Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse




Journal Article

Multi-task learning for pKa prediction


Hansen,  Katja
Theory, Fritz Haber Institute, Max Planck Society;
Machine Learning Group, TU Berlin;

There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available

Skolidis, G., Hansen, K., Sanguinetti, G., & Rupp, M. (2012). Multi-task learning for pKa prediction. Journal of Computer-Aided Molecular Design, 26(7), 883-895. doi:10.1007/s10822-012-9582-x.

Cite as:
Many compound properties depend directly on the dissociation constants of its acidic and basic groups. Significant effort has been invested in computational models to predict these constants. For linear regression models, compounds are often divided into chemically motivated classes, with a separate model for each class. However, sometimes too few measurements are available for a class to build a reasonable model, e.g., when investigating a new compound series. If data for related classes are available, we show that multi-task learning can be used to improve predictions by utilizing data from these other classes. We investigate performance of linear Gaussian process regression models (single task, pooling, and multitask models) in the low sample size regime, using a published data set (n = 698, mostly monoprotic, in aqueous solution) divided beforehand into 15 classes. A multi-task regression model using the intrinsic model of co-regionalization and incomplete Cholesky decomposition performed best in 85 % of all experiments. The presented approach can be applied to estimate other molecular properties where few measurements are available.