Training Set Reduction Methods for Single Sequence Protein Secondary Structure Prediction

Orphan proteins are characterized by the lack of significant sequence similarity to almost all proteins in the database. To infer the functional properties of the orphans, more elaborate techniques that utilize structural information are required. In this regard, the protein structure prediction gains considerable importance. Secondary structure prediction algorithms designed for orphan proteins (also known as single-sequence algorithms) cannot utilize multiple alignments or aligment profiles, which are derived from similar proteins. This is a limiting factor for the prediction accuracy. One way to improve the performance of a single-sequence algorithm is to perform re-training. In this approach, first, the models used by the algorithm are trained by a representative set of proteins and a secondary structure prediction is computed. Then, using a distance measure, the original training set is refined by removing proteins that are dissimilar to the initial prediction. This step is followed by the re-estimation of the model parameters and the prediction of the secondary structure. In this paper, we compare training set reduction methods that are used to re-train the hidden semi-Markov models employed by the IPSSP algorithm. We found that the composition based reduction method has the highest performance compared to the other reduction methods. In addition, threshold-based reduction performed better than the reduction technique that selects the first 80% of the dataset proteins.