A classification model to predict synergism/antagonism of cytotoxic mixtures using protein-drug docking scores
2008

Predicting Drug Synergism with Docking Scores

Sample size: 45 publication Evidence: moderate

Author Information

Author(s): Boik John C, Newman Robert A

Primary Institution: Department of Experimental Therapeutics, University of Texas M. D. Anderson Cancer Center

Hypothesis

Can classification models predict which drug mixtures will show synergism against cancer cells using protein-drug docking scores?

Conclusion

The study successfully developed classification models that can predict drug synergism using virtual docking data.

Supporting Evidence

  • The study tested 45 mixtures derived from a pool of 10 drugs.
  • Models were validated using leave-one-out and leave-many-out cross-validation methods.
  • Five out of ten new mixtures tested in the lab were found to be highly synergistic.

Takeaway

Scientists created a way to guess which combinations of cancer drugs work better together by looking at how they interact with proteins.

Methodology

The study used protein-drug docking scores and a classification model to predict the synergism of drug mixtures tested in vitro.

Potential Biases

Potential misclassification of drug interactions due to limitations in docking software accuracy.

Limitations

The models may not accurately predict synergism for all drug combinations, particularly for doxorubicin-containing mixtures.

Participant Demographics

The study focused on drug mixtures tested against H460 human lung cancer cells.

Statistical Information

P-Value

1.0E-07

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2210-8-13

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication