diffnet_to_snQTL_stats {snQTL} | R Documentation |
Test statistics for snQTL
Description
Generate snQTL test statistics from a given list of differential networks. This function takes a list of differential networks, the choice of test statistics, and other computational tuning parameters as inputs. Outputs include the calculated statistics, recall of the choice, and the decomposition components associated with the statistics.
Usage
diffnet_to_snQTL_stats(
diffnet_list,
method = c("sum", "sum_square", "max", "tensor"),
rho = 1000,
sumabs = 0.2,
niter = 20,
trace = FALSE,
tensor_iter = 20,
tensor_tol = 10^(-3),
tensor_seed = NULL
)
Arguments
diffnet_list |
list, a list of p-by-p differential networks |
method |
character, the choice of test statistics; see "details" |
rho |
number, a large positive constant adding to the diagonal elements to ensure positive definiteness in symmetric matrix spectral decomposition |
sumabs |
number, the number specify the sparsity level in the matrix/tensor eigenvector; |
niter |
integer, the number of iterations to use in the PMD algorithm (see |
trace |
logic variable, whether to trace the progress of PMD algorithm (see |
tensor_iter |
integer, the maximal number of iteration in SSTD algorithm (see |
tensor_tol |
number, a small positive constant for error difference to indicate the SSTD convergence (see |
tensor_seed |
number, the seed to generate random initialization for SSTD algorithm |
Details
The list diffnet_list
records the pairwise differential networks D_{AB}, D_{AH}, D_{AB}
. This package provides four options for test statistics:
sum, the sum of sparse leading matrix eigenvalues (sLMEs) of all pairwise differential networks:
Stat_sum = \lambda(D_{AB}) + \lambda(D_{AH}) + \lambda(D_{BH}),
where
\lambda
refers to the sLME operation with given sparsity level set up bysumabs
.sum_square, the sum of squared sLMEs:
Stat_sumsquare = \lambda^2(D_{AB}) + \lambda^2(D_{AH}) + \lambda^2(D_{BH}).
max, the maximal of sLMEs:
Stat_max = \max(\lambda(D_{AB}), \lambda(D_{AH}), \lambda(D_{BH})).
tensor, the sparse leading tensor eigenvalue (sLTE) of the differential tensor:
Stat_tensor = \Lambda(\mathcal{D}),
where
\Lambda
refers to the sLTE operation with given sparsity level set up bysumabs
, and\mathcal{D}
is the differential tensor composed by stacking three pairwise differential networks.
The sparse symmetric matrix decomposition is implemented by symmPMD()
with parameters rho, sumabs, niter, trace
.
The sparse symmetric tensor decomposition is implemented by SSTD()
.
Since symmPMD()
is used in SSTD()
, parameters for symmPMD()
are used for SSTD()
.
While parameters tensor_iter, tensor_tol, tensor_seed
should be uniquely defined for tensor
method.
Value
a list containing the following:
method |
character, recall of the choice of test statistics |
stats |
number, the calculated test statistics with given network list and choices |
decomp_result |
list, if |
References
Hu, J., Weber, J. N., Fuess, L. E., Steinel, N. C., Bolnick, D. I., & Wang, M. (2025). A spectral framework to map QTLs affecting joint differential networks of gene co-expression. PLOS Computational Biology, 21(4), e1012953.