Perform permutation-based testings on a sample of permuted input scores
using candidate_search as the main iterative function for each run.
CaDrA(
FS,
input_score,
method = c("ks_pval", "ks_score", "wilcox_pval", "wilcox_score", "revealer", "custom"),
custom_function = NULL,
custom_parameters = NULL,
alternative = c("less", "greater", "two.sided"),
weight = NULL,
top_N = 1,
search_start = NULL,
search_method = c("both", "forward"),
max_size = 7,
n_perm = 1000,
obs_best_score = NULL,
smooth = TRUE,
plot = TRUE,
ncores = 1,
cache_path = NULL,
verbose = FALSE
)a SummarizedExperiment object containing binary features where rows represent features of interest (e.g. genes, transcripts, exons, etc...) and columns represent the samples.
a vector of continuous scores representing a phenotypic readout of interest such as protein expression, pathway activity, etc.
NOTE: input_score object must have names or labels that match the column
names of FS object.
a character string specifies a scoring method that is
used in the search. There are 6 options: ("ks_pval" or ks_score
or "wilcox_pval" or wilcox_score or
"revealer" (conditional mutual information from REVEALER) or
"custom" (a customized scoring method)).
Default is ks_pval.
if method is "custom", specifies
the name of the customized function here. Default is NULL.
NOTE: custom_function() must take FS and input_score
as its input arguments, and its final result must return a vector of row-wise
scores ordered from most significant to least significant where its labels or
names matched the row names of FS object.
if method is "custom", specifies a list of
additional arguments (excluding FS and input_score) to be
passed to custom_function. Default is NULL.
a character string specifies an alternative hypothesis
testing ("two.sided" or "greater" or "less").
Default is less for left-skewed significance testing.
NOTE: this argument only apply to KS and Wilcoxon method
if method is ks_score, specifies a vector of weights
to perform a weighted-KS testing. Default is NULL.
an integer specifies the number of features to start the
search over. By default, it starts from the top best feature (top_N = 1).
NOTE: If top_N is provided, then search_start parameter
will be ignored.
a list of character strings (separated by commas)
which specifies feature names within the FS object to start
the search with. If search_start is provided, then top_N
parameter will be ignored. Default is NULL.
a character string specifies an algorithm to filter out
the best candidates ("forward" or "both"). Default is
both (i.e., backward and forward).
an integer specifies a maximum size that a meta-feature can
extend to do for a given search. Default is 7.
an integer specifies the number of permutations to perform.
Default is 1000.
a numeric value corresponding to the best observed
score. This value is used to compare against the permuted best scores.
Default is NULL. If set to NULL, we will compute the observed
best score based on the given parameters.
a logical value indicates whether or not to smooth the p-value
calculation to avoid p-value of 0. Default is TRUE.
a logical value indicates whether or not to plot the empirical
null distribution of the permuted best scores. Default is TRUE.
an integer specifies the number of cores to perform
parallelization for permutation-based testing. Default is 1.
a full path uses to cache the permuted best scores.
We recycle these scores instead of re-computing them to save time.
Default is NULL. If NULL, the cache path is set to ~/.Rcache
for future loading.
a logical value indicates whether or not to print the
diagnostic messages. Default is FALSE.
a list of key parameters that are used to cache the result of
permutation-based testing, a vector of permuted best scores for a given
n_perm, an observed best score, and a permutation p-value.
# Load pre-computed feature set
data(sim_FS)
# Load pre-computed input-score
data(sim_Scores)
# Define additional parameters and start the function
cadra_result <- CaDrA(
FS = sim_FS, input_score = sim_Scores, method = "ks_pval",
weight = NULL, alternative = "less", top_N = 1,
search_start = NULL, search_method = "both", max_size = 7,
n_perm = 10, plot = FALSE, smooth = TRUE, obs_best_score = NULL,
ncores = 1, cache_path = NULL
)
#> Setting cache root path as: /home/runner/.cache/R/R.cache
#>
|
| | 0%
|
|======= | 10%
|
|============== | 20%
|
|===================== | 30%
|
|============================ | 40%
|
|=================================== | 50%
|
|========================================== | 60%
|
|================================================= | 70%
|
|======================================================== | 80%
|
|=============================================================== | 90%
|
|======================================================================| 100%