In this work we consider an inference task that biologists are very good at: bringing together the knowledge that has been obtained in experiments on various organisms in order to understand the differences and commonalities of molecular processes in these related organisms. We look at this problem from an sequence analysis point of view, where we aim at solving the same classification task in different organisms. We investigate the challenge of combining information from related organisms. Here, we consider relation between the organisms that are defined by a tree or graph implied by their taxonomy or phylogeny. Multitask learning, a machine learning technique that recently received considerable attention, considers the problem of learning across tasks that are related to each other. We treat each organism as one task and present three novel multitask learning methods to handle situations in which the relationships among tasks can be described by a hierarchy or by a graph. These algorithms are designed for large-scale applications and scale to problems with a large number of training examples, which frequently appear in sequence analysis. We perform experimental analyses on related synthetic datasets in order to illustrate the properties of our algorithms. Moreover, we consider a problem from genomic sequence analysis, namely splice site recognition, to illustrate the usefulness of our approach. We are able show that using data from 15 eukaryotic organisms one can indeed significantly improve the prediction performance compared to traditional approaches. On a broader perspective, we expect that approaches like the ones presented in this work have the potential to complement and enrich the strategy of homology-based sequence analysis that are currently the quasi-standard in biological sequence analysis.

accepted