Table 3.
Summary | Data | Diff. expr. | m2 m8 | m3 m7 | m4 m6 | m1 m6 | m4 m9 | m1 m4 | m6 m9 | m1 m5a | m5a m9 | m1 m5b | m5b m9 | m1 m5c | m5c m9 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Average difference | Raw | Student | 0.69 | 0.64 | 0.56 | 0.82 | 0.79 | 0.66 | 0.44 | 0.63 | 0.60 | 0.73 | 0.66 | 0.75 | 0.67 |
Win. t | 0.80 | 0.78 | 0.67 | 0.88 | 0.85 | 0.70 | 0.53 | 0.75 | 0.66 | 0.81 | 0.74 | 0.81 | 0.72 | ||
Reg. t | 0.66 | 0.66 | 0.54 | 0.82 | 0.79 | 0.63 | 0.48 | 0.73 | 0.59 | 0.77 | 0.67 | 0.75 | 0.58 | ||
Scaled | Student | 0.68 | 0.68 | 0.55 | 0.80 | 0.76 | 0.62 | 0.47 | 0.67 | 0.64 | 0.74 | 0.69 | 0.74 | 0.68 | |
Win. t | 0.81 | 0.80 | 0.63 | 0.87 | 0.83 | 0.68 | 0.50 | 0.76 | 0.71 | 0.80 | 0.75 | 0.81 | 0.73 | ||
Reg. t | 0.70 | 0.70 | 0.51 | 0.80 | 0.76 | 0.59 | 0.41 | 0.66 | 0.59 | 0.71 | 0.64 | 0.73 | 0.65 | ||
Li-Wong MBEI | Raw | Student | 0.74 | 0.68 | 0.62 | 0.84 | 0.79 | 0.69 | 0.45 | 0.63 | 0.64 | 0.75 | 0.70 | 0.76 | 0.72 |
Win. t | 0.82 | 0.79 | 0.71 | 0.86 | 0.83 | 0.70 | 0.53 | 0.71 | 0.68 | 0.80 | 0.77 | 0.79 | 0.74 | ||
Reg. t | 0.79 | 0.77 | 0.66 | 0.86 | 0.82 | 0.66 | 0.52 | 0.70 | 0.67 | 0.80 | 0.76 | 0.77 | 0.69 | ||
Scaled | Student | 0.71 | 0.70 | 0.58 | 0.77 | 0.74 | 0.61 | 0.46 | 0.63 | 0.63 | 0.72 | 0.68 | 0.71 | 0.68 | |
Win. t | 0.81 | 0.81 | 0.65 | 0.83 | 0.80 | 0.66 | 0.50 | 0.72 | 0.70 | 0.78 | 0.75 | 0.77 | 0.72 | ||
Reg. t | 0.77 | 0.77 | 0.60 | 0.81 | 0.77 | 0.63 | 0.47 | 0.70 | 0.67 | 0.76 | 0.72 | 0.75 | 0.68 | ||
1-Step Tukey-Biweight | Raw | Student | 0.77 | 0.71 | 0.66 | 0.87 | 0.83 | 0.72 | 0.48 | 0.67 | 0.66 | 0.78 | 0.73 | 0.80 | 0.73 |
Win. t | 0.84 | 0.82 | 0.73 | 0.91 | 0.88 | 0.74 | 0.57 | 0.76 | 0.70 | 0.83 | 0.79 | 0.83 | 0.76 | ||
Reg. t | 0.80 | 0.80 | 0.69 | 0.89 | 0.85 | 0.68 | 0.55 | 0.75 | 0.68 | 0.83 | 0.77 | 0.80 | 0.69 | ||
Scaled | Student | 0.76 | 0.75 | 0.62 | 0.84 | 0.80 | 0.67 | 0.53 | 0.70 | 0.69 | 0.78 | 0.73 | 0.78 | 0.73 | |
Win. t | 0.84 | 0.84 | 0.68 | 0.88 | 0.85 | 0.72 | 0.55 | 0.78 | 0.74 | 0.83 | 0.78 | 0.83 | 0.77 | ||
Reg. t | 0.83 | 0.82 | 0.65 | 0.87 | 0.82 | 0.67 | 0.50 | 0.75 | 0.71 | 0.81 | 0.75 | 0.80 | 0.72 | ||
Median | Raw | Student | 0.69 | 0.64 | 0.57 | 0.82 | 0.79 | 0.66 | 0.45 | 0.63 | 0.61 | 0.72 | 0.66 | 0.75 | 0.67 |
Win. t | 0.80 | 0.78 | 0.68 | 0.88 | 0.85 | 0.70 | 0.53 | 0.74 | 0.67 | 0.80 | 0.74 | 0.81 | 0.72 | ||
Reg. t | 0.77 | 0.76 | 0.63 | 0.86 | 0.82 | 0.65 | 0.50 | 0.73 | 0.64 | 0.79 | 0.72 | 0.78 | 0.66 | ||
Scaled | Student | 0.68 | 0.69 | 0.55 | 0.80 | 0.77 | 0.63 | 0.48 | 0.67 | 0.64 | 0.74 | 0.69 | 0.74 | 0.69 | |
Win. t | 0.81 | 0.80 | 0.64 | 0.87 | 0.83 | 0.69 | 0.51 | 0.76 | 0.71 | 0.81 | 0.75 | 0.81 | 0.74 | ||
Reg. t | 0.78 | 0.77 | 0.59 | 0.85 | 0.80 | 0.63 | 0.45 | 0.72 | 0.67 | 0.77 | 0.72 | 0.77 | 0.69 | ||
Median-polish | Raw | Student | 0.85 | 0.75 | 0.74 | 0.91 | 0.85 | 0.78 | 0.50 | 0.74 | 0.69 | 0.84 | 0.76 | 0.85 | 0.78 |
Win. t | 0.90 | 0.87 | 0.81 | 0.93 | 0.90 | 0.81 | 0.61 | 0.79 | 0.74 | 0.86 | 0.82 | 0.88 | 0.82 | ||
Reg. t | 0.91 | 0.87 | 0.83 | 0.95 | 0.90 | 0.83 | 0.62 | 0.80 | 0.75 | 0.88 | 0.84 | 0.90 | 0.82 | ||
Scaled | Student | 0.82 | 0.82 | 0.64 | 0.83 | 0.81 | 0.68 | 0.56 | 0.66 | 0.70 | 0.79 | 0.75 | 0.80 | 0.74 | |
Win. t | 0.90 | 0.90 | 0.72 | 0.89 | 0.86 | 0.75 | 0.60 | 0.79 | 0.77 | 0.85 | 0.81 | 0.85 | 0.79 | ||
Reg. t | 0.91 | 0.91 | 0.76 | 0.92 | 0.89 | 0.77 | 0.62 | 0.82 | 0.80 | 0.87 | 0.84 | 0.87 | 0.81 |
We analyzed the Hugene 1.0 ST Tissue Mixture Study (Affymetrix) for differential expression, using Student t-test, Regularized t-test, and Window t-test. Summarization tests were performed on probe concentrations computed with AffyILM. Comparison between heart (mix 1) and brain (mix 9) is assumed to provide the reference list of p-values. For each combination of summarization/analysis steps (rows), Pearson's correlation coefficient has been computed on log10(p-values) between the reference analysis and several comparisons of mixtures (columns). Underlined characters highlights the top 5 correlation coefficients for each column. Raw/Scaled labels respectively refers to summarization tests performed with/without a scaling step between arrays.