iDACP is a web server for identifying anticancer peptide (ACPs).

To facilitate this process, a several tool has been proposed for the computational identification of ACPs. In this study, we developed a two layers rule-based method to investigate the specificities of ACPs based on the sequence-based features. The libsvm algorithm was then applied to train a ACP prediction model with the amino acid composition (AAC) feature, the composition of k-space amino acid pair (CKSAAP), and physicalchemical properties (PCP). Evaluation using the 5-fold cross validation approach showed that the predictive model trained with the selected features significantly outperformed existing tools. The effectiveness of the constructed model was further evaluated with experimentally verified ACPs manually extracted from published research articles and databases.