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

Boik JC, Newman RA - BMC Pharmacol. (2008)

Bottom Line: Safer and more effective mixtures of anticancer drugs are needed, and modeling can assist in this endeavor.Compared to the pseudomolecule approach, the virtual docking approach has the advantage of greater potential for biologic interpretation.This distinction may become important as virtual docking software becomes more accurate and docking results more closely resemble actual binding affinities.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Experimental Therapeutics, University of Texas MD Anderson Cancer Center, Houston, TX 77054, USA. jcboik@stanford.edu

ABSTRACT

Background: Safer and more effective mixtures of anticancer drugs are needed, and modeling can assist in this endeavor. This paper describes classification models that were constructed to predict which fixed-ratio mixtures created from a pool of 10 drugs would show a high degree of in-vitro synergism against H460 human lung cancer cells. One of the tested drugs was doxorubicin and the others were natural compounds including quercetin, curcumin, and EGCG. Explanatory variables were based on virtual docking profiles. Docking profiles for the 10 drugs were obtained for 1087 proteins using commercial docking software. The cytotoxicity of all 10 drugs and of 45 of the 1,013 possible mixtures was tested in the laboratory and synergism indices were generated using the MixLow method. Model accuracy was assessed using cross validation, as well as using predictions on a new set of 10 tested mixtures. Results were compared to models where explanatory variables were constructed using the pseudomolecule approach of Sheridan.

Results: On this data set, the pseudomolecule and docking data approach produce models of similar accuracy. Leave-one-out precision for the negative (highly synergistic) class and the positive (low- or non-synergistic) class was 0.73 and 0.80, respectively. Precision for a nonstandard leave-many-out cross validation procedure was 0.60 and 0.77 for the negative and positive classes, respectively.

Conclusion: Useful classification models can be constructed to predict drug synergism, even in those situations where a limited subset of component drugs can be tested. Compared to the pseudomolecule approach, the virtual docking approach has the advantage of greater potential for biologic interpretation. This distinction may become important as virtual docking software becomes more accurate and docking results more closely resemble actual binding affinities. This is the first published report of a model designed to predict the degree of in-vitro synergism based on the pseudomolecule or docking data approach.

Show MeSH

Related in: MedlinePlus

Doxorubicin dose reduction vs. mixture size and observed response for 25 doxorubicin-containing mixtures. The relative degree of dose reduction is indicated by marker size. The smallest circle corresponds to a doxorubicin dose reduction of 3.30 and the largest circle to a dose reduction of 10.87. Dose reduction is calculated from experimental data.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2526994&req=5

Figure 1: Doxorubicin dose reduction vs. mixture size and observed response for 25 doxorubicin-containing mixtures. The relative degree of dose reduction is indicated by marker size. The smallest circle corresponds to a doxorubicin dose reduction of 3.30 and the largest circle to a dose reduction of 10.87. Dose reduction is calculated from experimental data.

Mentions: The degree of synergism may not be the best index for identifying promising mixtures. An alternative index is the degree of dose reduction that can be achieved for a given drug. For example, one of the dose-limiting side effects of doxorubicin is cardiac toxicity [14]. To prevent this, mixtures could be chosen to minimize the dose of doxorubicin required for a given effect level. Based on the experimental data listed in Tables S.1 and S.2, doxorubicin dose-reduction values for the 25 doxorubicin-containing mixtures tested are plotted in Figure 1 against the number of drugs per mixture and observed synergism score. The mixture with the greatest dose reduction was M47, which contained doxorubicin, curcumin, and juglone. The IC50 of doxorubicin alone was 5.22 μL and that of M47 was 12.36 μL. The fraction of doxorubicin in the mixture was 0.039. Therefore, M47 allowed a 5.22/(12.36·0.039) = 10.9-fold reduction in doxorubicin concentration to achieve the same effect (50 percent inhibition) as doxorubicin used alone. Some larger mixtures also showed high dose reduction, even though they were less synergistic. For example, dose reduction values for M49 and M50, which had five and six components, respectively, were 9.1 and 10.8, respectively. The dose reduction value for M35, with seven drugs, was 9.7.


