HybridSucc: A Hybrid-Learning Architecture for General and Species-Specific Succinylation Site Prediction

Ning, Wanshan; Xu, Haodong; Jiang, Peiran; Cheng, Han; Deng, Wankun; Guo, Yaping; Xue, Yu

doi:10.1016/j.gpb.2019.11.010

Cited by 31 publications

(28 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent studies have identified global lysine succinylation sites at the proteomic level in microorganisms, animals, humans and plants [ 15 – 18 ], demonstrating that succinylation is ubiquitous in diverse organisms. Subsequent studies verified histone lysine succinylation in prokaryotes [ 19 ] and eukaryotic cells [ 20 ], and more comprehensive lysine succinylome studies in humans, yeast, mice and bacteria have confirmed that Ksuc is evolutionarily conserved and ubiquitous [ 21 , 22 ]. Hundreds of succinylation sites and proteins have been identified in a variety of microorganisms.…”

Section: Introductionmentioning

confidence: 99%

First comprehensive analysis of lysine succinylation in paper mulberry (Broussonetia papyrifera)

Dong

Chen

2021

BMC Genomics

View full text Add to dashboard Cite

Background Lysine succinylation is a naturally occurring post-translational modification (PTM) that is ubiquitous in organisms. Lysine succinylation plays important roles in regulating protein structure and function as well as cellular metabolism. Global lysine succinylation at the proteomic level has been identified in a variety of species; however, limited information on lysine succinylation in plant species, especially paper mulberry, is available. Paper mulberry is not only an important plant in traditional Chinese medicine, but it is also a tree species with significant economic value. Paper mulberry is found in the temperate and tropical zones of China. The present study analyzed the effects of lysine succinylation on the growth, development, and physiology of paper mulberry. Results A total of 2097 lysine succinylation sites were identified in 935 proteins associated with the citric acid cycle (TCA cycle), glyoxylic acid and dicarboxylic acid metabolism, ribosomes and oxidative phosphorylation; these pathways play a role in carbon fixation in photosynthetic organisms and may be regulated by lysine succinylation. The modified proteins were distributed in multiple subcellular compartments and were involved in a wide variety of biological processes, such as photosynthesis and the Calvin-Benson cycle. Conclusion Lysine-succinylated proteins may play key regulatory roles in metabolism, primarily in photosynthesis and oxidative phosphorylation, as well as in many other cellular processes. In addition to the large number of succinylated proteins associated with photosynthesis and oxidative phosphorylation, some proteins associated with the TCA cycle are succinylated. Our study can serve as a reference for further proteomics studies of the downstream effects of succinylation on the physiology and biochemistry of paper mulberry.

show abstract

Section: Introductionmentioning

confidence: 99%

First comprehensive analysis of lysine succinylation in paper mulberry (Broussonetia papyrifera)

Dong

Chen

2021

BMC Genomics

View full text Add to dashboard Cite

show abstract

“…For each candidate combination, we randomly generated a training data set and a testing data set with a ratio of approximately 4:1. The testing data set was only used to test the performance but not for training, and the final total AUC value was calculated as below: The least absolute shrinkage and selection operator (LASSO, L1 regularization) penalty and the ridge regression (L2 regularization) penalty in PLR 25-27 , were iteratively used to optimize the weight values of the 5 proteins or metabolites. To simplify the composition of a combination, one or multiple protein or metabolite was randomly dropped if the total AUC value of the 5-fold cross-validation was increased.…”

Section: Methodsmentioning

confidence: 99%

“…The accuracy of a model was evaluated by calculating the total area under curve (AUC) value, 7 / 33 and we also computed the total root mean squared error (RMSE) to measure the prediction bias. In the step of FCP, a widely used machine learning algorithm, penalized logistic regression (PLR) [25][26][27] , was used for model training and parameter optimization (Fig. 3A).…”

Section: Machine Learning-based Inference Of Cc-specific Biomarker Comentioning

confidence: 99%

“…The least absolute shrinkage and selection operator (LASSO, L1 regularization) penalty and the ridge regression (L2 regularization) penalty in PLR [25][26][27] , were iteratively used to optimize the weight values of the 5 proteins or metabolites. To simplify the composition of a combination, one or multiple protein or metabolite was randomly dropped if the total AUC value of the 5-fold cross-…”

