IAM Graph Database

This database defined from the AIDS Antiviral Screen Database of Active Compounds is composed of 2000 chemical compounds some of them being disconnected. These chemical compounds have been screened as active or inactive against HIV and they are split into three different sets:

A train set composed of 250 compounds used to train SVM.

A validation set composed of 250 compounds used to find parameters giving the best accuracy result.

A test set composed of remaining 1500 compounds used to test the classification model.

Results on AIDS dataset.

Method
Classification accuracy (%)

(1)
Riesen and Bunke (2008)
97.3

(2)
Suard et al. (2002)
98.5

(3)
Vishwanathan et al. (2010)
98.5

(4)
Neuhaus and Bunke (2007)
99.7

(5)
Riesen et al. (2007)
98.2

(6)
Graph Laplacian kernel
99.3

(7)
Gauzere el al. (2012)
99.1

References

Gaüzère, B., et al. Two new graphs kernels in chemoinformatics. Pattern Recognition Lett. (2012), http://dx.doi.org/10.1016/j.patrec.2012.03.020.

Neuhaus, M., Bunke, H., 2007. Bridging the Gap between Graph Edit Distance and Kernel Machines. World Scientific Pub Co Inc..

Riesen, K., Neuhaus, M., Bunke, H., 2007. Graph embedding in vector spaces by means of prototype selection. In: Escolano, F., Vento, M. (Eds.), 6th IAPR-TC15 Internat. Workshop GbRPR 2007. IAPR TC15. Springer-Verlag, pp. 383–393.

Riesen, K., Bunke, H., 2008. Iam graph database repository for graph based pattern recognition and machine learning. In: Proc. 2008 Joint IAPR Internat. Workshop on Structural, Syntactic, and Statistical Pattern Recognition. SSPR & SPR ’08. Springer-Verlag, Berlin, Heidelberg, pp. 287–297.

Suard, F., Rakotomamonjy, A., Bensrhair, A., 2002. Kernel on bag of paths for measuring similarity of shapes. In: European Symposium on Artificial Neural Networks. pp. 355–360.

Vishwanathan, S., Borgwardt, K.M., Kondor, I.R., Schraudolph, N.N., 2010. Graph kernels. J. Machine Learn. Res. 11, 1201–1242.