DNA microarray technology provides biologists with the ability to measure the expression level of thousands of genes in a single experiment. As data from such experiments accumulate, it will be essential to have accurate means for extracting biological significance and using the data to assign functions to genes. In this paper, we try to provide a clear view of DNA microarray gene expression data analysis and modelling process by combining novel and effective visualization techniques with data mining algorithms. As a result, an integrated framework has been proposed to model and visualize short, high-dimensional time series gene expression data. The framework reduces the dimensionality of variables before applying appropriate temporal modelling method. The framework takes gene expression data as input, clusters the genes, displays the clustering results using a novel graph layout algorithm, models individual gene clusters using Dynamic Bayesian Network and visualizes the modelling results using simple but effective visualization techniques. A prototype has been built using Java3D to visualize the framework. Various user interactions are added to make the system a more effective visualization tool. Database has also been linked with the system to provide biologists with more background information of the models.