Neuropeptides (NPs) are short secreted peptides produced mainly in the nervous system and digestive system. They activate signaling cascades to control a wide range of biological functions, such as metabolism, sensation, and behavior. NPs are typically produced from a larger NP precursor (NPP) which includes a signal peptide sequence, one or more NP sequences, and other sequences. With the drastic growth of unknown protein sequences generated in the post-genomic age, it is highly desired to develop computational methods for identifying NPP rapidly and efficiently. In this article, we developed a predictor for NPPs based on optimized sequence composition of single amino acid, dipeptide, and tripeptide. Evaluated with independent data set, the predictor showed excellent performance that achieved an accuracy of 88.65% with AUC of 0.95. The corresponding web server was developed, which is freely available at http://i.uestc.edu.cn/neuropeptide/neuropp/home.html . It can help relevant researchers to screen candidate NP precursor, shorten experimental cycle, and reduce costs.
Keywords: Neuropeptide; Neuropeptide precursor; Predictor; Recognition; Sequence composition.