Home > Papers

 
 
PrAS: Prediction of amidation sites using a multiple feature extraction
WANG Tong 1, ZHENG Wei 1, WUYUN Qiqige 1, WU Zhenfeng 1, RUAN Jishou 2, HU Gang 1, GAO Jianzhao 1 *
1. School of Mathematical Sciences and LPMC, Nankai University, Tianjin, 300071
2. School of Mathematical Sciences and LPMC, Nankai University, Tianjin, 300071; State Key Laboratory of Medicinal Chemical Biology, Nankai University, Tianjin, 300071
*Correspondence author
#Submitted by
Subject:
Funding: This work was supported by Specialized Research Fund for the Doctoral Program of Higher Education (SRFDP grant number 20130031120001) and NSFC（No.grant number 11101226）, Canada （No.no. 104519-010）
Opened online:11 July 2016
Accepted by: none
Citation: WANG Tong, ZHENG Wei, WUYUN Qiqige.PrAS: Prediction of amidation sites using a multiple feature extraction[OL]. [11 July 2016] http://en.paper.edu.cn/en_releasepaper/content/4698552
 
 
Amidation plays an important role in a variety of pathological processes and serious diseases like neural dysfunction and hypertension. However, identification of protein amidation sites through traditional experimental methods is time consuming and laborious. There isn’t a user-friendly prediction tool tailored to amidation sites up to now either. Thus, it’s indispensable and valuable to create a specified convenient tool to provide the potential protein amidation sites for users. In this study we incorporated four types of features and employed improved two-step feature selection, positive contribution feature selection (PCFS), to optimize the final feature set for model learning based on SVM classifier. The predictive capability of each feature type was also be analyzed on the training set and the predictive model achieved AUC of 95.93%, accuracy of 92.10%, sensitivity of 81.21%, specificity of 94.94% and MCC of 75.98% on the independent test set. A novel predictor named PrAS, the first specified prediction tool for protein amidation sites with high predictive capability, can be freely available at https://sourceforge.net/p/praspkg.
Keywords:amidation site; Support vector machine; K nearest neighbors
 
 
 

For this paper
  • ● PDF (0B)
  • ● Revision 0 　　
  • ● Print this paper
  • ● Recommend this paper to a friend
  • ● Add to my favorite list

    Saved Papers

    Please enter a name for this paper to be shown in your personalized Saved Papers list

Tags
Add yours

Related Papers

Statistics
PDF Downloaded 45
Bookmarked 0
Recommend 0
Comments Array
Submit your papers