Machine learning-guided discovery and design of non-hemolytic peptides
06 de octubre de 2020
Te invitamos a leer el artículo "Machine learning-guided discovery and design of non-hemolytic peptides" publicado en Scientific Reports Nature, a cargo del profesor investigador Dr. Fabien Plisson y su equipo de trabajo de la UGA-Langebio.
Autores: Fabien Plisson1, Obed Ramírez-Sánchez2 & Cristina Martínez-Hernández2.
- CONACYT, Unidad de Genómica Avanzada, Laboratorio Nacional de Genómica para la Biodiversidad (Langebio),Centro de Investigación Y de Estudios Avanzados del IPN, 36824 Irapuato, Guanajuato, Mexico.
- Unidad de Genómica Avanzada, Laboratorio Nacional de Genómica para la Biodiversidad (Langebio), Centro de Investigación Y de Estudios Avanzados del IPN, 36824 Irapuato, Guanajuato, Mexico.
Felicitamos al estudiantado y profesorado que contribuyeron en esta investigación por su arduo trabajo.
Abstract: Reducing hurdles to clinical trials without compromising the therapeutic promises of peptide candidates becomes an essential step in peptide-based drug design. Machine-learning models are cost-effective and time-saving strategies used to predict biological activities from primary sequences. Their limitations lie in the diversity of peptide sequences and biological information within these models. Additional outlier detection methods are needed to set the boundaries for reliable predictions; the applicability domain. Antimicrobial peptides (AMPs) constitute an extensive library of peptides offering promising avenues against antibiotic-resistant infections. Most AMPs present in clinical trials are administrated topically due to their hemolytic toxicity. Here we developed machine learning models and outlier detection methods that ensure robust predictions for the discovery of AMPs and the design of novel peptides with reduced hemolytic activity. Our best models, gradient boosting classifiers, predicted the hemolytic nature from any peptide sequence with 95–97% accuracy. Nearly 70% of AMPs were predicted as hemolytic peptides. Applying multivariate outlier detection models, we found that 273 AMPs (~ 9%) could not be predicted reliably. Our combined approach led to the discovery of 34 high-confidence non-hemolytic natural AMPs, the de novo design of 507 non-hemolytic peptides, and the guidelines for non-hemolytic peptide design.