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

Build branch openpipeline/v4.0 with version v4.0.0 to openpipeline on branch v4.0 (de02293c)

Browse Source 
Build pipeline: openpipelines-bio.openpipeline.v4.0.0-kd9qj

Source commit: de02293c9e

Source message: Bump version to v4.0.0
This commit is contained in:
CI
2026-01-26 11:23:20 +00:00
commit 4caaaf68ef
2355 changed files with 1217591 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

308
target/executable/filter/delimit_fraction/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,308 @@
name: "delimit_fraction"
namespace: "filter"
version: "v4.0.0"
authors:
- name: "Dries Schaumont"
roles:
- "author"
- "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: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "Input h5mu file"
info: null
example:
- "input.h5mu"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--modality"
description: "Which modality from the input MuData file to process.\n"
info: null
default:
- "rna"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--obs_fraction_column"
description: "Name of column from .var dataframe selecting\na column that contains\
\ floating point values between 0 and 1.\n"
info: null
example:
- "fraction_mitochondrial"
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "Output h5mu file."
info: null
example:
- "output.h5mu"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--obs_name_filter"
description: "In which .obs slot to store a boolean array corresponding to which\
\ observations should be removed."
info: null
required: true
direction: "input"
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: ";"
- name: "Arguments"
arguments:
- type: "double"
name: "--min_fraction"
description: "Min fraction for an observation to be retained (True in output)."
info: null
default:
- 0.0
required: false
min: 0.0
max: 1.0
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--max_fraction"
description: "Max fraction for an observation to be retained (True in output)."
info: null
default:
- 1.0
required: false
min: 0.0
max: 1.0
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "python_script"
path: "script.py"
is_executable: true
- type: "file"
path: "setup_logger.py"
- type: "file"
path: "compress_h5mu.py"
- type: "file"
path: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Turns a column containing values between 0 and 1 into a boolean column\
\ based on thresholds.\n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "pbmc_1k_protein_v3"
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:3.12-slim"
target_registry: "images.viash-hub.com"
target_tag: "v4.0.0"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "anndata~=0.12.7"
- "awkward"
- "mudata~=0.3.2"
script:
- "exec(\"try:\\n import zarr; from importlib.metadata import version\\nexcept\
\ ModuleNotFoundError:\\n exit(0)\\nelse: assert int(version(\\\"zarr\\\"\
).partition(\\\".\\\")[0]) > 2\")"
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/filter/delimit_fraction/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/filter/delimit_fraction"
executable: "target/executable/filter/delimit_fraction/delimit_fraction"
viash_version: "0.9.4"
git_commit: "de02293c9e13198622b988dac952b2c8c70a1e35"
git_remote: "https://github.com/openpipelines-bio/openpipeline"
package_config:
name: "openpipeline"
version: "v4.0.0"
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\"\
)'"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v4.0.0'"
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"

87
target/executable/filter/delimit_fraction/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()

1402
target/executable/filter/delimit_fraction/delimit_fraction Executable file
View File

File diff suppressed because it is too large Load Diff

48
target/executable/filter/delimit_fraction/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 } }
}

12
target/executable/filter/delimit_fraction/setup_logger.py Normal file
View File

@@ -0,0 +1,12 @@
def setup_logger():
import logging
from sys import stdout
logger = logging.getLogger()
logger.setLevel(logging.INFO)
console_handler = logging.StreamHandler(stdout)
logFormatter = logging.Formatter("%(asctime)s %(levelname)-8s %(message)s")
console_handler.setFormatter(logFormatter)
logger.addHandler(console_handler)
return logger

