PAC {cola} | R Documentation |
The proportion of ambiguous clustering (PAC score)
PAC(consensus_mat, x1 = seq(0.1, 0.3, by = 0.02), x2 = seq(0.7, 0.9, by = 0.02), trim = 0.2)
consensus_mat |
a consensus matrix. |
x1 |
lower bound to define "ambiguous clustering". The value can be a vector. |
x2 |
upper bound to define "ambihuous clustering". The value can be a vector. |
trim |
percent of extreme values to trim if combinations of |
This a variant of the orignial PAC method.
For each x_1i
in x1
and x_2j
in x2
, PAC_k = F(x_2j) - F(x_1i)
where F(x)
is the cumulative distribution function of the consensus matrix (the lower triangle matrix without diagnals is only used).
The final PAC is the mean of all PAC_k
by removing top trim/2
percent and bottom trim/2
percent of all values.
A single numeric vaule.
See https://www.nature.com/articles/srep06207 for explanation of PAC score.
Zuguang Gu <z.gu@dkfz.de>
data(cola_rl) PAC(get_consensus(cola_rl[1, 1], k = 2)) PAC(get_consensus(cola_rl[1, 1], k = 3)) PAC(get_consensus(cola_rl[1, 1], k = 4)) PAC(get_consensus(cola_rl[1, 1], k = 5)) PAC(get_consensus(cola_rl[1, 1], k = 6))