Modeling the mass-spectrometry data is important to identify and characterize hundreds of thousands of proteins or molecules per experiment. The large volume of such data from a typical mass-spectrometry experiment needs heavy computations and storage. In this work, a semi-nonparametric regression model, which consists of a linear parametric components for individual location and scale as well as a nonparametric regression function for the common shape, is considered. Our approach gives accurate estimations for both the parametric and nonparametric components. Then, some shrinkage and pre-test techniques are applied to improve the parametric components. To demonstrate the effectiveness of this approach, it is applied to a SELDI-TOF mass-spectrometry data collected from a study on liver cancer patients.