How it works

ERPred is a threshold dependent, N-terminal, C-terminal and remaining amino acid composition and support vector machine based predictor, which predict Endoplasmic Reticular proteins. First it divide each amino acid into 3 parts, then calculate amino acid composition of each parts. After that it run SVM classify to predict protein. If SVM score is greater than threshold, the input sequence belongs to ER proteins and if SVM score is less than threshold, the input sequence belongs to Non-ER. Figure 1 shows the overall architecture of ERPred.

Please cite: Kumar R, Kumari B, Kumar M. Prediction of endoplasmic reticulum resident proteins using fragmented amino acid composition and support vector machine. PeerJ. 2017;5:e3561. doi:10.7717/peerj.3561