276
target/executable/filter/do_filter/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,276 @@
name: "do_filter"
namespace: "filter"
version: "v4.0.0"
authors:
- name: "Robrecht Cannoodt"
roles:
- "maintainer"
- "contributor"
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: "--input"
description: "Input h5mu file"
info: null
example:
- "input.h5mu"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--modality"
description: "Which modality from the input MuData file to process.\n"
info: null
default:
- "rna"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--obs_filter"
description: "Which .obs columns to use to filter the observations by."
info: null
example:
- "filter_with_x"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "string"
name: "--var_filter"
description: "Which .var columns to use to filter the observations by."
info: null
example:
- "filter_with_x"
required: false
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--output"
description: "Output h5mu file."
info: null
example:
- "output.h5mu"
must_exist: true
create_parent: true
required: false
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: "setup_logger.py"
- type: "file"
path: "compress_h5mu.py"
- type: "file"
path: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Remove observations and variables based on specified .obs and .var columns.\n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "pbmc_1k_protein_v3"
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:3.12-slim"
target_registry: "images.viash-hub.com"
target_tag: "v4.0.0"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "anndata~=0.12.7"
- "awkward"
- "mudata~=0.3.2"
script:
- "exec(\"try:\\n import zarr; from importlib.metadata import version\\nexcept\
\ ModuleNotFoundError:\\n exit(0)\\nelse: assert int(version(\\\"zarr\\\"\
).partition(\\\".\\\")[0]) > 2\")"
upgrade: true
test_setup:
- type: "python"
user: false
packages:
- "viashpy==0.8.0"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/filter/do_filter/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/filter/do_filter"
executable: "target/executable/filter/do_filter/do_filter"
viash_version: "0.9.4"
git_commit: "de02293c9e13198622b988dac952b2c8c70a1e35"
git_remote: "https://github.com/openpipelines-bio/openpipeline"
package_config:
name: "openpipeline"
version: "v4.0.0"
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\"\
)'"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v4.0.0'"
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"

87
target/executable/filter/do_filter/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()

1259
target/executable/filter/do_filter/do_filter Executable file
View File

File diff suppressed because it is too large Load Diff

48
target/executable/filter/do_filter/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 } }
}

12
target/executable/filter/do_filter/setup_logger.py Normal file
View File

@@ -0,0 +1,12 @@
def setup_logger():
import logging
from sys import stdout
logger = logging.getLogger()
logger.setLevel(logging.INFO)
console_handler = logging.StreamHandler(stdout)
logFormatter = logging.Formatter("%(asctime)s %(levelname)-8s %(message)s")
console_handler.setFormatter(logFormatter)
logger.addHandler(console_handler)
return logger

369
target/executable/filter/filter_with_counts/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,369 @@
name: "filter_with_counts"
namespace: "filter"
version: "v4.0.0"
authors:
- name: "Dries De Maeyer"
roles:
- "author"
info:
role: "Core Team Member"
links:
email: "ddemaeyer@gmail.com"
github: "ddemaeyer"
linkedin: "dries-de-maeyer-b46a814"
organizations:
- name: "Janssen Pharmaceuticals"
href: "https://www.janssen.com"
role: "Principal Scientist"
- 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: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "Input h5mu file"
info: null
example:
- "input.h5mu"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--modality"
description: "Which modality from the input MuData file to process.\n"
info: null
default:
- "rna"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--layer"
description: "Location of the count matrix. If specified, will be used to select\
\ a key from .layers,\notherwise .X is used.\n"
info: null
example:
- "raw_counts"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "Output h5mu file."
info: null
example:
- "output.h5mu"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--do_subset"
description: "Whether to subset before storing the output."
info: null
direction: "input"
- type: "string"
name: "--obs_name_filter"
description: "In which .obs slot to store a boolean array corresponding to which\
\ observations should be removed."
info: null
default:
- "filter_with_counts"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--var_name_filter"
description: "In which .var slot to store a boolean array corresponding to which\
\ variables should be removed."
info: null
default:
- "filter_with_counts"
required: false
direction: "input"
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: ";"
- name: "Arguments"
arguments:
- type: "integer"
name: "--min_counts"
description: "Minimum number of counts captured per cell."
info: null
example:
- 200
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--max_counts"
description: "Maximum number of counts captured per cell."
info: null
example:
- 5000000
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_genes_per_cell"
description: "Minimum of non-zero values per cell."
info: null
example:
- 200
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--max_genes_per_cell"
description: "Maximum of non-zero values per cell."
info: null
example:
- 1500000
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_cells_per_gene"
description: "Minimum of non-zero values per gene."
info: null
example:
- 3
required: false
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "python_script"
path: "script.py"
is_executable: true
- type: "file"
path: "setup_logger.py"
- type: "file"
path: "compress_h5mu.py"
- type: "file"
path: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Filter scRNA-seq data based on the primary QC metrics. \nThis is based\
\ on both the UMI counts, the gene counts \nand the mitochondrial genes (genes starting\
\ with mt/MT).\n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "pbmc_1k_protein_v3"
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:3.12-slim"
target_registry: "images.viash-hub.com"
target_tag: "v4.0.0"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "anndata~=0.12.7"
- "awkward"
- "mudata~=0.3.2"
script:
- "exec(\"try:\\n import zarr; from importlib.metadata import version\\nexcept\
\ ModuleNotFoundError:\\n exit(0)\\nelse: assert int(version(\\\"zarr\\\"\
).partition(\\\".\\\")[0]) > 2\")"
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/filter/filter_with_counts/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/filter/filter_with_counts"
executable: "target/executable/filter/filter_with_counts/filter_with_counts"
viash_version: "0.9.4"
git_commit: "de02293c9e13198622b988dac952b2c8c70a1e35"
git_remote: "https://github.com/openpipelines-bio/openpipeline"
package_config:
name: "openpipeline"
version: "v4.0.0"
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\"\
)'"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v4.0.0'"
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"

