vsh/rnaseq
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Build branch main with version main (1e1ffb3)

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

258
target/executable/tximport/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,258 @@
name: "tximport"
version: "main"
argument_groups:
- name: "Input"
arguments:
- type: "file"
name: "--quant_results"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: true
multiple_sep: ","
- type: "file"
name: "--tx2gene_tsv"
info: null
must_exist: true
create_parent: true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--quant_type"
description: "Method used for quantification"
info: null
required: false
choices:
- "salmon"
- "kallisto"
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--tpm_gene"
info: null
default:
- "merged.gene_tpm.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts_gene"
info: null
default:
- "merged.gene_counts.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts_gene_length_scaled"
info: null
default:
- "merged.gene_counts_length_scaled.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts_gene_scaled"
info: null
default:
- "merged.gene_counts_scaled.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--lengths_gene"
info: null
default:
- "merged.gene_length.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--tpm_transcript"
info: null
default:
- "merged.transcript_tpm.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--counts_transcript"
info: null
default:
- "merged.transcript_counts.tsv"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--lengths_transcript"
info: null
default:
- "merged.transcript_length.tsv"
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: "tximport.r"
description: "Get dataframe linking transcript ID, gene ID, and gene name"
info:
migration_info:
git_repo: "https://github.com/nf-core/rnaseq.git"
paths:
- "modules/local/tximport/main.nf"
last_sha: "489bcb4efdc7bd58839b22b0360d26b4d80b87a8"
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"
- "libssl-dev"
- "libxml2-dev"
interactive: false
- type: "r"
cran:
- "jsonlite"
bioc:
- "SummarizedExperiment"
- "tximport"
- "tximeta"
bioc_force_install: false
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/tximport/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/tximport"
executable: "target/executable/tximport/tximport"
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"

