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

245
target/executable/compression/compress_h5mu/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,245 @@
name: "compress_h5mu"
namespace: "compression"
version: "main"
authors:
- name: "Dries Schaumont"
roles:
- "maintainer"
info:
role: "Core Team Member"
links:
email: "dries@data-intuitive.com"
github: "DriesSchaumont"
orcid: "0000-0002-4389-0440"
linkedin: "dries-schaumont"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist"
argument_groups:
- name: "Arguments"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Path to the input .h5mu."
info: null
example:
- "sample_path"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output"
description: "location of output file."
info: null
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--output_compression"
description: "Compression format to use for the output AnnData and/or Mudata objects.\n\
By default no compression is applied.\n"
info: null
example:
- "gzip"
required: false
choices:
- "gzip"
- "lzf"
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "python_script"
path: "script.py"
is_executable: true
- type: "file"
path: "compress_h5mu.py"
- type: "file"
path: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Compress a MuData file. \n"
test_resources:
- type: "python_script"
path: "run_test.py"
is_executable: true
- type: "file"
path: "e18_mouse_brain_fresh_5k_filtered_feature_bc_matrix_subset_unique_obs.h5mu"
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: "python:3.10-slim"
target_registry: "images.viash-hub.com"
target_tag: "main"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "anndata~=0.11.1"
- "mudata~=0.3.1"
script:
- "exec(\"try:\\n import awkward\\nexcept ModuleNotFoundError:\\n exit(0)\\\
nelse: exit(1)\")"
upgrade: true
test_setup:
- type: "apt"
packages:
- "git"
interactive: false
- type: "python"
user: false
packages:
- "viashpy==0.8.0"
github:
- "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/compression/compress_h5mu/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/compression/compress_h5mu"
executable: "target/executable/compression/compress_h5mu/compress_h5mu"
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"

1160
target/executable/compression/compress_h5mu/compress_h5mu Executable file
View File

File diff suppressed because it is too large Load Diff

87
target/executable/compression/compress_h5mu/compress_h5mu.py Normal file
View File

@@ -0,0 +1,87 @@
import shutil
from anndata import AnnData
from mudata import write_h5ad
from h5py import File as H5File
from h5py import Group, Dataset
from pathlib import Path
from typing import Union, Literal
from functools import partial
def compress_h5mu(
input_path: Union[str, Path],
output_path: Union[str, Path],
compression: Union[Literal["gzip"], Literal["lzf"]],
):
input_path, output_path = str(input_path), str(output_path)
def copy_attributes(in_object, out_object):
for key, value in in_object.attrs.items():
out_object.attrs[key] = value
def visit_path(
output_h5: H5File,
compression: Union[Literal["gzip"], Literal["lzf"]],
name: str,
object: Union[Group, Dataset],
):
if isinstance(object, Group):
new_group = output_h5.create_group(name)
copy_attributes(object, new_group)
elif isinstance(object, Dataset):
# Compression only works for non-scalar Dataset objects
# Scalar objects dont have a shape defined
if not object.compression and object.shape not in [None, ()]:
new_dataset = output_h5.create_dataset(
name, data=object, compression=compression
)
copy_attributes(object, new_dataset)
else:
output_h5.copy(object, name)
else:
raise NotImplementedError(
f"Could not copy element {name}, "
f"type has not been implemented yet: {type(object)}"
)
with (
H5File(input_path, "r") as input_h5,
H5File(output_path, "w", userblock_size=512) as output_h5,
):
copy_attributes(input_h5, output_h5)
input_h5.visititems(partial(visit_path, output_h5, compression))
with open(input_path, "rb") as input_bytes:
# Mudata puts metadata like this in the first 512 bytes:
# MuData (format-version=0.1.0;creator=muon;creator-version=0.2.0)
# See mudata/_core/io.py, read_h5mu() function
starting_metadata = input_bytes.read(100)
# The metadata is padded with extra null bytes up until 512 bytes
truncate_location = starting_metadata.find(b"\x00")
starting_metadata = starting_metadata[:truncate_location]
with open(output_path, "br+") as f:
nbytes = f.write(starting_metadata)
f.write(b"\0" * (512 - nbytes))
def write_h5ad_to_h5mu_with_compression(
output_file: Union[str, Path],
h5mu: Union[str, Path],
modality_name: str,
modality_data: AnnData,
output_compression=None,
):
output_file = Path(output_file)
h5mu = Path(h5mu)
output_file_uncompressed = (
output_file.with_name(output_file.stem + "_uncompressed.h5mu")
if output_compression
else output_file
)
shutil.copyfile(h5mu, output_file_uncompressed)
write_h5ad(filename=output_file_uncompressed, mod=modality_name, data=modality_data)
if output_compression:
compress_h5mu(
output_file_uncompressed, output_file, compression=output_compression
)
output_file_uncompressed.unlink()

48
target/executable/compression/compress_h5mu/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 } }
}

219
target/executable/compression/tar_extract/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,219 @@
name: "tar_extract"
namespace: "compression"
version: "main"
argument_groups:
- name: "Arguments"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Input file"
info: null
example:
- "input.tar.gz"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Folder to restore file(s) to."
info: null
example:
- "output_folder"
must_exist: true
create_parent: true
required: true
direction: "output"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--strip_components"
alternatives:
- "-s"
description: "Strip this amount of leading components from file names on extraction.\
\ For example, to extract only 'myfile.txt' from an archive containing the structure\
\ `this/goes/deep/myfile.txt', use 3 to strip 'this/goes/deep/'."
info: null
example:
- 1
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--exclude"
alternatives:
- "-e"
description: "Prevents any file or member whose name matches the shell wildcard\
\ (pattern) from being extracted."
info: null
example:
- "docs/figures"
required: false
direction: "input"
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: "Extract files from a tar archive"
test_resources:
- type: "bash_script"
path: "test.sh"
is_executable: true
- type: "file"
path: "LICENSE"
info: null
status: "deprecated"
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: "ubuntu:latest"
target_registry: "images.viash-hub.com"
target_tag: "main"
namespace_separator: "/"
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/compression/tar_extract/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/compression/tar_extract"
executable: "target/executable/compression/tar_extract/tar_extract"
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"

48
target/executable/compression/tar_extract/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 } }
}

1180
target/executable/compression/tar_extract/tar_extract Executable file
View File

File diff suppressed because it is too large Load Diff