Antimicrobial peptides (also called host defense peptides) are an evolutionarily conserved component of the innate immune response and are found among all classes of life. It represents a class of natural peptides that form a part of the innate immune system, and this kind of ‘nature's antibiotics’ is quite promising for solving the problem of increasing antibiotic resistance.

To improve the accurateness, WANG Ping and her colleagues at the Genome Analysis Laboratory, Tianjin Institute of Industrial Biotechnology, Chinese Academy of Sciences, integrated two methods that are the sequence alignment method based on the BLASTP and the feature selection method with amino acid composition and pseudo amino acid composition features.

The prediction accuracy of the integrated method on the benchmark dataset is 80.23%. It is anticipated that the new method may be of use for helping to understand the role of peptide in antimicrobial activity, identify the natural AMPs, and design the synthetic AMPs against the resistance of microorganisms to antibiotics. For the convenience of readers, a user-friendly web-server is freely accessible at http://amp.biosino.org/.

The research article was published on PLOS one. http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0018476