Hu Chen's Homepage
Line
Resume Research Interests Publications  
Line

Research Projects

  • PMSVM
    is a new protein secondary structure prediction method based on SVM (support vector machine and PSSM (position specified matrix).It uses position matrices of proteins as input vector of SVM instead of protein sequences,so its prediction accuracy improves from SVM .

  • DBSubLoc SOAP
    Based on SOAP technology, the SubLoc server/client suite offers a user-friendly interface for searching and predicting protein subcellular location.  

  • MeMo
    MeMo  is the first protein methylation prediction server based on SVM  (support vector machine). Limited by available training data, at present MeMo  only focuses on Arginine and Lysine sites.
    Users could  submit their protein sequences to predict which arginine and Lysine sites are undergoing methylation.


  • NBA-Palm
    a computational web service of NBA-Palm - Prediction of Palmitoylation Site Implemented in Naive Bayesian Algorithm. The training data set includes 245 non-homologous sites from 105 proteins. The accuracy of NBA-Palm is 86.15% with the window length of seven. We propose the prediction results of NBA-Palm might be useful for further experimental consideration.