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

Build branch main with version main (173327cc)

Browse Source 
Build pipeline: vsh-ci-build-template-k4qzr

Source commit: 173327cc56

Source message: Cellranger multi conversion: fix combined AB + CB probe experiments (#1062)
This commit is contained in:
CI
2025-08-22 08:50:18 +00:00
commit cd5554d22f
2226 changed files with 1154442 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

285
target/executable/files/make_params/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,285 @@
name: "make_params"
namespace: "files"
version: "main"
authors:
- name: "Angela Oliveira Pisco"
roles:
- "author"
info:
role: "Contributor"
links:
github: "aopisco"
orcid: "0000-0003-0142-2355"
linkedin: "aopisco"
organizations:
- name: "Insitro"
href: "https://insitro.com"
role: "Director of Computational Biology"
- name: "Open Problems"
href: "https://openproblems.bio"
role: "Core Member"
- name: "Robrecht Cannoodt"
roles:
- "maintainer"
- "author"
info:
role: "Core Team Member"
links:
email: "robrecht@data-intuitive.com"
github: "rcannood"
orcid: "0000-0003-3641-729X"
linkedin: "robrechtcannoodt"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Science Engineer"
- name: "Open Problems"
href: "https://openproblems.bio"
role: "Core Member"
argument_groups:
- name: "Arguments"
arguments:
- type: "file"
name: "--base_dir"
description: "Base directory to search recursively"
info: null
example:
- "/path/to/dir"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--pattern"
description: "An optional regular expression. Only file names which match the\
\ regular expression will be matched."
info: null
example:
- "*.fastq.gz"
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--n_dirname_drop"
description: "For every matched file, the parent directory will be traversed N\
\ times."
info: null
default:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--n_basename_id"
description: "The unique identifiers will consist of at least N dirnames."
info: null
default:
- 0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--id_name"
description: "The name for storing the identifier field in the yaml."
info: null
default:
- "id"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--path_name"
description: "The name for storing the path field in the yaml."
info: null
default:
- "path"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--group_name"
description: "Top level name for the group of entries."
info: null
example:
- "param_list"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output"
description: "Output YAML file."
info: null
example:
- "params.yaml"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
resources:
- type: "r_script"
path: "script.R"
is_executable: true
- type: "file"
path: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Looks for files in a directory and turn it in a params file."
test_resources:
- type: "bash_script"
path: "test_make_params.sh"
is_executable: true
- type: "file"
path: "src"
info: null
status: "enabled"
scope:
image: "public"
target: "public"
license: "MIT"
links:
repository: "https://github.com/openpipelines-bio/openpipeline"
docker_registry: "ghcr.io"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
label:
- "singlecpu"
- "lowmem"
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: "ghcr.io/data-intuitive/randpy:r4.0"
target_registry: "images.viash-hub.com"
target_tag: "main"
namespace_separator: "/"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/files/make_params/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/files/make_params"
executable: "target/executable/files/make_params/make_params"
viash_version: "0.9.4"
git_commit: "173327cc5670aa8bd5cf473827de80b602c90092"
git_remote: "https://github.com/openpipelines-bio/openpipeline"
git_tag: "0.2.0-2055-g173327cc"
package_config:
name: "openpipeline"
version: "main"
summary: "Best-practice workflows for single-cell multi-omics analyses.\n"
description: "OpenPipelines are extensible single cell analysis pipelines for reproducible\
\ and large-scale single cell processing using [Viash](https://viash.io) and [Nextflow](https://www.nextflow.io/).\n\
\nIn terms of workflows, the following has been made available, but keep in mind\
\ that\nindividual tools and functionality can be executed as standalone components\
\ as well.\n\n * Demultiplexing: conversion of raw sequencing data to FASTQ objects.\n\
\ * Ingestion: Read mapping and generating a count matrix.\n * Single sample\
\ processing: cell filtering and doublet detection.\n * Multisample processing:\
\ Count transformation, normalization, QC metric calulations.\n * Integration:\
\ Clustering, integration and batch correction using single and multimodal methods.\n\
\ * Downstream analysis workflows\n"
info:
test_resources:
- type: "s3"
path: "s3://openpipelines-data"
dest: "resources_test"
nextflow_labels_ci:
- path: "src/workflows/utils/labels_ci.config"
description: "Adds the correct memory and CPU labels when running on the Viash\
\ Hub CI."
viash_version: "0.9.4"
source: "src"
target: "target"
config_mods:
- ".resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n\
.runners[.type == 'nextflow'].config.script := 'includeConfig(\"nextflow_labels.config\"\
)'\n"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'main'"
keywords:
- "single-cell"
- "multimodal"
license: "MIT"
organization: "vsh"
links:
repository: "https://github.com/openpipelines-bio/openpipeline"
docker_registry: "ghcr.io"
homepage: "https://openpipelines.bio"
documentation: "https://openpipelines.bio/fundamentals"
issue_tracker: "https://github.com/openpipelines-bio/openpipeline/issues"

1310
target/executable/files/make_params/make_params Executable file
View File

File diff suppressed because it is too large Load Diff

48
target/executable/files/make_params/nextflow_labels.config Normal file
View File

@@ -0,0 +1,48 @@
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
// The memory a task is assinged increases with each attempt
// uncomment the line below and adjust the value to set a global upper limit on the memory.
// resourceLimits = [ memory: 240.Gb ]
// CPU resources
withLabel: singlecpu { cpus = 1 }
withLabel: lowcpu { cpus = 4 }
withLabel: midcpu { cpus = 10 }
withLabel: highcpu { cpus = 20 }
// Memory resources
withLabel: lowmem { memory = { task?.resourceLimits?.memory && task?.maxRetries && task.attempt >= task.maxRetries ? task.resourceLimits.memory : 4.GB * task.attempt } }
withLabel: midmem { memory = { task?.resourceLimits?.memory && task?.maxRetries && task.attempt >= task.maxRetries ? task.resourceLimits.memory : 25.GB * task.attempt } }
withLabel: highmem { memory = { task?.resourceLimits?.memory && task?.maxRetries && task.attempt >= task.maxRetries ? task.resourceLimits.memory : 50.GB * task.attempt } }
withLabel: veryhighmem { memory = { task?.resourceLimits?.memory && task?.maxRetries && task.attempt >= task.maxRetries ? task.resourceLimits.memory : 75.GB * task.attempt } }
// Disk space
withLabel: lowdisk {
disk = {process.disk ? process.disk : null}
}
withLabel: middisk {
disk = {process.disk ? process.disk : null}
}
withLabel: highdisk {
disk = {process.disk ? process.disk : null}
}
withLabel: veryhighdisk {
disk = {process.disk ? process.disk : null}
}
// NOTE: The above labels intentionally do not have an effect by default.
// The user should set the disk space requirements by adding the following
// to the compute environment:
//
// withLabel: lowdisk { disk = { 20.GB * task.attempt } }
// withLabel: middisk { disk = { 100.GB * task.attempt } }
// withLabel: highdisk { disk = { 200.GB * task.attempt } }
// withLabel: veryhighdisk { disk = { 500.GB * task.attempt } }
}