Efficient Computational Framework for Target-Specific Active Peptide Discovery: A Case Study on IL-17C Targeting...

Area of Science:

• Computational chemistry and drug discovery
• Peptide therapeutics and bioinformatics

Background:

• Development of targeted active peptides is crucial for pharmaceutical growth.
• Existing methods for peptide discovery can be time-consuming and inefficient.

Purpose of the Study:

• To present an efficient computational framework for discovering target-specific active peptides.
• To demonstrate the framework's utility by targeting interleukin-17C (IL-17C).

Main Methods:

• Combined a conditional variational autoencoder (CVAE) for peptide generation with a Transformer-CNN classifier (TCPP) for screening.
• Employed a library-based in vitro selection strategy to construct an active cyclic peptide library against IL-17C.
• Trained the CVAE on preprocessed peptide data and utilized TCPP to filter generated peptides.

Main Results:

• Six candidate peptides were computationally predicted and subsequently synthesized.
• Four of the synthesized peptides demonstrated significant binding affinity to IL-17C.
• The computational framework successfully identified potent IL-17C inhibitors.

Conclusions:

• The developed computational framework offers an efficient, one-stop solution for target-specific active peptide discovery.
• This approach is expected to accelerate the peptide drug development pipeline.
• The study validates the framework's potential in identifying novel peptide therapeutics.