exploration of protein succinylation.

Novel Few-shots Learning Neural Network for Predicting Carbohydrate-active Enzyme (CAZyme) Affinity Towards Fructo-oligosaccharides

“…It should be noted that there are certain limitations for this study: a) Although it facilitates the acquirement of virtual calculated binding affinity data when the dataset is small and especially when the mass structure simulation is not an option, the Other methods using deep learning networks (Thapa, N. et al, 2020) may achieve better results for this kind of study, but in terms of time cost and coding vector embedding, it may not be very well suited to FSL framework, especially with pNN, but is definitely worthy of future investigation. e) Specifically, for CAZymes, more structural features involving side chain interactions with certain sugar structure types can be further explored.…”

RecSNO: Prediction of Protein S-Nitrosylation Sites Using a Recurrent Neural Network

“…A prerequisite for this approach is that the sequence data must be encoded in a form that is readable by our DL model. To this end, we utilized an embedding encoding technique [54], [58] and extracted features from this encoded matrix using BiLSTM. To decrease the number of dimensions, we used a max-pooling layer after feature extraction.…”

“…In recent years, deep learning (DL) based methods have been used to predict the PTM sites in cellular proteins. Typical applications include DeepSuccinylSite [54], MusiteDeep [55], DeepRMethylSite [56], and DeepPhos [57]. In DL, a suitable raw vector is given to the architecture and transformed into highly abstract features by propagating through whole model.…”

Deep Learning in Proteomics

“…Deep learning has been used in the prediction of PTM sites for phosphorylation, [96][97][98][99][100] ubiquitination, [101,102] acetylation, [103][104][105][106] glycosylation, [107] malonylation, [108,109] succinylation, [110,111] glycation, [112] nitration/nitrosylation, [113] crotonylation [114] and other modifications [115][116][117]224] as shown in Table 3. MusiteDeep, the first deep learning-based PTM prediction tool, provides both general phosphosite prediction and kinase-specific phosphosite prediction for five kinase families, each with more than 100 known substrates.…”