R/get_functions.R
get_pairwise_sharing_from_samples.RdCompute the proportion of (significant) signals shared by magnitude in each pair of conditions
get_pairwise_sharing_from_samples(
m,
factor = 0.5,
lfsr_thresh = 0.05,
FUN = identity
)the mash fit with samples from posteriors
a number in [0,1] the factor within which effects are considered to be shared
the lfsr threshold for including an effect in the assessment
a function to be applied to the estimated effect sizes before assessing sharing. The most obvious choice beside the default 'FUN=identity' would be 'FUN=abs' if you want to ignore the sign of the effects when assesing sharing.
For each pair of conditions, compute the fraction of effects that are within a factor `factor` of one another. The results are returned as an R by R matrix.
simdata = simple_sims(50,5,1)
data = mash_set_data(simdata$Bhat, simdata$Shat)
m = mash(data, cov_canonical(data), posterior_samples=5, algorithm='R')
#> - Computing 200 x 141 likelihood matrix.
#> - Likelihood calculations took 0.03 seconds.
#> - Fitting model with 141 mixture components.
#> - Model fitting took 0.16 seconds.
#> - Computing posterior matrices.
#> - Computation allocated took 0.11 seconds.
get_pairwise_sharing_from_samples(m) # sharing by magnitude (same sign)
#> condition_1 condition_2 condition_3 condition_4 condition_5
#> condition_1 1.0000000 0.8857143 0.8285714 0.8857143 0.9600000
#> condition_2 0.8857143 1.0000000 0.7714286 0.9714286 0.9666667
#> condition_3 0.8285714 0.7714286 1.0000000 0.7750000 0.8000000
#> condition_4 0.8857143 0.9714286 0.7750000 1.0000000 0.9714286
#> condition_5 0.9600000 0.9666667 0.8000000 0.9714286 1.0000000
get_pairwise_sharing_from_samples(m, factor=0) # sharing by sign
#> condition_1 condition_2 condition_3 condition_4 condition_5
#> condition_1 1.0000000 0.9714286 0.8285714 0.9714286 1.0
#> condition_2 0.9714286 1.0000000 0.9142857 1.0000000 1.0
#> condition_3 0.8285714 0.9142857 1.0000000 0.8750000 0.9
#> condition_4 0.9714286 1.0000000 0.8750000 1.0000000 1.0
#> condition_5 1.0000000 1.0000000 0.9000000 1.0000000 1.0
get_pairwise_sharing_from_samples(m, FUN=abs) # sharing by magnitude when sign is ignored
#> condition_1 condition_2 condition_3 condition_4 condition_5
#> condition_1 1.0000000 0.8857143 0.8285714 0.8857143 0.9600000
#> condition_2 0.8857143 1.0000000 0.7714286 0.9714286 0.9666667
#> condition_3 0.8285714 0.7714286 1.0000000 0.7750000 0.8000000
#> condition_4 0.8857143 0.9714286 0.7750000 1.0000000 0.9714286
#> condition_5 0.9600000 0.9666667 0.8000000 0.9714286 1.0000000