Using Data and Text Mining Techniques for Yeast Gene Regulation Prediction: A Case Study

We focus on the problem of predicting yeast gene regulation experiments. In order to construct a good solution, we study combinations of different methods that are not yet to be found in any single data mining application. We describe our approach to propositionalizing the given relational data that describes the interaction among proteins. We study how we can exploit a large archive of scientific publications that contain additional information about the proteins. We present experiments in which we automatically extract additional attributes from the text archive that enhance the predictive results. The studied task is one of the two data mining problems of the KDD Cup 2002; the solution that we describe achieved the highest score in one of the two subtasks and received an “Honorable Mention” for the overall task.