johrpan/geposan
1
0
Fork 0
mirror of https://github.com/johrpan/geposan.git synced 2025-10-26 18:57:25 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

Rename method source files

Browse source
This commit is contained in:
Elias Projahn 2022-01-26 09:58:33 +01:00
parent ab61f08d0d
commit c633b17db6
12 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

94
R/correlation.R
View file

@ -1,94 +0,0 @@
#' Score genes based on their correlation with the reference genes.
#'
#' @return An object of class `geposan_method`.
#'
#' @export
correlation <- function() {
method(
id = "correlation",
name = "Correlation",
description = "Correlation with reference genes",
function(preset, progress) {
species_ids <- preset$species_ids
gene_ids <- preset$gene_ids
reference_gene_ids <- preset$reference_gene_ids
cached(
"correlation",
c(species_ids, gene_ids, reference_gene_ids),
{ # nolint
# Prefilter distances by species.
distances <- geposan::distances[species %chin% species_ids]
# Tranform data to get species as rows and genes as columns.
# We construct columns per species, because it requires
# fewer iterations, and transpose the table afterwards.
data <- data.table(gene = gene_ids)
# Make a column containing distance data for each species.
for (species_id in species_ids) {
species_data <- distances[
species == species_id,
.(gene, distance)
]
data <- merge(data, species_data, all.x = TRUE)
setnames(data, "distance", species_id)
}
# Transpose to the desired format.
data <- transpose(data, make.names = "gene")
progress(0.33)
# Take the reference data.
reference_data <- data[, ..reference_gene_ids]
# Perform the correlation between all possible pairs.
results <- stats::cor(
data[, ..gene_ids],
reference_data,
use = "pairwise.complete.obs",
method = "spearman"
)
results <- data.table(results, keep.rownames = TRUE)
setnames(results, "rn", "gene")
# Remove correlations between the reference genes
# themselves.
for (reference_gene_id in reference_gene_ids) {
column <- quote(reference_gene_id)
results[gene == reference_gene_id, eval(column) := NA]
}
progress(0.66)
# Find the highes correlation.
results[,
max_correlation := max(.SD, na.rm = TRUE),
.SDcols = reference_gene_ids,
by = gene
]
# Normalize scores.
results[,
score := (max_correlation - min(max_correlation)) /
(max(max_correlation) - min(max_correlation))
]
# Normalize scores.
results[, .(gene, score)]
result(
method = "correlation",
scores = results[, .(gene, score)],
details = list(all_correlations = results)
)
}
)
}
)
}