Abstract | ||
---|---|---|
A recently published study showed the feasibility of chronic rat toxicity prediction, an important task to reduce the number of animal experiments using the knowledge of previous experiments. We benchmarked various kernel learning approaches for the prediction of chronic toxicity on a set of 565 chemical compounds, labeled with the Lowest Observed Adverse Effect Level, and achieved a prediction error close to the interlaboratory reproducibility. *** -Support Vector Regression was used in combination with numerical molecular descriptors and the Radial Basis Function Kernel, as well as with graph kernels for molecular graphs, to train the models. The results show that a kernel approach improves the Mean Squared Error and the Squared Correlation Coefficient using leave-one-out cross-validation and a seeded 10-fold-cross-validation averaged over 10 runs. Compared to the state-of-the-art, the Mean Squared Error was improved up to MSEloo of 0.45 and MSEcv of 0.46±0.09 which is close to the theoretical limit of the estimated interlaboratory reproducibility of 0.41. The Squared Empirical Correlation Coefficient was improved to $\text{Q}^2_{\text{loo}}$ of 0.58 and $\text{Q}^2_{\text{\text{cv}}}$ of 0.57±0.10. The results show that numerical kernels and graph kernels are both suited for predicting chronic rat toxicity for unlabeled compounds. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-01184-9_3 | EvoBIO |
Keywords | Field | DocType |
graph kernel,mean squared error,interlaboratory reproducibility,estimated interlaboratory reproducibility,squared correlation coefficient,kernel machines,squared empirical correlation coefficient,chronic toxicity,chronic rat toxicity prediction,prediction error close,chronic rat toxicity,molecular descriptor,support vector regression,radial basis function,kernel machine,leave one out cross validation,prediction error,cross validation,mean square error | Kernel (linear algebra),Correlation coefficient,Radial basis function,Square (algebra),Radial basis function kernel,Support vector machine,Mean squared error,Artificial intelligence,Machine learning,Mathematics,Kernel (statistics) | Conference |
Volume | ISSN | Citations |
5483 | 0302-9743 | 2 |
PageRank | References | Authors |
0.40 | 12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Georg Hinselmann | 1 | 96 | 8.12 |
Andreas Jahn | 2 | 2 | 0.40 |
Nikolas Fechner | 3 | 103 | 8.38 |
Andreas Zell | 4 | 1419 | 137.58 |