Identification of tissue-specific targeting peptide.

Area of Science:

• Biotechnology
• Computational Biology
• Molecular Biology

Background:

• Phage display is a powerful technique for identifying peptides with specific binding properties.
• Targeting specific tissues is crucial for effective drug delivery and minimizing off-target effects.

Purpose of the Study:

• To identify tissue-targeting peptide sets for various organs using phage display.
• To develop and apply machine learning models for predicting tissue-specific targeting activity of peptides based on sequence information.
• To isolate peptide groups capable of selective targeting to specific tissues.

Main Methods:

• Phage display technique was employed to identify peptide sets targeting specific tissues.
• Four machine learning models were utilized to predict tissue-specific targeting activity from peptide sequences.
• Sequence similarity analysis was performed to select representative targeting peptides, such as the liver-specific peptide "DKNLQLH".

Main Results:

• Identified peptide sets targeting bone-marrow dendritic cells, kidney, liver, lung, spleen, and visceral adipose tissue.
• Successfully developed machine learning models capable of predicting tissue-specific peptide targeting.
• Isolated peptide groups demonstrating selective targeting capabilities for specific tissues.
• Identified "DKNLQLH" as a representative liver-specific targeting peptide with homology to known protein ligands.

Conclusions:

• The developed machine learning models can rapidly evaluate and predict tissue-specific targeting peptides.
• These models are anticipated to be applicable for predicting peptides that recognize endothelial markers of target tissues.
• This approach facilitates the discovery of novel peptides for targeted drug delivery and diagnostics.