Quantification and classification are key points for differential analysis of proteomic studies and diagnostic tests. A MRM analytical chain is a cascade of molecular events depicted by a graph structure, each node being associated to a molecular state such as protein, peptide or ion and each branch to a molecular processing. Each protein is associated to a set of transition measurements. One key question is how to infer the protein level and the class label. We propose to compare a hierarchical model based Bayesian Hierarchical Inversion combining all transitions and a non-linear processing based on logarithmic transformation of standardized peak value combined with a median filter. Classification performances are evaluated on a colorectal cancer cohort for LFABP and PDI biomarkers.