This subproject is one of many research subprojects utilizing theresources provided by a Center grant funded by NIH/NCRR. The subproject andinvestigator (PI) may have received primary funding from another NIH source,and thus could be represented in other CRISP entries. The institution listed isfor the Center, which is not necessarily the institution for the investigator.In this project, we developed an SVM-based method for predicting protein function from structure. This work is, essentially, a simplification of existing SVM-based protein function annotation techniques. Previous work in this area relies on complicated similarity measures that are costly to compute and complex to program. We showed how to leverage an existing structural alignment algorithm, MAMMOTH, in the context of SVM classification. The resulting algorithm is easy to understand and provides much better classification accuracy than previously described methods.
Showing the most recent 10 out of 583 publications