Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions modules/nf-core/lsa/cosine/environment.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
---
channels:
- conda-forge
- bioconda
dependencies:
- conda-forge::r-base=4.5.2
- conda-forge::r-lsa=0.73.4
- conda-forge::r-pheatmap=1.0.13
- conda-forge::r-optparse=1.7.5
- conda-forge::r-readr=2.1.6
40 changes: 40 additions & 0 deletions modules/nf-core/lsa/cosine/main.nf
Original file line number Diff line number Diff line change
@@ -0,0 +1,40 @@
process LSA_COSINE {
tag "$meta.id"
label 'process_medium'

conda "${moduleDir}/environment.yml"
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/4d/4d94f159b95315adf8bf54fdc9db88db10a5aef72dca6245dd163b91e9e0437e/data' :
'community.wave.seqera.io/library/r-base_r-lsa_r-pheatmap_r-optparse_pruned:901156bc11e60b28' }"

input:
tuple val(meta), path(expression_matrix)

output:
tuple val(meta), path("*_matrix.csv") , emit: matrix
tuple val(meta), path("*_heatmap.png"), emit: heatmap
path "versions.yml" , emit: versions

when:
task.ext.when == null || task.ext.when

script:
args = task.ext.args ?: ''
prefix = task.ext.prefix ?: "${meta.id}"
template 'cosine.R'

stub:
args = task.ext.args ?: ''
prefix = task.ext.prefix ?: "${meta.id}"
"""
echo "dummy matrix data" > ${prefix}_matrix.csv
echo "dummy matrix data" > ${prefix}_heatmap.png

cat <<-END_VERSIONS > versions.yml
"${task.process}":
r-base: \$(R --version | sed -n 1p | sed 's/R version //g' | sed 's/ (.*//g')
r-lsa: \$(Rscript -e "library(lsa); cat(as.character(packageVersion('lsa')))")
r-pheatmap: \$(Rscript -e "library(pheatmap); cat(as.character(packageVersion('pheatmap')))")
END_VERSIONS
"""
}
71 changes: 71 additions & 0 deletions modules/nf-core/lsa/cosine/meta.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,71 @@
# name matches directory structure
name: "lsa_cosine"
description: Calculates the cosine similarity matrix between samples based on a gene
expression matrix.
keywords:
- similarity
- cosine
- clustering
- rnaseq
- heatmap
tools:
- "lsa":
description: "Latent Semantic Analysis (LSA) package for R."
homepage: "https://cran.r-project.org/web/packages/lsa/index.html"
documentation: "https://cran.r-project.org/web/packages/lsa/lsa.pdf"
licence: ["GPL-2"]
identifier: ""
- "pheatmap":
description: "Pretty Heatmaps package for R."
homepage: "https://cran.r-project.org/web/packages/pheatmap/index.html"
documentation: "https://cran.r-project.org/web/packages/pheatmap/pheatmap.pdf"
licence: ["GPL-2"]
identifier: biotools:pheatmap

input:
- - meta:
type: map
description: |
Groovy Map containing sample information, e.g. [ id:'test' ].
- expression_matrix:
type: file
description: |
CSV file containing the expression matrix.
Rows should be features (genes) and columns should be samples.
pattern: "*.csv"
ontologies:
- edam: http://edamontology.org/format_3752 # CSV
output:
matrix:
- - meta:
type: map
description: |
Groovy Map containing sample information, e.g. [ id:'test' ].
- "*_matrix.csv":
type: file
description: A square matrix (CSV) containing pairwise similarity scores.
pattern: "*_matrix.csv"
ontologies:
- edam: http://edamontology.org/format_3752 # CSV
heatmap:
- - meta:
type: map
description: |
Groovy Map containing sample information, e.g. [ id:'test' ].
- "*_heatmap.png":
type: file
description: A PNG image visualizing the similarity matrix as a heatmap.
pattern: "*_heatmap.png"
ontologies: []
versions:
- versions.yml:
type: file
description: File containing software versions.
pattern: "versions.yml"

ontologies:
- edam: http://edamontology.org/format_3750 # YAML
authors:
- "@miguelrosell"
maintainers:
- "@miguelrosell"
83 changes: 83 additions & 0 deletions modules/nf-core/lsa/cosine/templates/cosine.R
Original file line number Diff line number Diff line change
@@ -0,0 +1,83 @@
#!/usr/bin/env Rscript

suppressPackageStartupMessages({
library(optparse)
library(readr)
library(lsa)
library(pheatmap)
})

# ---- Configurable options via task.ext.args ----
option_list <- list(
make_option(c("-m", "--method"),
type = "character", default = "cosine",
help = "Similarity method: cosine, pearson, spearman"),
make_option(c("-g", "--min_gene_mean"),
type = "double", default = 0.0,
help = "Minimum gene mean expression filter")
)

opt <- parse_args(
OptionParser(option_list = option_list),
args = strsplit("$args", "[[:space:]]+")[[1]]
)

