Description Usage Arguments Author(s)
resolving target space and identify biomarkers by integrating drug target, cell line sensitivity and cell line molecular data
1 2 3 4 |
t |
target matrix in the form target (rows) x drug (columns), values should be the higher the more potent, e.g. pKD. |
s |
the sensitivity matrix, in the form drug (rows) x cell line (columns), the higher the more sensitive (e.g. -log10(GI50)) |
m |
a list of matrices, abundance of molecular features in the form of variables (rows) x cell lines (columns) |
ncomp |
the number of components want to retain |
center |
logical values, whether the variables should be centered |
scale |
logical values, whether the variables should be scaled |
option |
the option for normalizing matrix |
kt |
the number (if it is an integer >= 1) or the proportion (if 0 < kt < 1) of kept variables in t. It should be a numeric value. |
km |
the number (if it is an integer >= 1) or the proportion (if 0 < km < 1) of kept variables in m. It should be a numeric value. |
wt |
weight for the rows of t |
wm |
weight for the rows of m |
pos |
logical value, whether only non-negative loadings retained |
ncores |
number of cores to be used, passed to |
fold |
the number of fold to be used in cross-validation, only used if kx or ky is a vector |
init |
how to initialize the algorithm. if no sparsity, svd is fast. |
nstart |
how many time the k-fold cross validation should be done |
seed |
set seed for random number generation |
loorss |
if the Leave-one-out procedure should be used in matrix reconstruction |
scan |
If the PRESS plot should be shown and used to determine the optimal k in CV |
nsd |
the the n*sd for selecting k automatically |
verbose |
if the process of calculation should be printed |
Chen Meng
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.