johrpan/ubigen
1
0
Fork 0
mirror of https://github.com/johrpan/ubigen.git synced 2025-10-26 19:57:24 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

Reduce memory footprint during analysis

Browse source
This commit is contained in:
Elias Projahn 2022-09-25 19:01:59 +02:00
parent f59a71b16c
commit 2eec3285f9
4 changed files with 33 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

25
scripts/input.R
View file

@ -70,21 +70,24 @@ getpm <- DGEList(counts = read_counts) |>
data_wide_samples <- data.table(getpm, keep.rownames = "gene")
data_wide_samples[, hgnc_symbol := hgnc_symbols]
# Create lookup tables for genes and samples.
genes <- data_wide_samples[, .(id = .I, gene, hgnc_symbol)]
fwrite(genes, file = here("scripts", "input", "genes.csv"))
sample_names <- colnames(data_wide_samples[, !c("gene", "hgnc_symbol")])
samples <- data.table(id = seq_along(sample_names), sample = sample_names)
fwrite(samples, file = here("scripts", "input", "samples.csv"))
data_wide_samples[, `:=`(gene = .I, hgnc_symbol = NULL)]
colnames(data_wide_samples) <- c("gene", seq_along(sample_names))
data_long <- melt(
data_wide_samples,
id.vars = c("gene", "hgnc_symbol"),
id.vars = "gene",
variable.name = "sample",
value.name = "expression",
variable.factor = FALSE
)
fwrite(
data_wide_samples,
file = here(
"scripts",
"input",
"data_wide_samples.csv.gz"
)
)
fwrite(data_long, file = here("scripts", "input", "data_long.csv.gz"))
fwrite(data_long, file = here("scripts", "input", "data_long.csv"))