Modeling the QSAR of ACE-Inhibitory Peptides with ANN and Its Applied Illustration
2012

Modeling ACE-Inhibitory Peptides Using Artificial Neural Networks

Sample size: 58 publication Evidence: moderate

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)

10.1155/2012/620609

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication