Build branch main with version main (21831c2)

Build pipeline: viash-hub.htrnaseq.main-n8w4c

Source commit: 21831c2104

Source message: Fix well_demultiplex test
This commit is contained in:
CI
2024-08-29 08:10:20 +00:00
commit 044a3af7a9
59 changed files with 33214 additions and 0 deletions

View File

@@ -0,0 +1,267 @@
name: "parallel_map"
version: "main"
argument_groups:
- name: "Input arguments"
arguments:
- type: "file"
name: "--input_r1"
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--input_r2"
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--genomeDir"
description: "STAR reference directory"
info: null
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--barcodes"
description: "The barcodes/wells to process"
info: null
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- name: "Barcode arguments"
arguments:
- type: "integer"
name: "--wellBarcodesLength"
description: "The length of the well barcodes"
info: null
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--umiLength"
description: "The length of the UMIs"
info: null
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--limitBAMsortRAM"
info: null
default:
- "10000000000"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Runtime arguments"
arguments:
- type: "integer"
name: "--runThreadN"
description: "Number of threads to use for a single STAR execution."
info: null
default:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output arguments"
arguments:
- type: "file"
name: "--output"
description: "Location of the output folders, 1 folder per barcode. The value\
\ used\nfor this argument must contain a '*', which will be replaced with the\n\
barcode to form the final output location for that barcode.\n"
info: null
default:
- "./*"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--joblog"
description: "Where to store the log file listing all the jobs."
info: null
default:
- "execution_log.txt"
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: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Map wells in batch, using STAR\nSpliced Transcripts Alignment to a Reference\
\ (C) Alexander Dobin\nhttps://github.com/alexdobin/STAR\n"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
info: null
status: "enabled"
requirements:
commands:
- "ps"
license: "MIT"
links:
repository: "https://github.com/viash-hub/htrnaseq"
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"
script:
- "includeConfig(\"nextflow_labels.config\")"
debug: false
container: "docker"
engines:
- type: "docker"
id: "docker"
image: "debian:stable-slim"
target_registry: "images.viash-hub.com"
target_tag: "main"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
- "gzip"
- "bzip2"
- "parallel"
- "wget"
- "zlib1g-dev"
- "unzip"
- "xxd"
- "file"
interactive: false
- type: "docker"
run:
- "wget -O $STAR_TARGET $STAR_SOURCE && \\\n unzip $STAR_TARGET -d /tmp && \\\
\n mv /tmp/STAR_$STAR_VERSION/Linux_x86_64_static/STAR /usr/local/bin/$STAR_BINARY\
\ && \\\n chmod +x /usr/local/bin/$STAR_BINARY && \\\n rm $STAR_TARGET &&\
\ rm -rf /tmp/STAR_$STAR_VERSION\n"
env:
- "STAR_VERSION \"2.7.11b\""
- "STAR_SOURCE \"https://github.com/alexdobin/STAR/releases/download/$STAR_VERSION/STAR_$STAR_VERSION.zip\""
- "STAR_TARGET \"/tmp/star.zip\""
- "STAR_BINARY \"STAR\""
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/parallel_map/config.vsh.yaml"
runner: "nextflow"
engine: "docker|native"
output: "target/nextflow/parallel_map"
executable: "target/nextflow/parallel_map/main.nf"
viash_version: "0.9.0-RC7"
git_commit: "21831c2104098ecce57aa9b372e49f865296cc48"
git_remote: "https://github.com/viash-hub/htrnaseq"
package_config:
name: "htrnaseq"
version: "main"
description: "High-throughput pipeline [WIP]\n"
info: null
viash_version: "0.9.0-RC7"
source: "src"
target: "target"
config_mods:
- ".requirements.commands := ['ps']\n.runners[.type == 'nextflow'].config.script\
\ := 'includeConfig(\"nextflow_labels.config\")'\n.resources += {path: '/src/config/labels.config',\
\ dest: 'nextflow_labels.config'}\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'main'"
keywords:
- "bioinformatics"
- "sequence"
- "high-throughput"
- "mapping"
- "counting"
- "pipeline"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/viash-hub/htrnaseq"
issue_tracker: "https://github.com/viash-hub/htrnaseq/issues"

