Statistical analysis of variation in the human plasma proteome

Abstract

Quantifying the variation in the human plasma proteome is an essential prerequisite for disease-specific biomarker detection. We report here on the longitudinal and individual variation in human plasma characterized by two-dimensional difference gel electrophoresis (2-D DIGE) using plasma samples from eleven healthy subjects collected three times over a two week period. Fixed-effects modeling was used to remove dye and gel variability. Mixed-effects modeling was then used to quantitate the sources of proteomic variation. The subject-to-subject variation represented the largest variance component, while the time-within-subject variation was comparable to the experimental variation found in a previous technical variability study where one human plasma sample was processed eight times in parallel and each was then analyzed by 2-D DIGE in triplicate. Here, 21 protein spots had larger than 50% CV, suggesting that these proteins may not be appropriate as biomarkers and should be carefully scrutinized in future studies. Seventy-eight protein spots showing differential protein levels between different individuals or individual collections were identified by mass spectrometry and further characterized using hierarchical clustering. The results present a first step toward understanding the complexity of longitudinal and individual variation in the human plasma proteome, and provide a baseline for improved biomarker discovery.

Figure 1

The spatial distribution of proteins spots (yellow dots) detected in human plasma by 2-D DIGE. Identified proteins (blue dots) and those showing differences between the theoretical and observed molecular weights (numbered red dots) are highlighted.

Figure 2

The subject (σ_s), time-within-subject (σ_t), and random error (σ_e) variance component estimates (on SD scale) for the 397 protein spots matched on at least 75% of the gels, ordered by the magnitude of the subject component.

Figure 3

Principal component analysis of the 33 samples from the present study and the 8 replicates from the previous Technical Variation Study (TVS) [9], color-coded according to the legend, projected onto the first two principal components. Ellipses highlighting subjects 1 (red), 11 (green), and the TVS (black) are added for illustrative purposes only.

Figure 4

Hierarchical clustering of the 33 samples (y-axis) based on the abundance of the 397 high-quality protein spots on the x-axis, using Euclidean distance and average linkage. The samples are in SubjectNumberTime format, where SubjectNumber ranges from 01 to 11, and the Time values {x, y, and z } correspond to {T₁, T₂, and T₃}. The intensities range from −1.5-fold change (bright green) to 1.5-fold change (bright red). The dendrogram on the right indicates the order of the sample grouping, with more similar samples being grouped together first. The color band on the left shows the genders of the samples, with red for females, and blue for males.

Figure 5

Expression data for alpha-2-HS-glycoprotein, with an average increase of 1.49-fold between the female and male groups, and FDR-adjusted gender-effect P-value =.055. The samples are in SubjectNumberTime format, where SubjectNumber ranges from 01 to 11, and the Time values {x, y, and z } correspond to {T₁, T₂, and T₃}. The annotations indicate the gels (numbers) and the dyes (red for Cy5, green for Cy3) corresponding to the samples. Dotted lines connect samples multiplexed on the same gel. Crosses indicate sample averages over the technical replicates. The solid line connects all sample averages. Boxes around the three Time values for each SubjectNumber highlight male and female genders (blue and red respectively) added for illustrative purposes only.

Figure 6

Hierarchical clustering of the 33 samples (x-axis) based on the abundance of the 78-identified protein spots on the y-axis, using Euclidean distance metrics and average linkage methods. The samples are in SubjectNumberTime format, where SubjectNumber ranges from 01 to 11, and the Time values (x, y, and z) correspond to (T₁, T₂, and T₃). The intensities range from −1.5 (bright green) to 1.5 (bright red). The dendrogram on the top indicates the order of the sample grouping, with samples corresponding to the lower leaves being grouped together first. Similarly, the dendrogram on the left indicates the ordering of the protein spots. All transferrin (TF) and vitamin D-binding protein (GC) identifications are highlighted in blue and red, respectively.