Prediction of Inhibitory Activity of Epidermal Growth Factor Receptor Inhibitors Using Grid Search-Projection Pursuit Regression Method
2011

Predicting EGFR Inhibitors Using QSAR Models

Sample size: 128 publication 10 minutes Evidence: moderate

Author Information

Author(s): Du Hongying, Hu Zhide, Bazzoli Andrea, Zhang Yang

Primary Institution: Center for Computational Medicine and Bioinformatics, University of Michigan

Hypothesis

Can we develop reliable QSAR models to predict the inhibitory activity of quinazoline derivatives against EGFR?

Conclusion

The study successfully developed QSAR models that predict the inhibitory activity of quinazoline derivatives against EGFR, demonstrating the importance of structural features in drug design.

Supporting Evidence

  • The study developed two QSAR models using best multi-linear regression and grid-search assisted projection pursuit regression methods.
  • The models showed a strong correlation between the structural features of quinazoline derivatives and their inhibitory activity against EGFR.
  • The predictive ability of the GS-PPR model was superior to that of the BMLR model.

Takeaway

Scientists created computer models to guess how well certain drugs can stop a cancer-related protein from working, helping to find new medicines faster.

Methodology

The study used quantitative structure–activity relationship (QSAR) models based on known quinazoline derivatives to predict their inhibitory activity against EGFR.

Potential Biases

Potential bias in the selection of molecular descriptors and the training/test set division.

Limitations

The study focused only on quinazoline derivatives and may not generalize to other types of compounds.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1371/journal.pone.0022367

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication