Experimental proteomics is a promising and growing domain, as state-of-the-art equipment allows for accurate, fast and environment-friendly research and diagnostics. However, current high performance experimental equipment is often complex, making setting up experiments and interpreting the results non-trivial. Currently available models often are inaccurate, consider a single experimental step in isolation, and don't adapt to the specific characteristics of the equipment used. This PoC project aims at offering software, support and training for experimental proteomics based on data mining techniques developed in the ErcStG project MiGraNT. This technology allows for accurately modeling the characteristics of the experimental steps and provides advanced global inference techniques which can be applied for designing experiments, interpreting results and other forms of support useful for pharmaceutical R&D, quality control, food safety and diagnostics.