This function discovers outlying subjects whose RNA-seq have abnormal shapes and provides the most outlying direction for each outlier.
1 2 3 |
data |
precessed RNA-seq data from process_data |
siglev |
the significance level of the Chi-squared distribution. Default is 1e-10. |
subt.mean |
logical, whether to subtract mean before SVD. Default is FALSE. |
PCnum |
the number of PCs to be used. If NULL (the default) the number of PCs will be estimated. |
maxPCnum |
the maximum number of PCs to be used. Default is 20. |
eps |
tuning parameter for estimating the number of PCs. If NULL (default), eps = (1/nrow(data)) |
rm.PCdir |
logical or numeric, the indices of PCs to be excluded from further study. If TRUE (the default), this automatically excludes a set of PCs that deviate from normality. If a sequence is specified, the corresponding PCs will be excluded. |
ADcutoff |
a cutoff value for checking the normality based on Anderson-Darling test statistic |
filter.dir |
logical, wether to filter out directions that deviate from normality. Default is TRUE. |
less.return |
logical, whether to show less results and not to return large matrices. Default is TRUE. |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.