The Use of DeepQSAR Models for the Discovery of Peptides With Enhanced Antimicrobial and Antibiofilm Potential.

Abstract

Increasing concerns regarding prolonged antibiotic usage have spurred the search for alternative treatments. Antimicrobial peptides (AMPs), first discovered in the 1980s, have exhibited significant potential against a broad range of bacteria. Short-sequenced AMPs are abundant in nature and present across various organisms. Recently, machine learning technologies such as Quantitative Structure Activity Relationships (QSAR) have enabled expedited discovery of potential AMPs with broad-spectrum antibacterial activity as the amount of available AMP training data increases. Among those, Deep QSAR has recently emerged as a distinct type of application that utilizes conventional molecular descriptors in conjunction with more powerful deep learning (DL) models. Here, we demonstrate the power of Deep QSAR in predicting broad-spectrum AMP activity. Using a recurrent neural network-based QSAR model, we achieved nearly 90% fivefold cross-validated accuracy in classifying AMP activity. Using the developed approach, we designed 98 novel peptides, of which 36 experimentally demonstrated more effective antibiofilm activity and 26 peptides exhibited stronger antimicrobial activity compared to a well-characterized host defense peptide IDR-1018, which was demonstrated to possess broad spectrum antibiofilm activity against a wide range of bacterial pathogens and a previous computer-aided peptide design study employing IDR-1018 derivatives successfully identified novel peptides with enhanced antibiofilm activity. Notably, 22 of those peptides demonstrated improvements of both antimicrobial and, particularly, antibiofilm properties, making them suitable prototypes for preclinical development and demonstrating efficacy of DeepQSAR modeling in identifying novel and potent AMPs.