Prediction of Anuran Antimicrobial Peptides Using AdaBoost and Improved PSSM Profiles.

Antimicrobial resistance is one of our most serious health threats. Antimicrobial peptides (AMPs) are natural immune molecules that are commonly found in organisms. Over the last few decades several AMPs have been approved as drugs by FDA. We collected antimicrobial peptide sequences from the DAPA database and constructed a benchmark dataset. And we used PSSM profiles and spatial autocorrelation to design a new feature extraction method. This method can generate a smoother and standardized feature matrix and can find correlations between amino acids at different positions, helping to identify sequences with antimicrobial activity. The results show that the performance of our method is better than state-of-the-art feature extraction methods, and it can be used for many different classifiers.