Z-scores from log2fold change

Question

[writersblog02]

Hi, I am learning to analyze microarray data and was wondering if you can calculate z-scores from log2fold change values in R

[Vince FitzPatrick]

The formula for Z-scores is pretty straight-forward (z <- (logratios - mean)/stddev) but it requires a mean and standard deviation that define the distribution of experimental error under the null hypothesis. But we can't know what the null hypothesis is without knowing more. Could you tell us a bit more about the data you're looking at?

Answer 1

[Benn]

You can use the scale() function in R. It calculates z-score per column, so if you want z-scores from rows, you'll have to transpose first (and back afterwards).

transposed_matrix <- t(matrix)

z_tr_mt <- scale(transposed_matrix)

z_score <- t(z_tr_mt)