| Download Focused library sdf * mol2 | Score file | Contact |

The ubiquitin/proteasome system plays a major role in overall protein turnover, in eukaryotic cells including plasmodia. The 26s proteasome is a large multi-meric, ATP dependent, non-lysosomal assembly that controls degradation of wide range of cellular substrates and processes. 20s beta subunit is the catalytic core of the 26s proteasome assembly, and hence most of the inhibitors developed are being targeted toward this component. It has been shown that 20S proteasome is expressed and catalytically active in plasmodia and treatment with proteasome inhibitors arrests parasite growth. In this work, we have trained SVM based classifier using 170 molecular descriptors on 64 inhibitors and 208 putative non-inhibitors of 20s proteasome. The non-linear classifier based on Radial Basis Function (RBF) kernel yielded highest classification accuracy as compared to the linear classifier. The best classifier had 5-fold Cross-Validation (CV) accuracy of 97% and Area Under Curve (AUC) of 0.99, which is quite high. Additional validation of the classifier over an independent test dataset showed an accuracy, sensitivity, specificity and Matthews Correlation Coefficient (MCC) of 98%, 93%, 100 % and 0.96 respectively.

=== If you are using the data please cite: Subramaniam S, Mehrotra M, Gupta D: Support Vector Machine based prediction of P. falciparum proteasome inhibitors and development of focused library by molecular docking. Combinatorial Chemistry & High Throughput Screening 2011, 14:898-907

International Center for Genetic Engineering and Biotechnology