87
target/executable/filter/filter_with_counts/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()

1485
target/executable/filter/filter_with_counts/filter_with_counts Executable file
View File

File diff suppressed because it is too large Load Diff

48
target/executable/filter/filter_with_counts/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 } }
}

12
target/executable/filter/filter_with_counts/setup_logger.py Normal file
View File

@@ -0,0 +1,12 @@
def setup_logger():
import logging
from sys import stdout
logger = logging.getLogger()
logger.setLevel(logging.INFO)
console_handler = logging.StreamHandler(stdout)
logFormatter = logging.Formatter("%(asctime)s %(levelname)-8s %(message)s")
console_handler.setFormatter(logFormatter)
logger.addHandler(console_handler)
return logger

294
target/executable/filter/filter_with_pattern/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,294 @@
name: "filter_with_pattern"
namespace: "filter"
version: "v4.0.0"
authors:
- name: "Dorien Roosen"
roles:
- "author"
info:
role: "Core Team Member"
links:
email: "dorien@data-intuitive.com"
github: "dorien-er"
linkedin: "dorien-roosen"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist"
argument_groups:
- name: "Inputs"
arguments:
- type: "file"
name: "--input"
description: "Input h5mu file"
info: null
example:
- "input.h5mu"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--modality"
description: "Which modality from the input MuData file to process.\n"
info: null
default:
- "rna"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--var_gene_names"
description: "The .var field containing the gene names to be filtered. If not\
\ provided, `.var.index` will be used.\n"
info: null
example:
- "gene_symbol"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--pattern"
description: "A regex pattern to filter the gene names.\n"
info: null
example:
- "MIR\\d+"
- "AL\\d+"
- "LINC\\d+"
- "AC\\d+"
- "AP\\d+"
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- name: "Outputs"
arguments:
- type: "file"
name: "--output"
description: "Output h5mu file."
info: null
example:
- "output.h5mu"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--do_subset"
description: "Whether to subset before storing the output."
info: null
direction: "input"
- type: "string"
name: "--var_name_filter"
description: "In which .var slot to store a boolean array corresponding to which\
\ variables should be removed."
info: null
default:
- "filter_with_pattern"
required: false
direction: "input"
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: "setup_logger.py"
- type: "file"
path: "compress_h5mu.py"
- type: "file"
path: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Filter a MuData object based on gene names using a regex.\n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "pbmc_1k_protein_v3"
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:
- "lowcpu"
- "midmem"
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:3.12-slim"
target_registry: "images.viash-hub.com"
target_tag: "v4.0.0"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "anndata~=0.12.7"
- "awkward"
- "mudata~=0.3.2"
script:
- "exec(\"try:\\n import zarr; from importlib.metadata import version\\nexcept\
\ ModuleNotFoundError:\\n exit(0)\\nelse: assert int(version(\\\"zarr\\\"\
).partition(\\\".\\\")[0]) > 2\")"
upgrade: true
test_setup:
- type: "python"
user: false
packages:
- "viashpy==0.8.0"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/filter/filter_with_pattern/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/filter/filter_with_pattern"
executable: "target/executable/filter/filter_with_pattern/filter_with_pattern"
viash_version: "0.9.4"
git_commit: "de02293c9e13198622b988dac952b2c8c70a1e35"
git_remote: "https://github.com/openpipelines-bio/openpipeline"
package_config:
name: "openpipeline"
version: "v4.0.0"
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\"\
)'"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v4.0.0'"
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"

87
target/executable/filter/filter_with_pattern/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()

