ProteinGPS, the technology for navigation in protein space, addresses the shortcomings of existing protein engineering paradigms and takes advantage of the last 50 years of development in linear and nonlinear systems optimization. Protein engineering has classically been approached from two diametrically opposed directions: rational design and directed evolution. Rationalism attempts to understand protein structure and function at a complete mechanistic level so that the effect of any modification to the protein can be estimated by calculation from first principles. Directed evolution on the other hand follows the strict empirical tradition and attempts to find a desired solution by testing many many different solutions, typically using various evolution-based algorithms. ProteinGPS instead uses established machine learning and nonlinear systems optimization technologies to provide a standard convention for protein space navigation. The method calculates the specific location of a protein variant in multidimensional space and places unique information rich variants called infologs, at important crossroads within the space assessed. The resulting datasets are used to map the hyper space and calculate new protein variant sequences that fulfill the functional constraints needed. Application of technologies that the data mining society has established over the last 50 years, to Protein Engineering, results in far more functional protein improvement while needing far less samples to test.