1424
target/executable/tximport/tximport Executable file
View File

File diff suppressed because it is too large Load Diff

141
target/executable/tximport/tximport.r Executable file
View File

@@ -0,0 +1,141 @@
#!/usr/bin/env Rscript
# Script for importing and processing transcript-level quantifications.
# Written by Lorena Pantano, later modified by Jonathan Manning, and released under the MIT license.
# Loading required libraries
library(SummarizedExperiment)
library(tximport)
# Parsing command line arguments
args <- commandArgs(trailingOnly=TRUE)
if (length(args) < 4) {
stop("Usage: tximport.r <coldata_path> <path> <prefix> <quant_type> <tx2gene_path>",
call.=FALSE)
}
# Assigning command line arguments to variables
coldata_path <- args[1]
path <- args[2]
prefix <- args[3]
quant_type <- args[4]
tx2gene_path <- args[5]
## Functions
# Build a table from a SummarizedExperiment object
build_table <- function(se.obj, slot) {
cbind(rowData(se.obj)[,1:2], assays(se.obj)[[slot]])
}
# Write a table to a file with given parameters
write_se_table <- function(params) {
file_name <- paste0(prefix, ".", params$suffix)
write.table(build_table(params$obj, params$slot), file_name,
sep="\t", quote=FALSE, row.names = FALSE)
}
# Read transcript metadata from a given path
read_transcript_info <- function(tinfo_path){
info <- file.info(tinfo_path)
if (info$size == 0) {
stop("tx2gene file is empty")
}
transcript_info <- read.csv(tinfo_path, sep="\t", header = FALSE,
col.names = c("tx", "gene_id", "gene_name"))
extra <- setdiff(rownames(txi[[1]]), as.character(transcript_info[["tx"]]))
transcript_info <- rbind(transcript_info, data.frame(tx=extra, gene_id=extra, gene_name=extra))
transcript_info <- transcript_info[match(rownames(txi[[1]]), transcript_info[["tx"]]), ]
rownames(transcript_info) <- transcript_info[["tx"]]
list(transcript = transcript_info,
gene = unique(transcript_info[,2:3]),
tx2gene = transcript_info[,1:2])
}
# Read and process sample/column data from a given path
read_coldata <- function(coldata_path){
if (file.exists(coldata_path)) {
coldata <- read.csv(coldata_path, sep="\t")
coldata <- coldata[match(names, coldata[,1]),]
coldata <- cbind(files = fns, coldata)
} else {
message("ColData not available: ", coldata_path)
coldata <- data.frame(files = fns, names = names)
}
rownames(coldata) <- coldata[["names"]]
}
# Create a SummarizedExperiment object with given data
create_summarized_experiment <- function(counts, abundance, length, col_data, row_data) {
SummarizedExperiment(assays = list(counts = counts, abundance = abundance, length = length),
colData = col_data,
rowData = row_data)
}
# Main script starts here
# Define pattern for file names based on quantification type
pattern <- ifelse(quant_type == "kallisto", "abundance.tsv", ".*quant_results\\.sf")
fns <- list.files(path, pattern = pattern, recursive = T, full.names = T)
names <- basename(fns)
names(fns) <- names
dropInfReps <- quant_type == "kallisto"
# Import transcript-level quantifications
txi <- tximport(fns, type = quant_type, txOut = TRUE, dropInfReps = dropInfReps)
# Read transcript and sample data
transcript_info <- read_transcript_info(tx2gene_path)
coldata <- read_coldata(coldata_path)
# Create initial SummarizedExperiment object
se <- create_summarized_experiment(txi[["counts"]], txi[["abundance"]], txi[["length"]],
DataFrame(coldata), transcript_info$transcript)
# Setting parameters for writing tables
params <- list(
list(obj = se, slot = "abundance", suffix = "transcript_tpm.tsv"),
list(obj = se, slot = "counts", suffix = "transcript_counts.tsv"),
list(obj = se, slot = "length", suffix = "transcript_lengths.tsv")
)
# Process gene-level data if tx2gene mapping is available
if ("tx2gene" %in% names(transcript_info) && !is.null(transcript_info$tx2gene)) {
tx2gene <- transcript_info$tx2gene
gi <- summarizeToGene(txi, tx2gene = tx2gene)
gi.ls <- summarizeToGene(txi, tx2gene = tx2gene, countsFromAbundance = "lengthScaledTPM")
gi.s <- summarizeToGene(txi, tx2gene = tx2gene, countsFromAbundance = "scaledTPM")
gene_info <- transcript_info$gene[match(rownames(gi[[1]]), transcript_info$gene[["gene_id"]]),]
rownames(gene_info) <- gene_info[["tx"]]
col_data_frame <- DataFrame(coldata)
# Create gene-level SummarizedExperiment objects
gse <- create_summarized_experiment(gi[["counts"]], gi[["abundance"]], gi[["length"]],
col_data_frame, gene_info)
gse.ls <- create_summarized_experiment(gi.ls[["counts"]], gi.ls[["abundance"]], gi.ls[["length"]],
col_data_frame, gene_info)
gse.s <- create_summarized_experiment(gi.s[["counts"]], gi.s[["abundance"]], gi.s[["length"]],
col_data_frame, gene_info)
params <- c(params, list(
list(obj = gse, slot = "length", suffix = "gene_lengths.tsv"),
list(obj = gse, slot = "abundance", suffix = "gene_tpm.tsv"),
list(obj = gse, slot = "counts", suffix = "gene_counts.tsv"),
list(obj = gse.ls, slot = "abundance", suffix = "gene_tpm_length_scaled.tsv"),
list(obj = gse.ls, slot = "counts", suffix = "gene_counts_length_scaled.tsv"),
list(obj = gse.s, slot = "abundance", suffix = "gene_tpm_scaled.tsv"),
list(obj = gse.s, slot = "counts", suffix = "gene_counts_scaled.tsv")
))
}
# Writing tables for each set of parameters
done <- lapply(params, write_se_table)
# Output session information and citations
citation("tximeta")
sessionInfo()