1303
target/executable/filter/filter_with_pattern/filter_with_pattern Executable file
View File

File diff suppressed because it is too large Load Diff

48
target/executable/filter/filter_with_pattern/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 } }
}

12
target/executable/filter/filter_with_pattern/setup_logger.py Normal file
View File

@@ -0,0 +1,12 @@
def setup_logger():
import logging
from sys import stdout
logger = logging.getLogger()
logger.setLevel(logging.INFO)
console_handler = logging.StreamHandler(stdout)
logFormatter = logging.Formatter("%(asctime)s %(levelname)-8s %(message)s")
console_handler.setFormatter(logFormatter)
logger.addHandler(console_handler)
return logger

426
target/executable/filter/filter_with_scrublet/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,426 @@
name: "filter_with_scrublet"
namespace: "filter"
version: "v4.0.0"
authors:
- name: "Dries De Maeyer"
roles:
- "contributor"
info:
role: "Core Team Member"
links:
email: "ddemaeyer@gmail.com"
github: "ddemaeyer"
linkedin: "dries-de-maeyer-b46a814"
organizations:
- name: "Janssen Pharmaceuticals"
href: "https://www.janssen.com"
role: "Principal Scientist"
- name: "Robrecht Cannoodt"
roles:
- "maintainer"
- "contributor"
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: "--input"
description: "Input h5mu file"
info: null
example:
- "input.h5mu"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--modality"
description: "Which modality from the input MuData file to process.\n"
info: null
default:
- "rna"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--layer"
description: "Input layer to use as data for calculating doublets. .X is used\
\ not specified."
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output"
description: "Output h5mu file."
info: null
example:
- "output.h5mu"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--obs_name_filter"
description: "In which .obs slot to store a boolean array corresponding to which\
\ observations should be filtered out."
info: null
default:
- "filter_with_scrublet"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--do_subset"
description: "Whether to subset before storing the output."
info: null
direction: "input"
- type: "string"
name: "--obs_name_doublet_score"
description: "Name of the doublet scores column in the obs slot of the returned\
\ object."
info: null
default:
- "scrublet_doublet_score"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--expected_doublet_rate"
description: "The estimated fraction of doublets as from the experimental setup.\n"
info: null
required: false
min: 0.0
max: 1.0
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--stdev_doublet_rate"
description: "Uncertainty in the expected doublet rate."
info: null
required: false
min: 0.0
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--n_neighbors"
description: "Number of neighbors used to construct the KNN classifier of observed\
\ transcriptomes\nand simulated doublets.\n"
info: null
required: false
min: 0
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--sim_doublet_ratio"
description: "Number of doublets to simulate relative to the number of observed\n\
transcriptomes.\n"
info: null
required: false
min: 0.0
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_counts"
description: "The number of minimal UMI counts per cell that have to be present\
\ for initial cell detection."
info: null
default:
- 2
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--min_cells"
description: "The number of cells in which UMIs for a gene were detected."
info: null
default:
- 3
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "double"
name: "--min_gene_variablity_percent"
description: "Used for gene filtering prior to PCA. Keep the most highly variable\
\ genes (in the top min_gene_variability_pctl percentile), as measured by the\
\ v-statistic [Klein et al., Cell 2015]."
info: null
default:
- 85.0
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--num_pca_components"
description: "Number of principal components to use during PCA dimensionality\
\ reduction."
info: null
default:
- 30
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--distance_metric"
description: "The distance metric used for computing similarities."
info: null
default:
- "euclidean"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--allow_automatic_threshold_detection_fail"
description: "When scrublet fails to automatically determine the double score\
\ threshold, \nallow the component to continue and set the output columns to\
\ NA.\n"
info: null
direction: "input"
- 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: "setup_logger.py"
- type: "file"
path: "compress_h5mu.py"
- type: "file"
path: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Doublet detection using the Scrublet method (Wolock, Lopez and Klein,\
\ 2019).\nThe method tests for potential doublets by using the expression profiles\
\ of\ncells to generate synthetic potential doubles which are tested against cells.\
\ \nThe method returns a \"doublet score\" on which it calls for potential doublets.\n\
\nFor the source code please visit https://github.com/AllonKleinLab/scrublet.\n\n\
For 10x we expect the doublet rates to be:\n Multiplet Rate (%) - # of Cells Loaded\
\ - # of Cells Recovered\n ~0.4% ~800 ~500\n ~0.8% ~1,600 ~1,000\n ~1.6% ~3,200\
\ ~2,000\n ~2.3% ~4,800 ~3,000\n ~3.1% ~6,400 ~4,000\n ~3.9% ~8,000 ~5,000\n\
\ ~4.6% ~9,600 ~6,000\n ~5.4% ~11,200 ~7,000\n ~6.1% ~12,800 ~8,000\n ~6.9%\
\ ~14,400 ~9,000\n ~7.6% ~16,000 ~10,000\n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "pbmc_1k_protein_v3"
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"
docker_run_args:
- "--env NUMBA_CACHE_DIR=/tmp"
- type: "nextflow"
id: "nextflow"
directives:
label:
- "highcpu"
- "midmem"
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:3.13-slim"
target_registry: "images.viash-hub.com"
target_tag: "v4.0.0"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
- "build-essential"
interactive: false
- type: "python"
user: false
packages:
- "anndata~=0.12.7"
- "awkward"
- "mudata~=0.3.2"
- "scanpy~=1.11.4"
- "scrublet"
- "annoy==1.17.3"
script:
- "exec(\"try:\\n import zarr; from importlib.metadata import version\\nexcept\
\ ModuleNotFoundError:\\n exit(0)\\nelse: assert int(version(\\\"zarr\\\"\
).partition(\\\".\\\")[0]) > 2\")"
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/filter/filter_with_scrublet/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/filter/filter_with_scrublet"
executable: "target/executable/filter/filter_with_scrublet/filter_with_scrublet"
viash_version: "0.9.4"
git_commit: "de02293c9e13198622b988dac952b2c8c70a1e35"
git_remote: "https://github.com/openpipelines-bio/openpipeline"
package_config:
name: "openpipeline"
version: "v4.0.0"
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\"\
)'"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v4.0.0'"
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"

