A DYNAMIC BAYESIAN NETWORK PREDICTOR OF PROTEIN SECONDARY STRUCTURE

这个子项目是许多研究子项目中的一个 由NIH/NCRR资助的中心赠款提供的资源。子项目和 研究者（PI）可能从另一个NIH来源获得了主要资金， 因此可以在其他CRISP条目中表示。所列机构为 研究中心，而研究中心不一定是研究者所在的机构。 本工作的重点是蛋白质二级结构的预测， 这是由氢原子形成的局部有序结构 蛋白质骨架内的键合。 在这个项目中，我们使用一类称为动态贝叶斯网络的概率模型来解决这个问题。 具体来说，我们的目标是调查 提供稀疏模型的方法是否能让我们建立 更好的模型，更少的参数，这样我们就可以优先考虑 生物学上显著的相关性，并排除那些 无关

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. This work focuses on the prediction of protein secondary structure, which is the locally ordered structure that is created by hydrogen bonding within the protein backbone. In this project, we solve this problem using a class of probability models known as dynamic Bayesian networks. Specifically, we aim to investigate whether approaches that provide sparse models will allow us to build better models with fewer parameters so that we can give priority to biologically significant correlations and eliminate the ones that are irrelevant.