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

Boik JC, Newman RA - BMC Pharmacol. (2008)

Doxorubicin dose reduction vs. mixture size and observed response for 25 doxorubicin-containing mixtures. The relative degree of dose reduction is indicated by marker size. The smallest circle corresponds to a doxorubicin dose reduction of 3.30 and the largest circle to a dose reduction of 10.87. Dose reduction is calculated from experimental data.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2526994&req=5

Figure 1: Doxorubicin dose reduction vs. mixture size and observed response for 25 doxorubicin-containing mixtures. The relative degree of dose reduction is indicated by marker size. The smallest circle corresponds to a doxorubicin dose reduction of 3.30 and the largest circle to a dose reduction of 10.87. Dose reduction is calculated from experimental data.
Mentions: The degree of synergism may not be the best index for identifying promising mixtures. An alternative index is the degree of dose reduction that can be achieved for a given drug. For example, one of the dose-limiting side effects of doxorubicin is cardiac toxicity [14]. To prevent this, mixtures could be chosen to minimize the dose of doxorubicin required for a given effect level. Based on the experimental data listed in Tables S.1 and S.2, doxorubicin dose-reduction values for the 25 doxorubicin-containing mixtures tested are plotted in Figure 1 against the number of drugs per mixture and observed synergism score. The mixture with the greatest dose reduction was M47, which contained doxorubicin, curcumin, and juglone. The IC50 of doxorubicin alone was 5.22 μL and that of M47 was 12.36 μL. The fraction of doxorubicin in the mixture was 0.039. Therefore, M47 allowed a 5.22/(12.36·0.039) = 10.9-fold reduction in doxorubicin concentration to achieve the same effect (50 percent inhibition) as doxorubicin used alone. Some larger mixtures also showed high dose reduction, even though they were less synergistic. For example, dose reduction values for M49 and M50, which had five and six components, respectively, were 9.1 and 10.8, respectively. The dose reduction value for M35, with seven drugs, was 9.7.

Bottom Line: Safer and more effective mixtures of anticancer drugs are needed, and modeling can assist in this endeavor.Compared to the pseudomolecule approach, the virtual docking approach has the advantage of greater potential for biologic interpretation.This distinction may become important as virtual docking software becomes more accurate and docking results more closely resemble actual binding affinities.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Experimental Therapeutics, University of Texas MD Anderson Cancer Center, Houston, TX 77054, USA. jcboik@stanford.edu

ABSTRACT

Background: Safer and more effective mixtures of anticancer drugs are needed, and modeling can assist in this endeavor. This paper describes classification models that were constructed to predict which fixed-ratio mixtures created from a pool of 10 drugs would show a high degree of in-vitro synergism against H460 human lung cancer cells. One of the tested drugs was doxorubicin and the others were natural compounds including quercetin, curcumin, and EGCG. Explanatory variables were based on virtual docking profiles. Docking profiles for the 10 drugs were obtained for 1087 proteins using commercial docking software. The cytotoxicity of all 10 drugs and of 45 of the 1,013 possible mixtures was tested in the laboratory and synergism indices were generated using the MixLow method. Model accuracy was assessed using cross validation, as well as using predictions on a new set of 10 tested mixtures. Results were compared to models where explanatory variables were constructed using the pseudomolecule approach of Sheridan.

Results: On this data set, the pseudomolecule and docking data approach produce models of similar accuracy. Leave-one-out precision for the negative (highly synergistic) class and the positive (low- or non-synergistic) class was 0.73 and 0.80, respectively. Precision for a nonstandard leave-many-out cross validation procedure was 0.60 and 0.77 for the negative and positive classes, respectively.

Conclusion: Useful classification models can be constructed to predict drug synergism, even in those situations where a limited subset of component drugs can be tested. Compared to the pseudomolecule approach, the virtual docking approach has the advantage of greater potential for biologic interpretation. This distinction may become important as virtual docking software becomes more accurate and docking results more closely resemble actual binding affinities. This is the first published report of a model designed to predict the degree of in-vitro synergism based on the pseudomolecule or docking data approach.

Show MeSH
Related in: MedlinePlus