Discovering Novel Antimicrobial Peptides in Generative Adversarial Network

Due to the growing number of clinical antibiotic resistance cases in recent years, novel antimicrobial peptides (AMPs) can become ideal for next-generation antibiotics. This study trained a deep convolutional generative adversarial network (GAN) with known AMPs to generate novel AMP candidates. The quality of the GAN-designed peptides was evaluated in silico, and eight of them named GAN-pep 1[~]8 were chosen to be synthesized for further experiments. Disk diffusion testing and minimum inhibitory concentration (MIC) determination were used to determine the antibacterial effects of the synthesized GAN-designed peptides. Seven out of the eight synthesized GAN-designed peptides showed antibacterial activities. Additionally, GAN-pep 3 and GAN-pep 8 had a broad spectrum of antibacterial effects. Both of them were also effective against antibiotic-resistant bacteria strains such as methicillin-resistant Staphylococcus aureus (S. aureus) and carbapenem-resistant Pseudomonas aeruginosa (P. aeruginosa). GAN-pep 3, the most promising GAN-designed peptide candidate, had low MICs against all the tested bacteria.