Novel tools are needed for efficient analysis and visualization of the massive data sets associated with metabolomics, Here, we describe a batch-learning self-organizing map(BL-SOM) for metabolome informatics that makes the learning process and resulting map independent of the order of data input. This approach was successfully used in analyzing and organizing the metabolome data for Arabidopsis thaliana cells cultured under salt stress. Our $6{ imes}4$ matrix presented patterns of metabolite levels at different time periods. A negative correlation was found between the levels of amino acids and metabolites related to glycolysis metabolism in response to this stress. Therefore, BL-SOM could be an excellent tool for clustering and visualizing high dimensional, complex metabolome data in a single map.