Data preparation, processing and interpretation with R

4.4 Normalise data

There is one final stage to go with this data set before it is suitable for full analysis. To allow us to make valid comparisons between the data from different arrays, they need to be normalised. To do this, use the scale() function to give all samples (i.e. columns in the matrix) a mean value of zero and a standard deviation of one.

Compare the means and standard deviations of the samples using the apply function
Normalise the data in the intensity values matrix using scale
Use the apply() function again to confirm the normalised means and standard deviations
- Hint: review the function of the apply() and scale() commands using the R help function

Below is the first 5 rows and 5 columns of the matrix after normalisation:

##                       ALL        ALL         ALL
## AFFX-BioB-5_at -0.8127832 -0.7582651 -0.83906446
## AFFX-BioB-M_at -0.8127832 -0.7582651 -0.83906446
## AFFX-BioB-3_at -0.8127832 -0.7582651 -0.83906446
## AFFX-BioC-5_at -0.8127832  0.1126268  0.09173842
## AFFX-BioC-3_at -0.8127832 -0.7582651 -0.83906446