<br/>Antimicrobial peptides (AMPs) and cell penetrating peptides (CPPs) have been systematically investigated for decades. For example, well over 2000 natural and artificial AMPs have been characterized and information about them are organized into well-maintained databases. However, even given this knowledge, it is not clear how we should we think about them as a class of molecules. They are known to be cationic amphiphilic molecules but how are they different from other amphiphilic cationic molecules? Membrane permeation activity of AMPs are known to be important for host defense, but are there other functions besides membrane activity that are systematically enabled by their cationic charge and amphiphilicity? We offer a biased perspective on some emerging directions of inquiry by incorporating methods not usually applied to AMPs and CPPs, such as machine learning. We review recent progress by giving examples of what machine learning discovered against expectation as well as what it failed to anticipate in the context of quantitative immune activation.<br/>

Machine learning antimicrobial and cell penetrating peptides

2019 Spring National Meeting

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.