The visual content of this site is heavily reliant on JavaScript. We suggest navigating our site with a JavaScript-enabled browser, such as Firefox, Safari, or Internet Explorer. Also, please be sure you have the Sun Java Engine 1.4 or later installed. Visit java.com to download the latest version.
The KFC Server (Knowledge-based FADE and Contacts) predicts binding "hot spots" within protein-protein interfaces by recognizing structural features indicative of important binding contacts. The server analyzes several chemical and physical features surrounding an interface residue and predicts the classification of the residue using a model trained on prior experimental data. The KFC Server manual can be found here.
If you use the KFC Server, please cite: S. J. Darnell, D. Page, and J. C. Mitchell. Automated Decision-Tree Approach to Predicting Protein-Protein Interaction Hot Spots. Proteins, 68(4): 813-823, 2007. View Abstract