Iterative multi-task sequence labeling for predicting structural properties of proteins

Developing computational tools for predicting protein structural information given their amino acid sequence is of primary importance in protein science. Problems, such as the prediction of secondary structures, of solvent accessibility, or of disordered regions, can be expressed as sequence labeling problems and could be solved independently by existing machine learning based sequence labeling approaches. But, since these problems are closely related, we propose to rather approach them jointly in a multi-task approach. To this end, we introduce a new generic framework for iterative multi-task sequence labeling. We apply this - conceptually simple but quite effective - strategy to jointly solve a set of five protein annotation tasks. Our empirical results with two protein datasets show that the proposed strategy significantly outperforms the single-task approaches.