Build branch main with version main (1e1ffb3)

Build pipeline: vsh-ci-dev-jsbwk

Source commit: 1e1ffb315f

Source message: Merge pull request #17 from viash-hub/add_biobox_modules

- Migrate a number of components to biobox
- Fix tests
- Reduce size of test resources
- Prepare for Viash Hub
This commit is contained in:
CI
2024-09-13 07:41:13 +00:00
commit 1ebb61f1e8
557 changed files with 430700 additions and 0 deletions

View File

@@ -0,0 +1,210 @@
name: "summarizedexperiment"
version: "main"
argument_groups:
- name: "Input"
arguments:
- type: "file"
name: "--tpm_gene"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts_gene"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts_gene_length_scaled"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts_gene_scaled"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--tpm_transcript"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts_transcript"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--tx2gene_tsv"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--output"
info: null
default:
- "merged_summarizedexperiment"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "bash_script"
path: "script.sh"
is_executable: true
- type: "file"
path: "summarizedexperiment.r"
description: "Create SummarizedExperiment object from Salmon counts"
info:
migration_info:
git_repo: "https://github.com/nf-core/rnaseq.git"
paths:
- "modules/local/summarizedexperiment/main.nf"
last_sha: "0a1bdcfbb498987643b74e9fccab85ccd9f2a17d"
status: "enabled"
requirements:
commands:
- "ps"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
tag: "$id"
auto:
simplifyInput: true
simplifyOutput: false
transcript: false
publish: false
config:
labels:
mem1gb: "memory = 1000000000.B"
mem2gb: "memory = 2000000000.B"
mem5gb: "memory = 5000000000.B"
mem10gb: "memory = 10000000000.B"
mem20gb: "memory = 20000000000.B"
mem50gb: "memory = 50000000000.B"
mem100gb: "memory = 100000000000.B"
mem200gb: "memory = 200000000000.B"
mem500gb: "memory = 500000000000.B"
mem1tb: "memory = 1000000000000.B"
mem2tb: "memory = 2000000000000.B"
mem5tb: "memory = 5000000000000.B"
mem10tb: "memory = 10000000000000.B"
mem20tb: "memory = 20000000000000.B"
mem50tb: "memory = 50000000000000.B"
mem100tb: "memory = 100000000000000.B"
mem200tb: "memory = 200000000000000.B"
mem500tb: "memory = 500000000000000.B"
mem1gib: "memory = 1073741824.B"
mem2gib: "memory = 2147483648.B"
mem4gib: "memory = 4294967296.B"
mem8gib: "memory = 8589934592.B"
mem16gib: "memory = 17179869184.B"
mem32gib: "memory = 34359738368.B"
mem64gib: "memory = 68719476736.B"
mem128gib: "memory = 137438953472.B"
mem256gib: "memory = 274877906944.B"
mem512gib: "memory = 549755813888.B"
mem1tib: "memory = 1099511627776.B"
mem2tib: "memory = 2199023255552.B"
mem4tib: "memory = 4398046511104.B"
mem8tib: "memory = 8796093022208.B"
mem16tib: "memory = 17592186044416.B"
mem32tib: "memory = 35184372088832.B"
mem64tib: "memory = 70368744177664.B"
mem128tib: "memory = 140737488355328.B"
mem256tib: "memory = 281474976710656.B"
mem512tib: "memory = 562949953421312.B"
cpu1: "cpus = 1"
cpu2: "cpus = 2"
cpu5: "cpus = 5"
cpu10: "cpus = 10"
cpu20: "cpus = 20"
cpu50: "cpus = 50"
cpu100: "cpus = 100"
cpu200: "cpus = 200"
cpu500: "cpus = 500"
cpu1000: "cpus = 1000"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "ubuntu:22.04"
target_registry: "images.viash-hub.com"
target_tag: "main"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "r-base"
- "libcurl4-openssl-dev"
interactive: false
- type: "r"
bioc:
- "SummarizedExperiment"
- "tximeta"
bioc_force_install: false
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/summarizedexperiment/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/summarizedexperiment"
executable: "target/executable/summarizedexperiment/summarizedexperiment"
viash_version: "0.9.0"
git_commit: "1e1ffb315fefec05db2ee0c62e1c98ce4b49929c"
git_remote: "https://github.com/viash-hub/rnaseq"
package_config:
version: "main"
info:
test_resources:
- path: "gs://viash-hub-test-data/rnaseq/v1"
dest: "testData"
viash_version: "0.9.0"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].directives.tag\
\ := '$id'\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'main'"
organization: "vsh"

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,68 @@
#!/usr/bin/env Rscript
library(SummarizedExperiment)
## Create SummarizedExperiment (se) object from Salmon counts
args <- commandArgs(trailingOnly = TRUE)
if (length(args) < 2) {
stop("Usage: salmon_se.r <coldata> <counts> <tpm>", call. = FALSE)
}
coldata <- args[1]
counts_fn <- args[2]
tpm_fn <- args[3]
tx2gene <- args[4]
info <- file.info(tx2gene)
if (info$size == 0) {
tx2gene <- NULL
} else {
rowdata <- read.csv(tx2gene, sep = "\t", header = FALSE)
colnames(rowdata) <- c("tx", "gene_id", "gene_name")
tx2gene <- rowdata[, 1:2]
}
counts <- read.csv(counts_fn, row.names = 1, sep = "\t")
counts <- counts[, 2:ncol(counts), drop = FALSE] # remove gene_name column
tpm <- read.csv(tpm_fn, row.names = 1, sep = "\t")
tpm <- tpm[, 2:ncol(tpm), drop = FALSE] # remove gene_name column
if (length(intersect(rownames(counts), rowdata[["tx"]])) > length(intersect(rownames(counts), rowdata[["gene_id"]]))) {
by_what <- "tx"
} else {
by_what <- "gene_id"
rowdata <- unique(rowdata[, 2:3])
}
if (file.exists(coldata)) {
coldata <- read.csv(coldata, sep = "\t")
coldata <- coldata[match(colnames(counts), coldata[, 1]), ]
coldata <- cbind(files = fns, coldata)
} else {
message("ColData not avaliable ", coldata)
coldata <- data.frame(files = colnames(counts), names = colnames(counts))
}
rownames(coldata) <- coldata[["names"]]
extra <- setdiff(rownames(counts), as.character(rowdata[[by_what]]))
if (length(extra) > 0) {
rowdata <- rbind(
rowdata,
data.frame(
tx = extra,
gene_id = extra,
gene_name = extra
)[, colnames(rowdata)]
)
}
rowdata <- rowdata[match(rownames(counts), as.character(rowdata[[by_what]])), ]
rownames(rowdata) <- rowdata[[by_what]]
se <- SummarizedExperiment(
assays = list(counts = counts, abundance = tpm),
colData = DataFrame(coldata),
rowData = rowdata
)
saveRDS(se, file = paste0(tools::file_path_sans_ext(counts_fn), ".rds"))