87
target/executable/filter/filter_with_scrublet/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()

1653
target/executable/filter/filter_with_scrublet/filter_with_scrublet Executable file
View File

File diff suppressed because it is too large Load Diff

48
target/executable/filter/filter_with_scrublet/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 } }
}

12
target/executable/filter/filter_with_scrublet/setup_logger.py Normal file
View File

@@ -0,0 +1,12 @@
def setup_logger():
import logging
from sys import stdout
logger = logging.getLogger()
logger.setLevel(logging.INFO)
console_handler = logging.StreamHandler(stdout)
logFormatter = logging.Formatter("%(asctime)s %(levelname)-8s %(message)s")
console_handler.setFormatter(logFormatter)
logger.addHandler(console_handler)
return logger

266
target/executable/filter/intersect_obs/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,266 @@
name: "intersect_obs"
namespace: "filter"
version: "v4.0.0"
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"
- name: "Isabelle Bergiers"
roles:
- "contributor"
info:
role: "Contributor"
links:
github: "Isabelle-b"
orcid: "0000-0001-9622-7960"
organizations:
- name: "Janssen Pharmaceuticals"
href: "https://www.janssen.com"
role: "Scientist OMICS Technology"
argument_groups:
- name: "Arguments"
arguments:
- type: "file"
name: "--input"
description: "Input h5mu file"
info: null
example:
- "input.h5mu"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--modalities"
description: "Which modalities from the input MuData file to process.\n"
info: null
example:
- "rna"
- "prot"
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--output"
description: "Output h5mu file."
info: null
example:
- "output.h5mu"
must_exist: true
create_parent: true
required: false
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: "setup_logger.py"
- type: "file"
path: "compress_h5mu.py"
- type: "file"
path: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Create an intersection between two or more modalities.\n\nThis component\
\ removes any observations which are not present in all modalities.\n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "pbmc_1k_protein_v3"
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:
- "lowcpu"
- "midmem"
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:3.13-slim"
target_registry: "images.viash-hub.com"
target_tag: "v4.0.0"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "anndata~=0.12.7"
- "awkward"
- "mudata~=0.3.2"
script:
- "exec(\"try:\\n import zarr; from importlib.metadata import version\\nexcept\
\ ModuleNotFoundError:\\n exit(0)\\nelse: assert int(version(\\\"zarr\\\"\
).partition(\\\".\\\")[0]) > 2\")"
upgrade: true
test_setup:
- type: "python"
user: false
packages:
- "viashpy==0.8.0"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/filter/intersect_obs/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/filter/intersect_obs"
executable: "target/executable/filter/intersect_obs/intersect_obs"
viash_version: "0.9.4"
git_commit: "de02293c9e13198622b988dac952b2c8c70a1e35"
git_remote: "https://github.com/openpipelines-bio/openpipeline"
package_config:
name: "openpipeline"
version: "v4.0.0"
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\"\
)'"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v4.0.0'"
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"

