Abstract: Most of the prediction methods for secretory proteins require the
presence of a correct N-terminal end of the pre-protein for correct
classification. As large scale genome sequencing projects sometimes assign the
5'-end of genes incorrectly, many proteins are encoded without the correct
N-terminus leading to incorrect prediction. In this study, a systematic attempt
has been made to predict secretory proteins irrespective of presence or absence
of N-terminal signal peptides (also known as classical and non-classical
secreted proteins respectively), using machine-learning techniques; artificial
neural network (ANN) and support vector machine (SVM). We trained and tested
our methods on a dataset of 3321 secretory and 3654 non-secretory mammalian
proteins using five-fold cross-validation technique. First, ANN-based modules
have been developed for predicting secretory proteins using 33 physico-chemical
properties, amino acid composition and dipeptide composition and achieved
accuracies of 73.1%, 76.1% and 77.1%, respectively. Similarly,
SVM-based modules using 33 physico-chemical properties, amino acid, and
dipeptide composition have been able to achieve accuracies of 77.4%,
79.4% and 79.9%, respectively. In addition, BLAST and PSI-BLAST modules
designed for predicting secretory proteins based on similarity search achieved
23.4% and 26.9% accuracy, respectively. Finally, we developed a
hybrid-approach by integrating amino acid and dipeptide composition based SVM
modules and PSI-BLAST module that increased the accuracy to 83.2%, which is
significantly better than individual modules. We also achieved high sensitivity
of 60.4% with low value of 5% false positive predictions using hybrid
module. A web server SRTpred has been developed based on above study for
predicting classical and non-classical secreted proteins from whole sequence of
mammalian proteins, which is available from
http://www.imtech.res.in/raghava/srtpred/.
