Ulrich Rückert, Tobias Girschick, Fabian Buchwald, and Stefan Kramer (2010)
Adapted Transfer of Distance Measures for Quantitative Structure-Activity Relationships
In: Proceedings of the 13th International Conference on Discovery Science, ed. by B. Pfahringer, G. Holmes, A. Hoffman, vol. 6332, pp. 341-355, Springer. LNCS/LNAI.
Quantitative structure-activity relationships (QSARs) are regression models relating chemical structure to biological activity. Such models allow to make predictions for toxicologically or pharmacologi- cally relevant endpoints, which constitute the target outcomes of trials or experiments. The task is often tackled by instance-based methods (like k-nearest neighbors), which are all based on the notion of chemical (dis- )similarity. Our starting point is the observation by Raymond and Willett that the two big families of chemical distance measures, fingerprint-based and maximum common subgaph based measures, provide orthogonal in- formation about chemical similarity. The paper presents a novel method for finding suitable combinations of them, called adapted transfer, which adapts a distance measure learned on another, related dataset to a given dataset. Adapted transfer thus combines distance learning and transfer learning in a novel manner. In a set of experiments, we compare adapted transfer with distance learning on the target dataset itself and inductive transfer without adaptations. In our experiments, we visualize the per- formance of the methods by learning curves (i.e., depending on training set size) and present a quantitative comparison for 10\% and 100\% of the maximum training set size.