87
target/executable/filter/intersect_obs/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()

1237
target/executable/filter/intersect_obs/intersect_obs Executable file
View File

File diff suppressed because it is too large Load Diff

48
target/executable/filter/intersect_obs/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 } }
}

12
target/executable/filter/intersect_obs/setup_logger.py Normal file
View File

@@ -0,0 +1,12 @@
def setup_logger():
import logging
from sys import stdout
logger = logging.getLogger()
logger.setLevel(logging.INFO)
console_handler = logging.StreamHandler(stdout)
logFormatter = logging.Formatter("%(asctime)s %(levelname)-8s %(message)s")
console_handler.setFormatter(logFormatter)
logger.addHandler(console_handler)
return logger

246
target/executable/filter/remove_modality/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,246 @@
name: "remove_modality"
namespace: "filter"
version: "v4.0.0"
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"
description: "Input h5mu file"
info: null
example:
- "input.h5mu"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--modality"
description: "Name(s) of the modality to remove\n"
info: null
required: true
direction: "input"
multiple: true
multiple_sep: ";"
- type: "file"
name: "--output"
description: "Output h5mu file."
info: null
example:
- "output.h5mu"
must_exist: true
create_parent: true
required: false
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: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Remove a modality from a .h5mu file\n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "pbmc_1k_protein_v3_filtered_feature_bc_matrix.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:3.12-slim"
target_registry: "images.viash-hub.com"
target_tag: "v4.0.0"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "anndata~=0.12.7"
- "awkward"
- "mudata~=0.3.2"
script:
- "exec(\"try:\\n import zarr; from importlib.metadata import version\\nexcept\
\ ModuleNotFoundError:\\n exit(0)\\nelse: assert int(version(\\\"zarr\\\"\
).partition(\\\".\\\")[0]) > 2\")"
upgrade: true
test_setup:
- type: "python"
user: false
packages:
- "viashpy==0.8.0"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/filter/remove_modality/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/filter/remove_modality"
executable: "target/executable/filter/remove_modality/remove_modality"
viash_version: "0.9.4"
git_commit: "de02293c9e13198622b988dac952b2c8c70a1e35"
git_remote: "https://github.com/openpipelines-bio/openpipeline"
package_config:
name: "openpipeline"
version: "v4.0.0"
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\"\
)'"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v4.0.0'"
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/filter/remove_modality/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 } }
}

1183
target/executable/filter/remove_modality/remove_modality Executable file
View File

File diff suppressed because it is too large Load Diff

260
target/executable/filter/subset_h5mu/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,260 @@
name: "subset_h5mu"
namespace: "filter"
version: "v4.0.0"
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"
description: "Input h5mu file"
info: null
example:
- "input.h5mu"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--modality"
description: "Which modality from the input MuData file to process.\n"
info: null
default:
- "rna"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output"
description: "Output h5mu file."
info: null
example:
- "output.h5mu"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--number_of_observations"
description: "Number of observations to be selected from the h5mu file."
info: null
example:
- 5
required: false
direction: "input"
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: "setup_logger.py"
- type: "file"
path: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Create a subset of a mudata file by selecting the first number of observations\n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "pbmc_1k_protein_v3_filtered_feature_bc_matrix.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:3.12-slim"
target_registry: "images.viash-hub.com"
target_tag: "v4.0.0"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "anndata~=0.12.7"
- "awkward"
- "mudata~=0.3.2"
script:
- "exec(\"try:\\n import zarr; from importlib.metadata import version\\nexcept\
\ ModuleNotFoundError:\\n exit(0)\\nelse: assert int(version(\\\"zarr\\\"\
).partition(\\\".\\\")[0]) > 2\")"
upgrade: true
test_setup:
- type: "python"
user: false
packages:
- "viashpy==0.8.0"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/filter/subset_h5mu/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/filter/subset_h5mu"
executable: "target/executable/filter/subset_h5mu/subset_h5mu"
viash_version: "0.9.4"
git_commit: "de02293c9e13198622b988dac952b2c8c70a1e35"
git_remote: "https://github.com/openpipelines-bio/openpipeline"
package_config:
name: "openpipeline"
version: "v4.0.0"
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\"\
)'"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v4.0.0'"
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/filter/subset_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 } }
}

