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

Build branch v0.1 with version v0.1.0 (7a9cc3c)

Browse Source 
Build pipeline: openpipelines-bio.openpipeline-spatial.v0.1-67f47

Source commit: 7a9cc3c862

Source message: update package version
This commit is contained in:
CI
2025-08-25 07:52:57 +00:00
commit d102f5567c
471 changed files with 244424 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

264
target/executable/convert/from_xenium_to_h5mu/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,264 @@
name: "from_xenium_to_h5mu"
namespace: "convert"
version: "v0.1.0"
authors:
- name: "Dorien Roosen"
roles:
- "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: "file"
name: "--input"
alternatives:
- "-i"
description: "Input folder. Must contain the output from a Xenium run."
info: null
example:
- "xenium_output_bundle"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Output .h5mu file."
info: null
example:
- "xenium.h5mu"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--obsm_coordinates"
description: "Name of the .obsm slot under which to store the cell centroid coordinates."
info: null
default:
- "spatial"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--uns_experiment"
description: "Name of the .uns slot under which to store the Xenium experiment\
\ specifications."
info: null
default:
- "xenium_experiment"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--uns_metrics"
description: "Name of the .uns slot under which to store the summary QC metrics."
info: null
default:
- "xenium_metrics"
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: "Converts the output from Xenium to a single .h5mu file, where the count\
\ matrix is written to the `rna` modality.\nThe following files are expected to\
\ be present in the Xenium output bundle:\n├── cell_feature_matrix.h5\n├── cells.parquet\n\
├── experiment.xenium\n└── metrics_summary.csv\n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "xenium_tiny"
info: null
status: "enabled"
scope:
image: "public"
target: "public"
repositories:
- type: "vsh"
name: "openpipeline"
repo: "openpipeline"
tag: "v3.0.0"
links:
repository: "https://github.com/openpipelines-bio/openpipeline_spatial"
docker_registry: "ghcr.io"
runners:
- type: "executable"
id: "executable"
docker_setup_strategy: "ifneedbepullelsecachedbuild"
- type: "nextflow"
id: "nextflow"
directives:
label:
- "lowmem"
- "singlecpu"
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: "v0.1.0"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "anndata~=0.11.1"
- "mudata~=0.3.1"
- "scanpy~=1.10.4"
- "pyarrow"
script:
- "exec(\"try:\\n import awkward\\nexcept ModuleNotFoundError:\\n exit(0)\\\
nelse: exit(1)\")"
upgrade: true
test_setup:
- type: "python"
user: false
packages:
- "viashpy==0.9.0"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/convert/from_xenium_to_h5mu/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/convert/from_xenium_to_h5mu"
executable: "target/executable/convert/from_xenium_to_h5mu/from_xenium_to_h5mu"
viash_version: "0.9.4"
git_commit: "7a9cc3c862e39ab584bea178b10aeb4b19d46325"
git_remote: "https://github.com/openpipelines-bio/openpipeline_spatial"
package_config:
name: "openpipeline_spatial"
version: "v0.1.0"
info:
test_resources:
- type: "s3"
path: "s3://openpipelines-bio/openpipeline_spatial/resources_test"
dest: "resources_test"
repositories:
- type: "vsh"
name: "openpipeline"
repo: "openpipeline"
tag: "v3.0.0"
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 := 'v0.1.0'"
organization: "vsh"
links:
repository: "https://github.com/openpipelines-bio/openpipeline_spatial"
docker_registry: "ghcr.io"

1289
target/executable/convert/from_xenium_to_h5mu/from_xenium_to_h5mu Executable file
View File

File diff suppressed because it is too large Load Diff

68
target/executable/convert/from_xenium_to_h5mu/nextflow_labels.config Normal file
View File

@@ -0,0 +1,68 @@
process {
// Default resources for components that hardly do any processing
memory = { 2.GB * task.attempt }
cpus = 1
// Retry for exit codes that have something to do with memory issues
errorStrategy = { task.exitStatus in 137..140 ? 'retry' : 'terminate' }
maxRetries = 3
maxMemory = null
// CPU resources
withLabel: singlecpu { cpus = 1 }
withLabel: lowcpu { cpus = 4 }
withLabel: midcpu { cpus = 10 }
withLabel: highcpu { cpus = 20 }
// Memory resources
withLabel: lowmem { memory = { get_memory( 50.GB * task.attempt ) } }
withLabel: midmem { memory = { get_memory( 50.GB * task.attempt ) } }
withLabel: highmem { memory = { get_memory( 50.GB * task.attempt ) } }
withLabel: veryhighmem { memory = { get_memory( 75.GB * task.attempt ) } }
// Disk space
// Nextflow apparently can't handle empty directives, i.e.
// withLabel: lowdisk {}
// so for that reason we have to add a dummy directive
withLabel: lowdisk {
dummyDirective = "dummyValue"
}
withLabel: middisk {
dummyDirective = "dummyValue"
}
withLabel: highdisk {
dummyDirective = "dummyValue"
}
withLabel: veryhighdisk {
dummyDirective = "dummyValue"
}
// 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 } }
}
def get_memory(to_compare) {
if (!process.containsKey("maxMemory") || !process.maxMemory) {
return to_compare
}
try {
if (process.containsKey("maxRetries") && process.maxRetries && task.attempt == (process.maxRetries as int)) {
return process.maxMemory
}
else if (to_compare.compareTo(process.maxMemory as nextflow.util.MemoryUnit) == 1) {
return max_memory as nextflow.util.MemoryUnit
}
else {
return to_compare
}
} catch (all) {
println "Error processing memory resources. Please check that process.maxMemory '${process.maxMemory}' and process.maxRetries '${process.maxRetries}' are valid!"
System.exit(1)
}
}

12
target/executable/convert/from_xenium_to_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