This file reads in the tsv file with labels and converts it into a label object.
First row is expected to be #BINARY:1=[label for cases];
-1=[label for controls]
.
Second row should contain the sample identifiers as tab-separated list
(consistent with feature and metadata).
Third row is expected to contain the actual class labels (tab-separated):
1
for each case and -1
for each control.
Note: Labels can take other numeric values (but not characters or strings); importantly, the label for cases has to be greater than the one for controls
read.labels(fn.in.label)
fn.in.label | name of the tsv file containing labels |
---|
label object containing several entries:
$label
named vector containing the numerical labels from the
file;
$header
first row of the label file;
$info
information about the type of label (e.g. BINARY
);
$positive.lab
numerical label for controls, e.g. -1
;
$negative.lab
numerical label for cases, e.g. 1
;
$n.idx
logical vector of labels (TRUE
for controls,
FALSE
otherwise);
$n.lab
label for controls, e.g. healthy
;
$p.idx
logical vector of labels (TRUE
for cases,
FALSE
otherwise);
$p.lab
label for cases, e.g. cancer
# run with example data fn.label <- system.file('extdata', 'label_crc_study-pop-I_N141_tax_profile_mocat_bn_specI_clusters.tsv', package = 'SIAMCAT') labels <- read.labels(fn.label)