If you are going to do 17 of these, remember to do a multiple testing correction by multiplying the resulting p-values by 17. Hello Bioc Users, I am having a hard time understanding why heatmap.2 uses row (or column) Z-score instead of directly plotting logFC values Based on the formula for calculating Z-score, I understand that it is used for scaling or smoothing. For a logFC of -3, instead of getting 2-3 1/8 0. Function to use for fold change or average difference calculation. Alternatively, you can use sign (logFC)2abs (logFC) which has some symmetrical properties. Vector of cell names belonging to group 2. Or in excel is if the three values for X are in column A and the three values for $Y_1$ in column B =T.TEST(A1:A3,B1:B3,2,3) Vector of cell names belonging to group 1. If $X = (x_1, x_2, x_3)$ is your controls and $Y_i = (y_)$ are the treated samples from treatment i, to test the difference between treatment and control, do a t-test on X and Y (not T/mean(c)) I'm guessing the log transformed might well be better. Pick the set of values that has the weakest mean-SD relationship. Repeat the exercise with log transformed values. However, it is not recommended to simply rank by p-value and then discard genes with small logFCs, as this has been shown to increase the false discovery. So here is how i'd start, first calculate the mean and standard deviation of each of your 18 groups (17 treatments + control), and plot this on a scatter plot (i.e. Its also correct that you don't want to divide by the mean of the controls. The key point here is whether or not the values are approximately normally distributed and whether any transformations can be applied to make them so.įor a t-test, the most important thing is that there is no relationship between the mean and the variance.

Convert logfc to z score and rcode