# ---- Load table ----
df <- as.data.frame(
read_csv("${expression_matrix}",
col_types = cols(.default = col_guess()))
)

# ---- Set rownames from first column if character ----
first_col <- names(df)[1]
if (is.character(df[[first_col]]) || is.factor(df[[first_col]])) {
rownames(df) <- df[[first_col]]
df[[first_col]] <- NULL
}

# ---- Select numeric columns as the expression matrix ----
mat <- as.matrix(
df[, sapply(df, is.numeric), drop = FALSE]
)

# ---- Filter low-expression genes ----
if (opt\$min_gene_mean > 0) {
keep <- rowMeans(mat, na.rm = TRUE) >= opt\$min_gene_mean
mat <- mat[keep, , drop = FALSE]
}

# ---- Compute similarity ----
if (opt\$method == "cosine") {
sim <- lsa::cosine(mat)
} else {
sim <- cor(mat,
method = opt\$method, use = "pairwise.complete.obs")
}
colnames(sim) <- colnames(mat)
rownames(sim) <- colnames(mat)

# ---- Save matrix ----
write.csv(sim, "${prefix}_matrix.csv",
quote = FALSE, row.names = TRUE)

# ---- Save heatmap ----
png("${prefix}_heatmap.png", width = 900, height = 700)
pheatmap(sim,
display_numbers = TRUE,
cluster_rows = FALSE,
cluster_cols = FALSE)
dev.off()

# ---- Versions ----
writeLines(
c(
'"${task.process}":',
paste(" r-base:",
paste0(R.version\$major, ".", R.version\$minor)),
paste(" r-lsa:",
as.character(packageVersion("lsa"))),
paste(" r-pheatmap:",
as.character(packageVersion("pheatmap")))
),
"versions.yml"
)
63 changes: 63 additions & 0 deletions modules/nf-core/lsa/cosine/tests/main.nf.test
Original file line number Diff line number Diff line change
@@ -0,0 +1,63 @@
nextflow_process {

name "Test Process LSA_COSINE"
script "../main.nf"
process "LSA_COSINE"

tag "modules"
tag "modules_nfcore"
tag "lsa"
tag "lsa/cosine"

// Test 1: Real run
test("Should run successfully with a simple CSV") {

when {
process {
"""
// Create dummy CSV
def test_csv = file("test_data.csv")
test_csv.text = '''gene_id,sample_A,sample_B,sample_C
GENE_1,10.0,10.5,0.0
GENE_2,50.0,50.5,2.0
GENE_3,0.0,0.0,100.0
GENE_4,100.0,99.5,10.0'''

input[0] = [ [id:'test_sample'], test_csv ]
"""
}
}

then {
assert process.success
// Snapshot versions and the matrix content (heatmap is binary, so we check name only)
assert snapshot(
process.out.matrix,
process.out.versions,
file(process.out.heatmap[0][1]).name
).match()
}

}

// Test 2: Stub run (fast check)
test("Stub run") {
options "-stub"

when {
process {
"""
def test_csv = file("test_data.csv")
test_csv.text = '''gene_id,sample_A,sample_B''' // content doesn't matter for stub
input[0] = [ [id:'test_sample'], test_csv ]
"""
}
}

then {
assert process.success
assert snapshot(process.out).match()
}
}

}
72 changes: 72 additions & 0 deletions modules/nf-core/lsa/cosine/tests/main.nf.test.snap
Original file line number Diff line number Diff line change
@@ -0,0 +1,72 @@
{
"Stub run": {
"content": [
{
"0": [
[
{
"id": "test_sample"
},
"test_sample_matrix.csv:md5,3932b231a8a14016bc1e7a245f05246c"
]
],
"1": [
[
{
"id": "test_sample"
},
"test_sample_heatmap.png:md5,3932b231a8a14016bc1e7a245f05246c"
]
],
"2": [
"versions.yml:md5,b77351a76d91db12e57dd88f7e2e0184"
],
"heatmap": [
[
{
"id": "test_sample"
},
"test_sample_heatmap.png:md5,3932b231a8a14016bc1e7a245f05246c"
]
],
"matrix": [
[
{
"id": "test_sample"
},
"test_sample_matrix.csv:md5,3932b231a8a14016bc1e7a245f05246c"
]
],
"versions": [
"versions.yml:md5,b77351a76d91db12e57dd88f7e2e0184"
]
}
],
"timestamp": "2026-02-20T15:51:35.612855607",
"meta": {
"nf-test": "0.9.4",
"nextflow": "25.04.7"
}
},
"Should run successfully with a simple CSV": {
"content": [
[
[
{
"id": "test_sample"
},
"test_sample_matrix.csv:md5,d84209a90c22f35ef4e6ea89a9d11770"
]
],
[
"versions.yml:md5,b77351a76d91db12e57dd88f7e2e0184"
],
"test_sample_heatmap.png"
],
"timestamp": "2026-02-13T02:24:53.88495333",
"meta": {
"nf-test": "0.9.3",
"nextflow": "25.04.7"
}
}
}