12
target/executable/filter/subset_h5mu/setup_logger.py Normal file
View File

@@ -0,0 +1,12 @@
def setup_logger():
import logging
from sys import stdout
logger = logging.getLogger()
logger.setLevel(logging.INFO)
console_handler = logging.StreamHandler(stdout)
logFormatter = logging.Formatter("%(asctime)s %(levelname)-8s %(message)s")
console_handler.setFormatter(logFormatter)
logger.addHandler(console_handler)
return logger

1205
target/executable/filter/subset_h5mu/subset_h5mu Executable file
View File

File diff suppressed because it is too large Load Diff

296
target/executable/filter/subset_obsp/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,296 @@
name: "subset_obsp"
namespace: "filter"
version: "v4.0.0"
authors:
- name: "Dorien Roosen"
roles:
- "author"
- "maintainer"
info:
role: "Core Team Member"
links:
email: "dorien@data-intuitive.com"
github: "dorien-er"
linkedin: "dorien-roosen"
organizations:
- name: "Data Intuitive"
href: "https://www.data-intuitive.com"
role: "Data Scientist"
argument_groups:
- name: "Arguments"
arguments:
- 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: ";"
- name: "Input"
arguments:
- type: "file"
name: "--input"
description: "Input h5mu file"
info: null
example:
- "input.h5mu"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--modality"
description: "Which modality from the input MuData file to process.\n"
info: null
default:
- "rna"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--input_obsp_key"
description: "The .obsp field to be filtered."
info: null
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--input_obs_key"
description: "The .obs column to filter on."
info: null
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--input_obs_value"
description: "The value to filter on in the .obs column."
info: null
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- name: "Output"
arguments:
- type: "file"
name: "--output"
description: "Output h5mu file."
info: null
example:
- "output.h5mu"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--output_obsm_key"
description: "The .obsm key to store the subset in."
info: null
required: true
direction: "input"
multiple: false
multiple_sep: ";"
resources:
- type: "python_script"
path: "script.py"
is_executable: true
- type: "file"
path: "setup_logger.py"
- type: "file"
path: "compress_h5mu.py"
- type: "file"
path: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Create a subset of an .obsp field in a mudata file, by filtering the\
\ columns based on the values of an .obs column. The resulting subset is moved to\
\ an .obsm slot.\n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "pbmc_1k_protein_v3_mms.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:3.12-slim"
target_registry: "images.viash-hub.com"
target_tag: "v4.0.0"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "anndata~=0.12.7"
- "awkward"
- "mudata~=0.3.2"
script:
- "exec(\"try:\\n import zarr; from importlib.metadata import version\\nexcept\
\ ModuleNotFoundError:\\n exit(0)\\nelse: assert int(version(\\\"zarr\\\"\
).partition(\\\".\\\")[0]) > 2\")"
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/filter/subset_obsp/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/filter/subset_obsp"
executable: "target/executable/filter/subset_obsp/subset_obsp"
viash_version: "0.9.4"
git_commit: "de02293c9e13198622b988dac952b2c8c70a1e35"
git_remote: "https://github.com/openpipelines-bio/openpipeline"
package_config:
name: "openpipeline"
version: "v4.0.0"
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\"\
)'"
- ".engines += { type: \"native\" }"
- ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
- ".engines[.type == 'docker'].target_tag := 'v4.0.0'"
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"

87
target/executable/filter/subset_obsp/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/filter/subset_obsp/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 } }
}

12
target/executable/filter/subset_obsp/setup_logger.py Normal file
View File

@@ -0,0 +1,12 @@
def setup_logger():
import logging
from sys import stdout
logger = logging.getLogger()
logger.setLevel(logging.INFO)
console_handler = logging.StreamHandler(stdout)
logFormatter = logging.Formatter("%(asctime)s %(levelname)-8s %(message)s")
console_handler.setFormatter(logFormatter)
logger.addHandler(console_handler)
return logger

1290
target/executable/filter/subset_obsp/subset_obsp Executable file
View File

File diff suppressed because it is too large Load Diff