HelixGAN a deep-learning methodology for conditional de novo design of α-helix structures
Open Access
- 1 January 2023
- journal article
- research article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 39 (1)
Abstract
Protein and peptide engineering has become an essential field in biomedicine with therapeutics, diagnostics, and synthetic biology applications. Helices are both abundant structural feature in proteins and comprise a major portion of bioactive peptides. Precise design of helices for binding or biological activity is still a challenging problem. Here, we present HelixGAN, the first generative adversarial network method to generate de novo left-handed and right-handed alpha-helix structures from scratch at an atomic level. We developed a gradient-based search approach in latent space to optimize the generation of novel α-helical structures by matching the exact conformations of selected hotspot residues. The designed α-helical structures can bind specific targets or activate cellular receptors. There is a significant agreement between the helix structures generated with HelixGAN and PEP-FOLD, a well-known de novo approach for predicting peptide structures from amino acid sequences. HelixGAN outperformed RosettaDesign, and our previously developed structural similarity method to generate D-peptides matching a set of given hotspots in a known L-peptide. As proof of concept, we designed a novel D-GLP1_1 analog that matches the conformations of critical hotspots for the GLP1 function. MD simulations revealed a stable binding mode of the D-GLP1_1 analog coupled to the GLP1 receptor. This novel D-peptide analog is more stable than our previous D-GLP1 design along the MD simulations. We envision HelixGAN as a critical tool for designing novel bioactive peptides with specific properties in the early stages of drug discovery. https://github.com/xxiexuezhi/helix_gan Supplementary data are available at Bioinformatics online.Keywords
Funding Information
- Canadian Institute for Health Research (#PJT-166008, #PJT-153279)
This publication has 34 references indexed in Scilit:
- A clinical review of GLP-1 receptor agonists: efficacy and safety in diabetes and beyondDrugs in Context, 2015
- Glucagon-like Peptide-1 (GLP-1) Analogs: Recent Advances, New Possibilities, and Therapeutic ImplicationsJournal of Medicinal Chemistry, 2014
- Hot spots in protein–protein interfaces: Towards drug discoveryProgress in Biophysics and Molecular Biology, 2014
- MECHANISMS IN ENDOCRINOLOGY: Bile acid sequestrants in type 2 diabetes: potential effects on GLP1 secretionEuropean Journal of Endocrinology, 2014
- Basics and Recent Advances in Peptide and Protein Drug DeliveryTherapeutic Delivery, 2013
- Principles for designing ideal protein structuresNature, 2012
- The structure and function of the glucagon‐like peptide‐1 receptor and its ligandsBritish Journal of Pharmacology, 2012
- CHARMM‐GUI: A web‐based graphical user interface for CHARMMJournal of Computational Chemistry, 2008
- d-AMINO ACIDS IN ANIMAL PEPTIDESAnnual Review of Biochemistry, 1997
- Comparison of simple potential functions for simulating liquid waterThe Journal of Chemical Physics, 1983