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,125 @@
manifest {
name = 'parallel_map'
mainScript = 'main.nf'
nextflowVersion = '!>=20.12.1-edge'
version = 'main'
description = 'Map wells in batch, using STAR\nSpliced Transcripts Alignment to a Reference (C) Alexander Dobin\nhttps://github.com/alexdobin/STAR\n'
}
process.container = 'nextflow/bash:latest'
// detect tempdir
tempDir = java.nio.file.Paths.get(
System.getenv('NXF_TEMP') ?:
System.getenv('VIASH_TEMP') ?:
System.getenv('TEMPDIR') ?:
System.getenv('TMPDIR') ?:
'/tmp'
).toAbsolutePath()
profiles {
no_publish {
process {
withName: '.*' {
publishDir = [
enabled: false
]
}
}
}
mount_temp {
docker.temp = tempDir
podman.temp = tempDir
charliecloud.temp = tempDir
}
docker {
docker.enabled = true
// docker.userEmulation = true
singularity.enabled = false
podman.enabled = false
shifter.enabled = false
charliecloud.enabled = false
}
singularity {
singularity.enabled = true
singularity.autoMounts = true
docker.enabled = false
podman.enabled = false
shifter.enabled = false
charliecloud.enabled = false
}
podman {
podman.enabled = true
docker.enabled = false
singularity.enabled = false
shifter.enabled = false
charliecloud.enabled = false
}
shifter {
shifter.enabled = true
docker.enabled = false
singularity.enabled = false
podman.enabled = false
charliecloud.enabled = false
}
charliecloud {
charliecloud.enabled = true
docker.enabled = false
singularity.enabled = false
podman.enabled = false
shifter.enabled = false
}
}
process{
withLabel: mem1gb { memory = 1000000000.B }
withLabel: mem2gb { memory = 2000000000.B }
withLabel: mem5gb { memory = 5000000000.B }
withLabel: mem10gb { memory = 10000000000.B }
withLabel: mem20gb { memory = 20000000000.B }
withLabel: mem50gb { memory = 50000000000.B }
withLabel: mem100gb { memory = 100000000000.B }
withLabel: mem200gb { memory = 200000000000.B }
withLabel: mem500gb { memory = 500000000000.B }
withLabel: mem1tb { memory = 1000000000000.B }
withLabel: mem2tb { memory = 2000000000000.B }
withLabel: mem5tb { memory = 5000000000000.B }
withLabel: mem10tb { memory = 10000000000000.B }
withLabel: mem20tb { memory = 20000000000000.B }
withLabel: mem50tb { memory = 50000000000000.B }
withLabel: mem100tb { memory = 100000000000000.B }
withLabel: mem200tb { memory = 200000000000000.B }
withLabel: mem500tb { memory = 500000000000000.B }
withLabel: mem1gib { memory = 1073741824.B }
withLabel: mem2gib { memory = 2147483648.B }
withLabel: mem4gib { memory = 4294967296.B }
withLabel: mem8gib { memory = 8589934592.B }
withLabel: mem16gib { memory = 17179869184.B }
withLabel: mem32gib { memory = 34359738368.B }
withLabel: mem64gib { memory = 68719476736.B }
withLabel: mem128gib { memory = 137438953472.B }
withLabel: mem256gib { memory = 274877906944.B }
withLabel: mem512gib { memory = 549755813888.B }
withLabel: mem1tib { memory = 1099511627776.B }
withLabel: mem2tib { memory = 2199023255552.B }
withLabel: mem4tib { memory = 4398046511104.B }
withLabel: mem8tib { memory = 8796093022208.B }
withLabel: mem16tib { memory = 17592186044416.B }
withLabel: mem32tib { memory = 35184372088832.B }
withLabel: mem64tib { memory = 70368744177664.B }
withLabel: mem128tib { memory = 140737488355328.B }
withLabel: mem256tib { memory = 281474976710656.B }
withLabel: mem512tib { memory = 562949953421312.B }
withLabel: cpu1 { cpus = 1 }
withLabel: cpu2 { cpus = 2 }
withLabel: cpu5 { cpus = 5 }
withLabel: cpu10 { cpus = 10 }
withLabel: cpu20 { cpus = 20 }
withLabel: cpu50 { cpus = 50 }
withLabel: cpu100 { cpus = 100 }
withLabel: cpu200 { cpus = 200 }
withLabel: cpu500 { cpus = 500 }
withLabel: cpu1000 { cpus = 1000 }
}
includeConfig("nextflow_labels.config")

