LEARNING SPARSE MODELS FOR A DYNAMIC BAYESIAN NETWORK CLASSIFIER OF PROTEIN SECO

点击翻译按钮获取中文摘要

This subproject is one of many research subprojects utilizing the resources provided by a Center grant funded by NIH/NCRR. The subproject and investigator (PI) may have received primary funding from another NIH source, and thus could be represented in other CRISP entries. The institution listed is for the Center, which is not necessarily the institution for the investigator. Protein secondary structure prediction provides insight into protein function and is a valuable preliminary step for predicting the 3D structure of a protein. Dynamic Bayesian networks (DBNs) have been shown to provide state-of-the-art performance in secondary structure prediction. As the size of the protein database grows, it becomes feasible to use a richer model in an effort to capture subtle correlations among the amino acids and the predicted labels. In this context, it is beneficial to derive sparse models that discourage over-fitting and provide biological insight. Results: We introduce an algorithm for sparsifying the parameters of a DBN. Using this algorithm, we can automatically remove up to 80% of the parameters of a DBN while maintaining the same level of predictive accuracy. We also prove an upper bound for the test error difference between the sparse and fully dense models. Finally, we demonstrate, using simulated data, that the algorithm is able to recover true sparse structures with high accuracy, and using real data, that the sparse model identifies known correlation structure related to different classes of secondary structure elements.