PREDICTION OF THE PROTEIN O-GLYCOSYLATION SITES BY COMBINING SUPPORT VECTOR MACHINES AND INDEPENDENT COMPONENT ANALYSIS

Journal Title: Asian Pacific Journal of Microbiology Research (APJMR) - Year 2017, Vol 1, Issue 1

Abstract

O-glycosylation is one of the main types of the mammalian protein glycosylation, it occurs on the particular site of serine and threonine, and has important functions in secretion, antigenicity, and metabolism of glycoproteins, it is very important to predict the O-glycosylation sites for pharmacy, food, and disease control. To improve the prediction accuracy, we proposed a new method of ICA+SVM. The samples(protein sequence) for experiment are encoded by the sparse coding with window size w=21, 120 independent components(feature) are extracted by independent component analysis(ICA), and inputed to the support vector machines(SVM), then the prediction(classification) is done in feature space by SVM. The results of experiment show that the performance of ICA+SVM is better than that of PCA+SVM and SVM. The prediction accuracy is about 88%. Furthermore, we investigated the same protein sequence under various window size, the results indicate that the longer the length of protein sequence, the higher the prediction accuracy.

Authors and Affiliations

Xue Mei Yang, Zhen Su

Keywords

Related Articles

PREVALENCE AND IDENTIFICATION OF UROPATHOGENS IN EASTERN NEPAL AND UNDERSTANDING THEIR ANTIBIOGRAM DUE TO MULTIDRUG RESISTANCE AND ESBL

This study was basically aimed at identifying the diversity of uropathogens; their drug response like multi-drug resistance (MDR) or extended spectrum β-lactamase (ESBL); and the evaluation of empirical treatment. Betwee...

DESIGN OF A PAINTING ROBOT WITH HOLLOW NON-SPHERICAL WRIST

Painting robot is one of the key systems for automobile manufacturing, thus its structural design and safety check have significant value in industrial circles. To facilitate the layout of pipeline and reduce the bending...

FIVE YEARS FOLLOW-UP OBSERVATION ON PATIENTS WITH SPINAL CORD INJURY TREATED WITH OLFACTORY ENSHEATHING CELL TRANSPLANTATION

Olfactory ensheathing cell transplantation (OECT) has been applied to treat patients with spinal cord injury (SCI). This study was to investigate the long-term curative efficacy and safety of OECT by observing the long-t...

DEVELOPMENT OF AN ECONOMIC TENSILE AND TORSION TESTING MACHINE FOR WIRES

The tensile and torsion properties of materials are extremely important in the design, analysis and manufacture of a wide variety of products and components which are loaded primarily in tensile and torsion loads. A bulk...

RECENT TREND OF ACQUISITION OF MULTI-DRUG RESISTANCE IN PSEUDOMONAS AERUGINOSA

Continues emergence of resistance among Pseudomonas (P.) aeruginosa strains to common antimicrobial drugs have been documented world-wide. This study investigated the antimicrobial resistance patterns of P.aeruginosa amo...

Download PDF file
  • EP ID EP403983
  • DOI 10.26480/ajmr.01.2017.12.14
  • Views 92
  • Downloads 0

How To Cite

Xue Mei Yang, Zhen Su (2017). PREDICTION OF THE PROTEIN O-GLYCOSYLATION SITES BY COMBINING SUPPORT VECTOR MACHINES AND INDEPENDENT COMPONENT ANALYSIS. Asian Pacific Journal of Microbiology Research (APJMR), 1(1), 12-14. https://europub.co.uk/articles/-A-403983