Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2012;13(6):7015-7037.
doi: 10.3390/ijms13067015. Epub 2012 Jun 7.

Toward the prediction of FBPase inhibitory activity using chemoinformatic methods

Ming Hao  1 , Shuwei Zhang  1 , Jieshan Qiu  1
Affiliations

Toward the prediction of FBPase inhibitory activity using chemoinformatic methods

Ming Hao et al. Int J Mol Sci. 2012.

Abstract

Currently, Chemoinformatic methods are used to perform the prediction for FBPase inhibitory activity. A genetic algorithm-random forest coupled method (GA-RF) was proposed to predict fructose 1,6-bisphosphatase (FBPase) inhibitors to treat type 2 diabetes mellitus using the Mold(2) molecular descriptors. A data set of 126 oxazole and thiazole analogs was used to derive the GA-RF model, yielding the significant non-cross-validated correlation coefficient r(2) (ncv) and cross-validated r(2) (cv) values of 0.96 and 0.67 for the training set, respectively. The statistically significant model was validated by a test set of 64 compounds, producing the prediction correlation coefficient r(2) (pred) of 0.90. More importantly, the building GA-RF model also passed through various criteria suggested by Tropsha and Roy with r(2) (o) and r(2) (m) values of 0.90 and 0.83, respectively. In order to compare with the GA-RF model, a pure RF model developed based on the full descriptors was performed as well for the same data set. The resulting GA-RF model with significantly internal and external prediction capacities is beneficial to the prediction of potential oxazole and thiazole series of FBPase inhibitors prior to chemical synthesis in drug discovery programs.

Keywords: FBPase inhibitor; chemoinformatics methods; genetic algorithm; random forest.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Self-organizing map (SOM) analysis for fructose 1,6-bisphosphatase (FBPase) inhibitors, where the black dot denotes the training set and the red asterisk stands for the test set.
Figure 2
Figure 2
The scatter plots of actual and predicted activity by GA-RF and RF models.
Figure 3
Figure 3
Boxplot of 50 replications of OOB estimation (r2oob) at various values of mtry. Horizontal lines inside the boxes are the median correlation.
Figure 4
Figure 4
Comparison of mean squared errors from out-of-bag (OOB) set, test set and training set as the number of trees increases for FBPase inhibitors.
Figure 5
Figure 5
Variable importance plot from GA-RF. The first two important descriptors are surrounded by red frames.
See this image and copyright information in PMC

References

    1. King H., Aubert R.E., Herman W.H. Global burden of diabetes, 1995–2025: Prevalence, numerical estimates, and projections. Diabetes Care. 1998;21:1414–1431. - PubMed
    1. Zhang B.B., Moller D.E. New approaches in the treatment of type 2 diabetes. Curr. Opin. Chem. Biol. 2000;4:4614–4667. - PubMed
    1. Reaven G.M. Pathophysiology of insulin resistance in human disease. Physiol. Rev. 1995;75:4734–4786. - PubMed
    1. Haffner S.M., Lehto S., Rönnemaa T., Pyörälä K., Laakso M. Mortality from coronary heart disease in subjects with type 2 diabetes and in nondiabetic subjects with and without prior myocardial infarction. N. Engl. J. Med. 1998;339:2292–2234. - PubMed
    1. Moller D.E. New drug targets for type 2 diabetes and the metabolic syndrome. Nature. 2001;414:8218–8227. - PubMed

Publication types

LinkOut - more resources