Predicting O-glycosylation sites in mammalian proteins by using SVMs

Li, Sujun; Liu, Boshu; Zeng, Rong; Cai, Yu-Dong; Li, Yixue

doi:10.1016/j.compbiolchem.2006.02.002

Cited by 76 publications

(63 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ROC curves of Dphos, AAphos, Figure 7. Comparison of AUCs for AADOGlySite, DOGlySite, AAOGlySite, Li et al, 26 and EnsembleGly. 27 and AADphos are drawn in Figure 2, Table 2, we show the performance in terms of precision and recall to compare our methods with the three models.…”

Section: Kinase-specific Phosphorylation Sitesmentioning

confidence: 99%

“…ROC curves of AADOGlySite, DOGlySite, and AAOGlySite for mucin-type O-glycosylation site prediction by 10-fold crossvalidation. For comparison, the corresponding performance measures reported in literature are shown: CKSAAPOGlySite, 24 Li et al, 26 EnsembleGly, 27 and NetOGlyc 3.1. 24 Li et al, 26 EnsembleGly, 27 and NetOGlyc 3.1.…”

Section: Kinase-specific Phosphorylation Sitesmentioning

confidence: 99%

“…For comparison, the corresponding performance measures reported in literature are shown: CKSAAPOGlySite, 24 Li et al, 26 EnsembleGly, 27 and NetOGlyc 3.1. 24 Li et al, 26 EnsembleGly, 27 and NetOGlyc 3.1. 25 For other kinase except the above four well-studied ones, the performance of AADphos also outperforms Dphos and AAphos (see Supporting Information).…”

Section: Kinase-specific Phosphorylation Sitesmentioning

confidence: 99%

“…The ROC curves are shown in Figure 6. The AUCs reported in the literature 24,26 are displayed for comparison in Figure 7. The results in Figures 6 and 7 illustrate that the performance of our methods is a little better or much better than that of other methods for prediction of mucin-type O-glycosylation sites.…”

Section: Mucin-type O-glycosylation Sites In Mammalian Proteinsmentioning

confidence: 99%

“…Following the approach used in the articles, [24][25][26] We use the approach similar to the last section to compare our methods with the existing methods. The ROC curves are shown in Figure 6.…”

Section: Mucin-type O-glycosylation Sites In Mammalian Proteinsmentioning

confidence: 99%

See 4 more Smart Citations

Retracted: Prediction of posttranslational modification sites from sequences with kernel methods

2012

J Comput Chem

View full text Add to dashboard Cite

Abstract:Posttranslational modification (PTM) is the chemical modification of a protein after its translation and one of the later steps in protein biosynthesis for many proteins. It plays an important role in modifying the end product of gene expression and contributes toward biological processes and diseased conditions. However, the experimental methods for identifying PTM sites are not only costly but also time consuming. Hence, computational methods are highly desired. In this article, a novel encoding method PSDP (position-specific dipeptide propensity), which is a modified version of position-specific amino acid propensity, is developed. Then, a support vector machine SVM with the kernel matrix computed by PSDP is applied to predict the PTM sites related to serine (S) and threonine (T) residues. The numerical results indicate that the performance of new method is better than the existing methods. Therefore, the new method is a useful computational resource for the identification of PTM sites. As the application, a software PTMPred is developed for predicting phosphorylation and O-glycosylation sites, and available at http://www.aporc.org/doc/wiki/PTMPred.

show abstract

Section: Kinase-specific Phosphorylation Sitesmentioning

confidence: 99%

Section: Kinase-specific Phosphorylation Sitesmentioning

confidence: 99%

Section: Kinase-specific Phosphorylation Sitesmentioning

confidence: 99%

Section: Mucin-type O-glycosylation Sites In Mammalian Proteinsmentioning

confidence: 99%

Section: Mucin-type O-glycosylation Sites In Mammalian Proteinsmentioning

confidence: 99%

See 3 more Smart Citations

Retracted: Prediction of posttranslational modification sites from sequences with kernel methods

2012

J Comput Chem

View full text Add to dashboard Cite

show abstract

Design of an epitope‐based peptide vaccine against Cryptococcus neoformans

Omer,

Khalil,

Abdalmumin

et al. 2024

FEBS Open Bio

View full text Add to dashboard Cite

Cryptococcus neoformans is the highest‐ranked fungal pathogen in the Fungal Priority Pathogens List (FPPL) released by the World Health Organization (WHO). In this study, through in silico simulations, a multi‐epitope vaccine against Cryptococcus neoformans was developed using the mannoprotein antigen (MP88) as a vaccine candidate. Following the retrieval of the MP88 protein sequences, these were used to predict antigenic B‐cell and T‐cell epitopes via the bepipred tool and the artificial neural network, respectively. Conserved B‐cell epitopes AYSTPA, AYSTPAS, PASSNCK, and DSAYPP were identified as the most promising B‐cell epitopes. While YMAADQFCL, VSYEEWMNY, and FQQRYTGTF were identified as the best candidates for CD8+ T‐cell epitopes; and YARLLSLNA, ISYGTAMAV, and INQTSYARL were identified as the most promising CD4+ T‐cell epitopes. The vaccine construct was modeled along with adjuvant and peptide linkers and the expasy protparam tool was used to predict the physiochemical properties. According to this, the construct vaccine was predicted to be antigenic, nontoxic, nonallergenic, soluble, stable, hydrophilic, and thermostable. Furthermore, the three‐dimensional structure was also used in docking analyses with Toll‐like receptor (TLR4). Finally, the cDNA of vaccine was successfully cloned into the E. coli pET‐28a (+) expression vector. The results presented here could contribute towards the design of an effective vaccine against Cryptococcus neoformans.

show abstract