A QSAR modeling approach for predicting myeloid antimicrobial peptides with high sequence similarity

Abstract

Microbial resistance to conventional antibiotics has led to a surge in antimicrobial peptide (AMP) rational design initiatives that rely heavily on algorithms with good prediction accuracy and sensitivity. We present a quantitative structure-activity relationship (QSAR) approach for predicting activity of cathelicidins, an AMP family with broad-spectrum activity. The best multiple linear regression model built against Escherichia coli ATCC 25922 could accurately predict activity of three rationally designed peptides CP, DP, and Mapcon, having high sequence similarity. On further experimental validation of the rationally designed peptides, CP was found to exhibit high antimicrobial activity with negligible hemolysis. Here, we provide CP, an AMP with potential therapeutic applications and a family-based QSAR model for AMP prediction.

The multifaceted nature of antimicrobial peptides: current synthetic chemistry approaches and future directions

“…436 More recently, Idicula-Thomas and co-workers used a QSAR-based model to accurately predict the activity of rationally designed peptides derived from the cathelicidin AMP family against E. coli ATCC 25922. 437 Apart from AI and machine learning, other computational methods have demonstrated their efficacy to predict and identify potent antimicrobial peptides. 421 Methods including de novo (non-template sequence), linguistic, pattern insertion, and evolutionary/genetic algorithms in the area of AMPs have been summarised recently.…”

“… 436 More recently, Idicula-Thomas and co-workers used a QSAR-based model to accurately predict the activity of rationally designed peptides derived from the cathelicidin AMP family against E. coli ATCC 25922. 437 …”

Machine-Learning-Guided Peptide Drug Discovery: Development of GLP-1 Receptor Agonists with Improved Drug Properties

“…We identified three substitutions preventing fibril formation, 18Aib, 19Aib, and 21E which could be responsible for the formation of amyloid fibrils of GLP-1R agonists previously reported. 10,11 Previous studies using QSAR for peptide optimization have been limited to case studies on peptide families with large data sets publicly available such as antimicrobial peptides (AMPs), 36 Major histocompatibility complex (MHC) 37 and antitumor activity of peptides. 38 Other related studies have extracted information about QSAR from smaller publicly available data sets.…”

“…Previous studies using QSAR for peptide optimization have been limited to case studies on peptide families with large data sets publicly available such as antimicrobial peptides (AMPs), 36 Major histocompatibility complex (MHC) 37 and antitumor activity of peptides. 38 Other related studies have extracted information about QSAR from smaller publicly available data sets.…”