Limits...
Molecular evolution of a peptide GPCR ligand driven by artificial neural networks.

Bandholtz S, Wichard J, Kühne R, Grötzinger C - PLoS ONE (2012)

Bottom Line: 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.

View Article: PubMed Central - PubMed

Affiliation: Charité-Universitätsmedizin Berlin, Campus Virchow-Klinikum, Department of Hepatology and Gastroenterology and Molecular Cancer Research Center (MKFZ), Tumor Targeting Lab, Berlin, Germany.

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.

Show MeSH

Related in: MedlinePlus

As peptide sequences evolve, metabolic stability of the peptides improves while their biological activity is retained. Upper panel (A+B):depiction of EC50 values of the receptor activating potency (A) and of the metabolic stability (B,  = t1/2) for the three GNN-based optimization rounds. Both graphs show all the peptides from a given round, sorted according to their activity in the parameter on the y axis. With receptor activity, low EC50 values are favorable, while in the stability parameter t1/2, high values are to be achieved. Lower panel (C): Peptide sequence comparisons by multiple alignments illustrate the evolution over the different steps of the process. Four sets of alignments represent the start population ( = input) and three optimization rounds.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3351444&req=5

pone-0036948-g003: As peptide sequences evolve, metabolic stability of the peptides improves while their biological activity is retained. Upper panel (A+B):depiction of EC50 values of the receptor activating potency (A) and of the metabolic stability (B,  = t1/2) for the three GNN-based optimization rounds. Both graphs show all the peptides from a given round, sorted according to their activity in the parameter on the y axis. With receptor activity, low EC50 values are favorable, while in the stability parameter t1/2, high values are to be achieved. Lower panel (C): Peptide sequence comparisons by multiple alignments illustrate the evolution over the different steps of the process. Four sets of alignments represent the start population ( = input) and three optimization rounds.

Mentions: Round 1 to 3 of the optimization process included at least 34 different sequences each from a GNN model as described above (Table S1). These variants were synthesized as peptides with a free acid function at their carboxy terminus and were subjected to EC50 determination for agonistic activity on HEK293 cells expressing CMKLR1. In these subsequent rounds of screening, we explored the capacity for the exchange against other (natural) L-amino acids and also stabilizing D-amino acids in the activation assay, as well as the metabolic stability of the various compounds. As can be seen from the comparison with data from the native nonamer chemerin-9 (Table 1, bottom line), and with results from round 0, the following rounds of optimization yielded a marked improvement in metabolic stability while retaining high agonistic activity. Quite obvious is the gradual enhancement over the three rounds: both bioactivity (EC50) and half-life of the peptides improve from first to third cycle (Fig. 3 A and B).


Molecular evolution of a peptide GPCR ligand driven by artificial neural networks.

Bandholtz S, Wichard J, Kühne R, Grötzinger C - PLoS ONE (2012)

As peptide sequences evolve, metabolic stability of the peptides improves while their biological activity is retained. Upper panel (A+B):depiction of EC50 values of the receptor activating potency (A) and of the metabolic stability (B,  = t1/2) for the three GNN-based optimization rounds. Both graphs show all the peptides from a given round, sorted according to their activity in the parameter on the y axis. With receptor activity, low EC50 values are favorable, while in the stability parameter t1/2, high values are to be achieved. Lower panel (C): Peptide sequence comparisons by multiple alignments illustrate the evolution over the different steps of the process. Four sets of alignments represent the start population ( = input) and three optimization rounds.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3351444&req=5

pone-0036948-g003: As peptide sequences evolve, metabolic stability of the peptides improves while their biological activity is retained. Upper panel (A+B):depiction of EC50 values of the receptor activating potency (A) and of the metabolic stability (B,  = t1/2) for the three GNN-based optimization rounds. Both graphs show all the peptides from a given round, sorted according to their activity in the parameter on the y axis. With receptor activity, low EC50 values are favorable, while in the stability parameter t1/2, high values are to be achieved. Lower panel (C): Peptide sequence comparisons by multiple alignments illustrate the evolution over the different steps of the process. Four sets of alignments represent the start population ( = input) and three optimization rounds.
Mentions: Round 1 to 3 of the optimization process included at least 34 different sequences each from a GNN model as described above (Table S1). These variants were synthesized as peptides with a free acid function at their carboxy terminus and were subjected to EC50 determination for agonistic activity on HEK293 cells expressing CMKLR1. In these subsequent rounds of screening, we explored the capacity for the exchange against other (natural) L-amino acids and also stabilizing D-amino acids in the activation assay, as well as the metabolic stability of the various compounds. As can be seen from the comparison with data from the native nonamer chemerin-9 (Table 1, bottom line), and with results from round 0, the following rounds of optimization yielded a marked improvement in metabolic stability while retaining high agonistic activity. Quite obvious is the gradual enhancement over the three rounds: both bioactivity (EC50) and half-life of the peptides improve from first to third cycle (Fig. 3 A and B).

Bottom Line: 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.

View Article: PubMed Central - PubMed

Affiliation: Charité-Universitätsmedizin Berlin, Campus Virchow-Klinikum, Department of Hepatology and Gastroenterology and Molecular Cancer Research Center (MKFZ), Tumor Targeting Lab, Berlin, Germany.

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.

Show MeSH
Related in: MedlinePlus