Modeling ACE-Inhibitory Peptides Using Artificial Neural Networks
Author Information
Author(s): He Ronghai, Ma Haile, Zhao Weirui, Qu Wenjuan, Zhao Jiewen, Luo Lin, Zhu Wenxue
Primary Institution: Jiangsu University
Hypothesis
Can a QSAR model built with an artificial neural network predict the ACE-inhibitory activity of peptides?
Conclusion
The study found that the C-terminal of peptides is crucial for ACE-inhibitory activity, and defatted wheat germ protein is a suitable source for producing such peptides.
Supporting Evidence
- The QSAR model achieved a correlation coefficient of R = 0.928.
- Hydrophobic amino acids at the C-terminal significantly enhance ACE-inhibitory activity.
- Alcalase was identified as a suitable protease for producing ACE-inhibitory peptides from defatted wheat germ protein.
Takeaway
This study shows that certain proteins can be used to make special peptides that help lower blood pressure, and the way these peptides are built is really important.
Methodology
A QSAR model was built using an artificial neural network based on structural and activity data of 58 dipeptides.
Limitations
The study primarily focused on dipeptides and may not generalize to larger peptides or proteins.
Statistical Information
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website