Abstract

Peptide ligands of G protein-coupled receptors constitute valuable natural lead structures for the development of highly selective drugs and high-affinity tools to probe ligand-receptor interaction. Currently, pharmacological and metabolic modification of natural peptides involves either an iterative trial-and-error process based on structure-activity relationships or screening of peptide libraries that contain many structural variants of the native molecule. Here, we present a novel neural network architecture for the improvement of metabolic stability without loss of bioactivity. In this approach the peptide sequence determines the topology of the neural network and each cell corresponds one-to-one to a single amino acid of the peptide chain. Using a training set, the learning algorithm calculated weights for each cell. The resulting network calculated the fitness function in a genetic algorithm to explore the virtual space of all possible peptides. The network training was based on gradient descent techniques which rely on the efficient calculation of the gradient by back-propagation. After three consecutive cycles of sequence design by the neural network, peptide synthesis and bioassay this new approach yielded a ligand with 70fold higher metabolic stability compared to the wild type peptide without loss of the subnanomolar activity in the biological assay. Combining specialized neural networks with an exploration of the combinatorial amino acid sequence space by genetic algorithms represents a novel rational strategy for peptide design and optimization.

Highlights

  • Gprotein-coupled receptors (GPCRs) regulate vital cellular functions such as energy and ion homeostasis, cellular adhesion, motility and proliferation [1,2]

  • Graph Neural Networks and Genetic Algorithms The GNN was designed to reflect the topology of a peptide by mimicking the sequence and the type of the constituting amino acids

  • We presented a Graph Neural Network (GNN) that utilizes individual processing elements as building blocks with a one-toone correspondence to the amino acids of the peptide

Read more

Summary

Introduction

Gprotein-coupled receptors (GPCRs) regulate vital cellular functions such as energy and ion homeostasis, cellular adhesion, motility and proliferation [1,2]. At least one third of all currently marketed drugs are directed against GPCRs, while due to the lack of highly potent and stable ligands many other receptors of this protein superfamily still await their pharmaceutical use [4] In this target class, structure-based drug discovery using rational design is still hampered by the small number of available 3D data for GPCRs. When this study was initiated only five x-ray structures of GPCRS were known: those of of two rhodopsins (PDB 1F88, 2Z73) [5,6], of the b2- and b1adrenergic receptors (PDB 2RH1, 2VT4) [7,8] and the structure of the A2A adenosine receptor (PDB 2RH1) [9]. For this stepwise improvement of molecular parameters, no a priori knowledge of quantitative structure-activity relationships (QSAR) is required and the whole process may take place in vitro, in vivo or even in silico by computer-based algorithms

Methods
Results
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.