Statistical contributions to proteomic research

Abstract

Proteomic profiling has the potential to impact the diagnosis, prognosis, and treatment of various diseases. A number of different proteomic technologies are available that allow us to look at many proteins at once, and all of them yield complex data that raise significant quantitative challenges. Inadequate attention to these quantitative issues can prevent these studies from achieving their desired goals, and can even lead to invalid results. In this chapter, we describe various ways the involvement of statisticians or other quantitative scientists in the study team can contribute to the success of proteomic research, and we outline some of the key statistical principles that should guide the experimental design and analysis of such studies.

Figure 1

Discovery of clusters in data from bsa70 fraction of brain tumor samples.

Figure 2

Unsupervised clustering of Leukemia spectra reveals clustering driven by run date, not type of leukemia.

Figure 3

Plot reveals confounding between cancer status and run date in the study design, which is especially problematic given the quality control problems evident on day 3.

Figure 4

A simple heat map revealed peaks at integer multiples of 180.6, which is unlikely to be driven by biology, so we removed these peaks from consideration when discriminating between cancers and normals.

Figure 5

Heat map of all 216 samples run on the H4 chip (top), and on the WCX2 chip (bottom). The extreme difference in the ‘benign disease’ group in the spectra on the top, along with the similarity of these profiles to the WCX2 spectra, suggest a change in protocol occurred in the middle of the first experiment.

Figure 6

Comparisons of urine spectra in the vicinity of M/Z 3400, revealing calibration issues between the spectra in different groups.

Figure 7

Portion of a raw MALDI spectrum (top), along with the preprocessed version after denoising, baseline correction and normalization (bottom) using the method described in Morris, et al. (2005), with detected peaks indicated by the dots.

Figure 8

Average gel from a 2d gel experiment, with detected spots using the Pinnacle method indicated the symbol “x”.