View File

@@ -0,0 +1,43 @@
process {
// Default resources for components that hardly do any processing
memory = { 2.GB * task.attempt }
cpus = 1
// Retry for exit codes that have something to do with memory issues
errorStrategy = { task.exitStatus in 137..140 ? 'retry' : 'terminate' }
maxRetries = 3
maxMemory = null
// Resource labels
withLabel: singlecpu { cpus = 1 }
withLabel: lowcpu { cpus = 4 }
withLabel: midcpu { cpus = 10 }
withLabel: highcpu { cpus = 20 }
withLabel: lowmem { memory = { get_memory( 4.GB * task.attempt ) } }
withLabel: midmem { memory = { get_memory( 25.GB * task.attempt ) } }
withLabel: highmem { memory = { get_memory( 50.GB * task.attempt ) } }
withLabel: veryhighmem { memory = { get_memory( 75.GB * task.attempt ) } }
}
def get_memory(to_compare) {
if (!process.containsKey("maxMemory") || !process.maxMemory) {
return to_compare
}
try {
if (process.containsKey("maxRetries") && process.maxRetries && task.attempt == (process.maxRetries as int)) {
return process.maxMemory
}
else if (to_compare.compareTo(process.maxMemory as nextflow.util.MemoryUnit) == 1) {
return max_memory as nextflow.util.MemoryUnit
}
else {
return to_compare
}
} catch (all) {
println "Error processing memory resources. Please check that process.maxMemory '${process.maxMemory}' and process.maxRetries '${process.maxRetries}' are valid!"
System.exit(1)
}
}

