“…Too small sample sizes, poorly defined research questions, incorrectly justified statistical analysis, statistical overfitting, lack of instrumental standardization, and validation costs are several causes for this phenomenon [ 8 , 9 , 10 ]. Multiple reviews are available on how to address these individual challenges but do not discuss how choices made in one component of the biomarker discovery process influence the decisions for another component [ 1 , 4 , 11 , 12 , 13 , 14 , 15 , 16 ]. This review aims to discuss chemometrical and statistical aspects of the complete biomarker discovery process for clinical proteomics.…”