Identifying differences in protein expression levels by spectral counting and feature selection

Abstract

Spectral counting is a strategy to quantify relative protein concentrations in pre-digested protein mixtures analyzed by liquid chromatography online with tandem mass spectrometry. In the present study, we used combinations of normalization and statistical (feature selection) methods on spectral counting data to verify whether we could pinpoint which and how many proteins were differentially expressed when comparing complex protein mixtures. These combinations were evaluated on real, but controlled, experiments (yeast lysates were spiked with protein markers at different concentrations to simulate differences), which were therefore verifiable. The following normalization methods were applied: total signal, Z-normalization, hybrid normalization, and log preprocessing. The feature selection methods were: the Golub index, the Student t-test, a strategy based on the weighting used in a forward-support vector machine (SVM-F) model, and SVM recursive feature elimination. The results showed that Z-normalization combined with SVM-F correctly identified which and how many protein markers were added to the yeast lysates for all different concentrations. The software we used is available at http://pcarvalho.com/patternlab.

Figure 1

Protein markers were spiked at different concentrations in 15 yeast total cell lysate samples. Each lysate was analyzed by MudPIT (1.2) and protein identification carried out by Pep_Prob (1.3) and post-processed by DTASelect. Three different test sets were then generated. Combinations of normalization / feature selection methods were used to search for the spiked protein markers with different concentrations in each test set (1.4).

Figure 2

Sum of Pscores calculated for each combination of normalization / feature selection method when comparing the different spiked concentrations (legend), with (B) and without (A) Log preprocessing. Lower bars indicate better performance. The bar heights were limited to 4. We recall that the Pscore is calculated by obtaining the Log₁₀ of the sum of the ranks and subtracting 1. Note that SVM-F with and without log preprocessing obtains at least one perfect score. UD stands for “unnormalized” data.