A Fuzzy Query Method Based on Human-Readable Rules for Predicting Protein Stability Changes

ABSTRACT

Predicting protein mutant stability changes is important for protein design. Many methods have tried to improve prediction accuracy by various models. However, it will be difficult to employ them when the required input information is incomplete. This paper presents a fuzzy query method (named FQ-STAB), which cooperates with a humanreadable rule base to predict stability changes upon single mutations. Firstly, we have effectively established a set of classification rules as a knowledge representation from the thermodynamic database. Next, we applied the proposed method on the rules to predict stability changes under the condition without sufficient information. Further, FQ-STAB has been tested on a data set of single point mutants. The results show that it can be applied to the prediction of stability changes using partial input information, and can also provide the explanation capabilities for the predicted outcome. We have developed a web server for predicting protein stability changes upon single mutations by using fuzzy query mechanism and it is available at http: //bioinformatics.myweb.hinet.net/fqstab.htm.