ImputeNetwork {ADImpute} | R Documentation |
Network-based imputation
ImputeNetwork(data, net.coef = NULL, cores = BiocParallel::bpworkers(BPPARAM), BPPARAM = BiocParallel::SnowParam(type = "SOCK"), type = 'iteration', write = FALSE, ...)
data |
matrix with entries equal to zero to be imputed, normalized and log2-transformed (genes as rows and samples as columns) |
net.coef |
matrix; network coefficients. |
cores |
integer; number of cores to use |
BPPARAM |
parallel back-end to be used during parallel computation.
See |
type |
character; either 'iteration', for an iterative solution, or 'pseudoinv', to use Moore-Penrose pseudo-inversion as a solution. |
write |
logical; should a file with the imputation results be written? |
... |
additional arguments to |
Imputes dropouts using a gene regulatory network trained on external
data, as provided in net.coef
. Dropout expression values are
estimated from the expression of their predictor genes and the network
coefficients.
matrix; imputation results incorporating network information