TargetAntiAngio: A Sequence-Based Tool for the Prediction and Analysis of Anti-Angiogenic Peptides

Area of Science:

• Biochemistry
• Computational Biology
• Oncology

Background:

• Angiogenesis, the formation of new blood vessels, is vital for solid tumor growth and a key target for cancer therapies.
• Identifying anti-angiogenic peptides is crucial for developing novel anti-cancer drugs and understanding their mechanisms.
• Existing methods for identifying anti-angiogenic peptides require improvement in efficiency and interpretability.

Purpose of the Study:

• To develop an efficient and interpretable computational model, TargetAntiAngio, for predicting and characterizing anti-angiogenic peptides.
• To leverage peptide features and machine learning for accurate anti-angiogenic peptide identification.
• To provide insights into the structural and functional characteristics of anti-angiogenic peptides.

Main Methods:

• Development of the TargetAntiAngio model using a random forest classifier.
• Integration of various classes of peptide features into the model.
• Validation using an independent benchmark dataset to assess predictive accuracy.

Main Results:

• TargetAntiAngio achieved an average accuracy of 77.50% in identifying anti-angiogenic peptides.
• The model demonstrated superior performance compared to existing anti-angiogenic peptide identification methods.
• Key characteristics of anti-angiogenic peptides were identified, including the role of cysteine residues and disulfide bonds.

Conclusions:

• TargetAntiAngio is an effective computational tool for predicting anti-angiogenic peptides.
• Disulfide bond forming Cys residues, particularly at the C-terminal domain, are important for inhibiting angiogenesis and tumor growth.
• Cyclic disulfide-rich peptides exhibit enhanced selectivity, stability, and anti-angiogenic properties, offering potential for cancer therapy.