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.This project is an extension of a method that we developed previously for predicting protein-protein interactions. In the current project, we have applied similar techniques, using kernel methods from heterogeous data sources, to the task of predicting co-complex protein pair (CCPP) relationships. We show that combination of complementary information improves the performance of our CCPP recognizer. Furthermore, we applied our prediction method to two recently described affinity purification coupled with mass spectrometry data sets. We find that our predicted positives are highly enriched with CCPPs that are identified by both datasets, suggesting that our method successfully identifies true CCPPs.
Showing the most recent 10 out of 583 publications
