Protein Structure Prediction: Selecting Salient Features from Large Candidate Pools

We introduce a parallel approach, "DT-SELECT," for selecting features used by inductive learning algorithms to predict protein secondary structure. DT-SELECT is able to rapidly choose small, nonredundant feature sets from pools containing hundreds of thousands of potentially useful features. It does this by building a decision tree, using features from the pool, that classifies a set of training examples. The features included in the tree provide a compact description of the training data and are thus suitable for use as inputs to other inductive learning algorithms. Empirical experiments in the protein secondary-structure task, in which sets of complex features chosen by DT-SELECT are used to augment a standard artificial neural network representation, yield surprisingly little performance gain, even though features are selected from very large feature pools. We discuss some possible reasons for this result.