GeneFAS (Gene Function Annotation System) is a java based graphical user interface for prediction of gene function using multiple sources of data.
It is based on an integrated probabilistic approach, which combines high-throughput data of protein-protein interactions, protein complexes, microarray gene-expression profiles, and genomic sequences. We quantified the relationship between functional similarity in the GO biological process and high-throughput data, and coded the relationship into a "functional linkage graph", where each node represents one gene and the weight of each edge is characterized by the Bayesian probability of function similarity between the two connected genes. Then we used Boltzmann machine and simulated annealing to perform optimization for assigning gene functions based on the global information of the functional linkage graph.
If you have any comments or suggestion, please contact:
Digital Biology Laboratory
Computer Science Department and Christopher S. Bond Life Sciences Center
University of Missouri Columbia