Section: Inference Of Optimal Biomarker Combinationsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Omic Profiling of Plasma Identify Biomarkers and Pathogenesis of COVID-19 in Children

Wang

Ning

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Although children usually develop less severe disease responding to COVID-19 than adults, little is known about the pathogenesis of COVID-19 in children. Herein, we conducted the plasma proteomic and metabolomic profiling of a cohort of COVID-19 pediatric patients with mild symptoms. Our data show that numerous proteins and metabolites involved in immune as well as anti-inflammatory processes were up-regulated on a larger scale in children than in adults. By developing a machine learning-based pipeline, we prioritized two sets of biomarker combinations, and identified 5 proteins and 5 metabolites as potential children-specific COVID-19 biomarkers. Further study showed that these identified metabolites not only inhibited the expression of pro-inflammatory factors, but also suppressed coronaviral replication, implying that these factors played key roles in protecting pediatric patients from both viral infection and infection-induced inflammation. Together, our study uncovered a protective mechanism responding to COVID-19 in children, and sheds light on potential therapies.

show abstract

“…Huang et al developed a computational predictor, named CNN-SuccSite, which has been developed based on deep learning architectures with different encoding schemes [ 16 ]. Recently, Ning et al developed HybridSucc using Group-based Prediction System (GPS) via diverse encoding systems including k-space amino acid pair composition (CKSAAP), amino acid index (AAindex) physicochemical properties and pseudo amino acid composition (PseAAC) [ 17 ]. More recently, Hasan et al also suggested a predictor termed GPSuc, by combining five sequence encoding schemes i.e.…”

Section: Introductionmentioning

confidence: 99%

An Improved Computational Prediction Model for Lysine Succinylation Sites Mapping on Homo sapiens by Fusing Three Sequence Encoding Schemes with the Random Forest Classifier

Tasmia

Ahmed²,

Mosharaf

et al. 2021

View full text Add to dashboard Cite

Background: Lysine succinylation is one of the reversible protein post-translational modifications (PTMs), which regulate the structure and function of proteins. It plays a significant role in various cellular physiologies including some diseases of human as well as many other organisms. The accurate identification of succinylation site is essential to understand the various biological functions and drug development. In this study, we developed an improved method to predict lysine succinylation sites mapping on Homo sapiens by the fusion of three encoding schemes such as binary, composition of k-spaced amino acid pairs (CKSAAP) and Amino acid composition (AAC) with the random forest (RF) classifier. The prediction performance of the proposed random forest (RF) based fusion model in a comparison of the other candidates was investigated by using 20-fold cross-validation (CV) and two independent test datasets that were collected from two different sources. The CV results showed that the proposed predictor achieves the highest scores of sensitivity (SN) as 0.800, specificity (SP) as 0.902, accuracy (ACC) as 0.919, Mathew correlation coefficient (MCC) as 0.766 and partial AUC (pAUC) as 0.163 at false positive rate (FPR) = 0.10 and area under the ROC curve (AUC) as 0.958. It achieved the highest performance scores of SN as 0.811, SP as 0.902, ACC as 0.891, MCC as 0.629 and pAUC as 0.139 and AUC as 0.921 for the independent test protein set-1 and SN as 0.772, SP as 0.901, ACC as 0.836, MCC as 0.677 and pAUC as 0.141 at FPR = 0.10 and AUC as 0.923 for the independent test protein set-2. It also outperformed all the other existing prediction models. Conclusion: The prediction performances as discussed in this article recommend that the proposed method might be a useful and encouraging computational resource for lysine succinylation site prediction in the case of human population.

show abstract

HybridSucc: A Hybrid-Learning Architecture for General and Species-Specific Succinylation Site Prediction

Cited by 31 publications

References 49 publications

First comprehensive analysis of lysine succinylation in paper mulberry (Broussonetia papyrifera)

First comprehensive analysis of lysine succinylation in paper mulberry (Broussonetia papyrifera)

Multi-Omic Profiling of Plasma Identify Biomarkers and Pathogenesis of COVID-19 in Children

An Improved Computational Prediction Model for Lysine Succinylation Sites Mapping on Homo sapiens by Fusing Three Sequence Encoding Schemes with the Random Forest Classifier

Contact Info

Product

Resources

About