Project type: Bilateral Collaboration Project
Project duration: 2008 - 2010
Collaborators on project
With recently developed high-throughput technologies that allow us to gather biomedical data on genome-wide scale under a wide range of experimental conditions, scientific discovery has shifted from labor-intensive to computationally intensive task. Since the early experiments with gene expression microarrays, artificial intelligence and data mining have played a crucial role in uncovering new knowledge in biomedicine. At present, scientific discovery in this field largely depends on availability of dedicated computational tools. The goal of this project, where we are collaborating with Drs. Gad Shaulsky in Adam Kuspa, Baylor College of Medicine, Houston, is to develop and apply new data mining and artificial intelligence-based approaches for knowledge discovery in functional and chemogenomics. In particular, we will develop approaches to analyze gene expression and growth profile data from experiments in which the model organism has been either mutated or exposed to some active compound or drug. Our working hypothesis is that through the use of appropriate computational approaches we can use these experiments to characterize the function of a set of genes and place them within a relevant biological network (functional genomics), or characterize and predict the effects of drugs and relate them to genetic networks and potential drug targets (chemogenomics). The expected outputs of the project are a set of new methods for functional genomics and chemogenomics, their open-source implementation within the existing data mining framework called Orange, and their application in research that involves studies on the social amoeba Dictyostelium discoideum.