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 project generalizes upon a method that we developed previously for predicting protein-protein interactions. In that work, we used a machine learning method known as a support vector machine (SVM) to predict yeast protein-protein interactions from a combination of diverse data types, including primary protein sequence, known interactions in other species, and topological properties of the yeast protein-protein interaction network. In the current project, we have applied similar techniques to predicting co-membership in a complex; i.e., rather than predicting direct physical interaction, we are interested in predicting whether a given pair of proteins participates in the same complex. For this task, many more types of data are relevant. For example, mRNA expression data can identify co-complexed proteins but will not discriminate between co-complexed and directly interacting pairs.
Showing the most recent 10 out of 583 publications