View File

@@ -0,0 +1,206 @@
{
"$schema": "http://json-schema.org/draft-07/schema",
"title": "parallel_map",
"description": "Map wells in batch, using STAR\nSpliced Transcripts Alignment to a Reference (C) Alexander Dobin\nhttps://github.com/alexdobin/STAR\n",
"type": "object",
"definitions": {
"input arguments" : {
"title": "Input arguments",
"type": "object",
"description": "No description",
"properties": {
"input_r1": {
"type":
"string",
"description": "Type: List of `file`, required, multiple_sep: `\";\"`. ",
"help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. "
}
,
"input_r2": {
"type":
"string",
"description": "Type: List of `file`, required, multiple_sep: `\";\"`. ",
"help_text": "Type: List of `file`, required, multiple_sep: `\";\"`. "
}
,
"genomeDir": {
"type":
"string",
"description": "Type: `file`, required. STAR reference directory",
"help_text": "Type: `file`, required. STAR reference directory"
}
,
"barcodes": {
"type":
"string",
"description": "Type: List of `string`, required, multiple_sep: `\";\"`. The barcodes/wells to process",
"help_text": "Type: List of `string`, required, multiple_sep: `\";\"`. The barcodes/wells to process"
}
}
},
"barcode arguments" : {
"title": "Barcode arguments",
"type": "object",
"description": "No description",
"properties": {
"wellBarcodesLength": {
"type":
"integer",
"description": "Type: `integer`, required. The length of the well barcodes",
"help_text": "Type: `integer`, required. The length of the well barcodes"
}
,
"umiLength": {
"type":
"integer",
"description": "Type: `integer`, required. The length of the UMIs",
"help_text": "Type: `integer`, required. The length of the UMIs"
}
,
"limitBAMsortRAM": {
"type":
"string",
"description": "Type: `string`, default: `10000000000`. ",
"help_text": "Type: `string`, default: `10000000000`. "
,
"default": "10000000000"
}
}
},
"runtime arguments" : {
"title": "Runtime arguments",
"type": "object",
"description": "No description",
"properties": {
"runThreadN": {
"type":
"integer",
"description": "Type: `integer`, default: `1`. Number of threads to use for a single STAR execution",
"help_text": "Type: `integer`, default: `1`. Number of threads to use for a single STAR execution."
,
"default": "1"
}
}
},
"output arguments" : {
"title": "Output arguments",
"type": "object",
"description": "No description",
"properties": {
"output": {
"type":
"string",
"description": "Type: List of `file`, required, default: `$id.$key.output_*./*`, multiple_sep: `\";\"`. Location of the output folders, 1 folder per barcode",
"help_text": "Type: List of `file`, required, default: `$id.$key.output_*./*`, multiple_sep: `\";\"`. Location of the output folders, 1 folder per barcode. The value used\nfor this argument must contain a \u0027*\u0027, which will be replaced with the\nbarcode to form the final output location for that barcode.\n"
,
"default": "$id.$key.output_*./*"
}
,
"joblog": {
"type":
"string",
"description": "Type: `file`, default: `$id.$key.joblog.txt`. Where to store the log file listing all the jobs",
"help_text": "Type: `file`, default: `$id.$key.joblog.txt`. Where to store the log file listing all the jobs."
,
"default": "$id.$key.joblog.txt"
}
}
},
"nextflow input-output arguments" : {
"title": "Nextflow input-output arguments",
"type": "object",
"description": "Input/output parameters for Nextflow itself. Please note that both publishDir and publish_dir are supported but at least one has to be configured.",
"properties": {
"publish_dir": {
"type":
"string",
"description": "Type: `string`, required, example: `output/`. Path to an output directory",
"help_text": "Type: `string`, required, example: `output/`. Path to an output directory."
}
,
"param_list": {
"type":
"string",
"description": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel",
"help_text": "Type: `string`, example: `my_params.yaml`. Allows inputting multiple parameter sets to initialise a Nextflow channel. A `param_list` can either be a list of maps, a csv file, a json file, a yaml file, or simply a yaml blob.\n\n* A list of maps (as-is) where the keys of each map corresponds to the arguments of the pipeline. Example: in a `nextflow.config` file: `param_list: [ [\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027], [\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027] ]`.\n* A csv file should have column names which correspond to the different arguments of this pipeline. Example: `--param_list data.csv` with columns `id,input`.\n* A json or a yaml file should be a list of maps, each of which has keys corresponding to the arguments of the pipeline. Example: `--param_list data.json` with contents `[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]`.\n* A yaml blob can also be passed directly as a string. Example: `--param_list \"[ {\u0027id\u0027: \u0027foo\u0027, \u0027input\u0027: \u0027foo.txt\u0027}, {\u0027id\u0027: \u0027bar\u0027, \u0027input\u0027: \u0027bar.txt\u0027} ]\"`.\n\nWhen passing a csv, json or yaml file, relative path names are relativized to the location of the parameter file. No relativation is performed when `param_list` is a list of maps (as-is) or a yaml blob.",
"hidden": true
}
}
}
},
"allOf": [
{
"$ref": "#/definitions/input arguments"
},
{
"$ref": "#/definitions/barcode arguments"
},
{
"$ref": "#/definitions/runtime arguments"
},
{
"$ref": "#/definitions/output arguments"
},
{
"$ref": "#/definitions/nextflow input-output arguments"
}
]
}