Training Neural Network Models Using Molecular Dynamics Simulation Results to Efficiently Predict Cyclic Hexapeptide Structural Ensembles
Open Access
- 26 May 2023
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 19 (14) , 4757-4769
Abstract
Cyclic peptides have emerged as a promising class of therapeutics. However, their de novo design remains challenging, and many cyclic peptide drugs are simply natural products or their derivatives. Most cyclic peptides, including the current cyclic peptide drugs, adopt multiple conformations in water. The ability to characterize cyclic peptide structural ensembles would greatly aid their rational design. In a previous pioneering study, our group demonstrated that using molecular dynamics results to train machine learning models can efficiently predict structural ensembles of cyclic pentapeptides. Using this method, which was termed StrEAMM (Structural Ensembles Achieved by Molecular Dynamics and Machine Learning), linear regression models were able to predict the structural ensembles for an independent test set with R2 = 0.94 between the predicted populations for specific structures and the observed populations in molecular dynamics simulations for cyclic pentapeptides. An underlying assumption in these StrEAMM models is that cyclic peptide structural preferences are predominantly influenced by neighboring interactions, namely, interactions between (1,2) and (1,3) residues. Here we demonstrate that for larger cyclic peptides such as cyclic hexapeptides, linear regression models including only (1,2) and (1,3) interactions fail to produce satisfactory predictions (R2 = 0.47); further inclusion of (1,4) interactions leads to moderate improvements (R2 = 0.75). We show that when using convolutional neural networks and graph neural networks to incorporate complex nonlinear interaction patterns, we can achieve R2 = 0.97 and R2 = 0.91 for cyclic pentapeptides and hexapeptides, respectively.Keywords
Funding Information
- National Institute of General Medical Sciences (R01GM124160)
This publication has 58 references indexed in Scilit:
- Chemical and structural lessons from recent successes in protein–protein interaction inhibition (2P2I)Current Opinion in Chemical Biology, 2011
- Constructing ensembles for intrinsically disordered proteinsCurrent Opinion in Structural Biology, 2011
- Improved side‐chain torsion potentials for the Amber ff99SB protein force fieldProteins: Structure, Function, and Bioinformatics, 2010
- Working outside the protein‐synthesis rules: insights into non‐ribosomal peptide synthesisJournal of Peptide Science, 2009
- A Bias-Exchange Approach to Protein FoldingThe Journal of Physical Chemistry B, 2007
- Energy landscape of a small peptide revealed by dihedral angle principal component analysisProteins: Structure, Function, and Bioinformatics, 2004
- UCSF Chimera—A visualization system for exploratory research and analysisJournal of Computational Chemistry, 2004
- Learning from Nature's Drug Factories: Nonribosomal Synthesisof MacrocyclicPeptidesJournal of Bacteriology, 2003
- Comparison of simple potential functions for simulating liquid waterThe Journal of Chemical Physics, 1983
- The Generation of a Unique Machine Description for Chemical Structures-A Technique Developed at Chemical Abstracts Service.Journal of Chemical Documentation, 1965