VirulentPred is a bacterial virulent protein prediction method based on bi-layer cascade Support Vector Machine (SVM). The first layer SVM classifiers were trained and optimized with different individual protein sequence features like amino acid composition, dipeptide composition (occurrences of the possible pairs of i and i+1 amino acid residues), higher order dipeptide composition (pairs of i and i+2 residues) and remote evolutionary relationships by use of Position-Specific Iterated BLAST (PSI-BLAST) generated Position Specific Scoring Matrix (PSSM). A five-fold cross-validation technique was used for the evaluation of various prediction strategies in the current work. The results from the first layer (SVM scores and PSI-BLAST output) were cascaded to the second layer SVM classifier to train and generate the final classifier. The cascade SVM classifier was able to accomplish a significantly higher accuracy of 81.8%, covering 86% area in the Receiver Operator Characteristic (ROC) plot, better than that of either of the layer one SVM classifiers based either on single or multiple sequence features.