Checking a Deconvolution Method

Description

This function runs a given algorithm on a small random toy dataset, to check that the algorithm works correctly

Usage

gedCheck(method, ..., maxIter = 5L, verbose = 3L)

Arguments

method
algorithm specification
...
other arguments passed to ged.
maxIter
maximum number of iterations. Note that it is fixed to a small default value for the purpose of the check, which is likely to make no sense for real application.
verbose
defines verbosity level (FALSE/TRUE or a number).

Value

returns invisibly the result of running the algorithm, which usually is an NMFfit object.

Examples


gedCheck('deconf')
##   Using ged algorithm: "deconf"
## NMF algorithm: 'deconf'
## NMF seeding method: rprop
##      Algorithm version 'fast'
##       Scaling Strategy - coef: yes | signatures: yes
## Iterations: 0/5Iterations: 1/5Iterations: 2/5Iterations: 3/5Iterations: 4/5Iterations: 5/5
## DONE (stopped at 5/5 iterations)
## # NMF computation exit status ... OK
##   Timing:
##    user  system elapsed 
##   0.376   0.000   0.376 
##   GED final wrap up ...   OK
gedCheck('DSA', log=FALSE)
##   Using ged algorithm: "DSA"
## NMF algorithm: 'qprog'
## NMF seeding method: none
##      Estimating basis and mixture coefficients matrices from marker features [DSA]
##      Using 15/15 markers to estimate cell proportions: 
##  CL_1 CL_2 CL_3 
##     5    5    5 
##       Checking data scale ...       NOTE [log]
##       Converting data to linear scale ...       SKIP
##        Computing proportions using DSA method ...        OK
##        Estimating basis matrix from mixture coefficients [qprog]
##        Building data range constraint matrices:        0.18 <= x <= 20.12
##        Not using any marker constraints
## # NMF computation exit status ... OK
##   Timing:
##    user  system elapsed 
##   0.628   0.016   0.642 
##   GED final wrap up ...   OK