Machine Learning Guided Discovery of Non‐Hemolytic Membrane Disruptive Anticancer Peptides

• Published in: ChemMedChem Vol. 17; no. 17; pp. e202200291 - n/a
• Main Authors: Zakharova, Elena, Orsi, Markus, Capecchi, Alice, Reymond, Jean‐Louis
• Format: Journal Article
• Language: English
• Published: Germany Wiley Subscription Services, Inc 05-09-2022
• Subjects: anticancer peptides; Antiinfectives and antibacterials; Antimicrobial peptides; Antineoplastic Agents - chemistry; Antineoplastic Agents - pharmacology; Cell Death; chemical space; genetic algorithm; Genetic algorithms; Helices; Helicity; Hemolysis; Humans; Learning algorithms; Machine Learning; Membranes; Neural networks; peptide design; Peptides; Recurrent neural networks; genetic algorithm; peptide design; chemical space; machine learning; anticancer peptides
• ISSN: 1860-7179; 1860-7187; 1860-7187
• DOI: 10.1002/cmdc.202200291

Most antimicrobial peptides (AMPs) and anticancer peptides (ACPs) fold into membrane disruptive cationic amphiphilic α‐helices, many of which are however also unpredictably hemolytic and toxic. Here we exploited the ability of recurrent neural networks (RNN) to distinguish active from inactive and non‐hemolytic from hemolytic AMPs and ACPs to discover new non‐hemolytic ACPs. Our discovery pipeline involved: 1) sequence generation using either a generative RNN or a genetic algorithm, 2) RNN classification for activity and hemolysis, 3) selection for sequence novelty, helicity and amphiphilicity, and 4) synthesis and testing. Experimental evaluation of thirty‐three peptides resulted in eleven active ACPs, four of which were non‐hemolytic, with properties resembling those of the natural ACP lasioglossin III. These experiments show the first example of direct machine learning guided discovery of non‐hemolytic ACPs.
Using machine learning models trained with bioactive peptides from DBAASP, we designed new non‐hemolytic anticancer peptides (ACPs). The subsequently selected hit‐compounds A1 and B1 showed IC50 activities with low micromolar range against several cancer cell lines, having adopted amphiphilic α‐helical conformations. Further biological evaluations revealed membranolytic and mitochondria targeting properties of selected anticancer peptides.