Hydrophobicity is probably the most important property of amino acid that is being often exploited o predict protein folds. There are many amino acid hydrophobicity scales available in the literature. Here we propose two computational approaches based on self-organizing map (SOM) and fuzzy clustering to find some consensus scales. Although SOM and fuzzy clustering produce centroids, we propose new schemes to compute more effective representative scales that exploit the properties of SOM and fuzzy memberships. To demonstrate the utility of the new scales, we apply them to predict the protein folds of a benchmark data set using neural networks. Our experiments show that it is possible to generate useful scales with better utility compared to some existing scales. There can be other applications of the proposed scales. © Dynamic Publishers, Inc.