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

Build branch build/main with version build_main (4e97231)

Browse Source 
Build pipeline: openpipelines-bio.openpipeline-spatial.build-main-vddz8

Source commit: 4e9723127d

Source message: deploy: bd077dc2a66dae009780f4c95ebb8a0f19116470
This commit is contained in:
CI
2025-06-06 07:12:05 +00:00
commit 9097024992
67 changed files with 25764 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

262
target/executable/convert/from_cosmx_to_h5mu/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,262 @@
name: "from_cosmx_to_h5mu"
namespace: "convert"
version: "build_main"
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"
- name: "Weiwei Schultz"
roles:
- "contributor"
info:
role: "Contributor"
organizations:
- name: "Janssen R&D US"
role: "Associate Director Data Sciences"
argument_groups:
- name: "Arguments"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Input folder. Must contain the output from a NanoString CosMx run."
info: null
example:
- "cosmx_data"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--dataset_id"
description: "ID of the dataset. By default expects the following file structure:\n\
path/to/dataset/\n├── CellComposite/\n├── CellLabels/\n├── CellOverlay/\n├──\
\ CompartmentLabels/\n├── <dataset_id>_exprMat_file.csv\n├── <dataset_id>_fov_positions_file.csv\n\
├── <dataset_id>_metadata_file.csv\n└── <dataset_id>_tx_file.csv \n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--modality"
info: null
default:
- "rna"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "The 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"
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 NanoString experiment into a MuData objcet.\n\
\ - `<dataset_id>_exprMat_file.csv`: File containing the counts.\n - `<dataset_id>`_metadata_file:\
\ File containing the spatial coordinates and additional cell-level metadata.\n\
\ - `<dataset_id>_fov_file.csv`: File containing the coordinates of all the fields\
\ of view.\nIn addition to reading the regular Nanostring output, it loads CellComposite\
\ and CellLabels directories, if present,\ncontaining the images.\n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "Lung5_Rep2_tiny"
info: null
status: "enabled"
scope:
image: "public"
target: "public"
repositories:
- type: "github"
name: "openpipeline"
repo: "openpipelines-bio/openpipeline"
tag: "main_build"
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: "build_main"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "squidpy~=1.6.5"
- "mudata~=0.3.1"
upgrade: true
test_setup:
- type: "apt"
packages:
- "git"
interactive: false
- type: "python"
user: false
packages:
- "viashpy==0.8.0"
github:
- "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/convert/from_cosmx_to_h5mu/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/convert/from_cosmx_to_h5mu"
executable: "target/executable/convert/from_cosmx_to_h5mu/from_cosmx_to_h5mu"
viash_version: "0.9.3"
git_commit: "4e9723127ddb6353bf8f7f2ed65f880f77cbe764"
git_remote: "https://github.com/openpipelines-bio/openpipeline_spatial"
package_config:
name: "incubator"
version: "build_main"
info:
test_resources:
- type: "s3"
path: "s3://openpipelines-bio/openpipeline_spatial/resources_test"
dest: "resources_test"
repositories:
- type: "github"
name: "openpipeline"
repo: "openpipelines-bio/openpipeline"
tag: "main_build"
viash_version: "0.9.3"
source: "src"
target: "target"
config_mods:
- ".resources += {path: '/src/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 := 'build_main'"
organization: "vsh"
links:
repository: "https://github.com/openpipelines-bio/openpipeline_spatial"
docker_registry: "ghcr.io"

1236
target/executable/convert/from_cosmx_to_h5mu/from_cosmx_to_h5mu Executable file
View File

File diff suppressed because it is too large Load Diff

68
target/executable/convert/from_cosmx_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_cosmx_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

248
target/executable/convert/from_spatialdata_to_h5mu/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,248 @@
name: "from_spatialdata_to_h5mu"
namespace: "convert"
version: "build_main"
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"
- name: "Weiwei Schultz"
roles:
- "contributor"
info:
role: "Contributor"
organizations:
- name: "Janssen R&D US"
role: "Associate Director Data Sciences"
argument_groups:
- name: "Arguments"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Input zarr folder where the SpatialData object is stored."
info: null
example:
- "input.zarr"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--modality"
info: null
default:
- "rna"
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "The 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"
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: "Reads in the Tables field stored in a SpatialData object and converts\
\ it to an h5mu file.\n \n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "xenium_tiny.zarr"
info: null
status: "enabled"
scope:
image: "public"
target: "public"
repositories:
- type: "github"
name: "openpipeline"
repo: "openpipelines-bio/openpipeline"
tag: "main_build"
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: "build_main"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "spatialdata~=0.3.0"
- "spatialdata-io~=0.1.7"
- "mudata~=0.3.1"
upgrade: true
test_setup:
- type: "apt"
packages:
- "git"
interactive: false
- type: "python"
user: false
packages:
- "viashpy==0.8.0"
github:
- "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/convert/from_spatialdata_to_h5mu/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/convert/from_spatialdata_to_h5mu"
executable: "target/executable/convert/from_spatialdata_to_h5mu/from_spatialdata_to_h5mu"
viash_version: "0.9.3"
git_commit: "4e9723127ddb6353bf8f7f2ed65f880f77cbe764"
git_remote: "https://github.com/openpipelines-bio/openpipeline_spatial"
package_config:
name: "incubator"
version: "build_main"
info:
test_resources:
- type: "s3"
path: "s3://openpipelines-bio/openpipeline_spatial/resources_test"
dest: "resources_test"
repositories:
- type: "github"
name: "openpipeline"
repo: "openpipelines-bio/openpipeline"
tag: "main_build"
viash_version: "0.9.3"
source: "src"
target: "target"
config_mods:
- ".resources += {path: '/src/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 := 'build_main'"
organization: "vsh"
links:
repository: "https://github.com/openpipelines-bio/openpipeline_spatial"
docker_registry: "ghcr.io"

1194
target/executable/convert/from_spatialdata_to_h5mu/from_spatialdata_to_h5mu Executable file
View File

File diff suppressed because it is too large Load Diff

68
target/executable/convert/from_spatialdata_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_spatialdata_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

345
target/executable/convert/from_xenium_to_spatialdata/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,345 @@
name: "from_xenium_to_spatialdata"
namespace: "convert"
version: "build_main"
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"
- name: "Weiwei Schultz"
roles:
- "contributor"
info:
role: "Contributor"
organizations:
- name: "Janssen R&D US"
role: "Associate Director Data Sciences"
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_data"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "Zarr directory where the SpatialData object will be stored"
info: null
example:
- "xenium_data.zarr"
must_exist: true
create_parent: true
required: false
direction: "output"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--cells_boundaries"
description: "Whether to read cell boundaries (polygons)."
info: null
default:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--nucleus_boundaries"
description: "Whether to read nucleus boundaries (polygons)."
info: null
default:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean_true"
name: "--cells_as_circles"
description: "Whether to read cells also as circles (the center and the radius\
\ of each circle is computed from the corresponding labels cell)."
info: null
direction: "input"
- type: "boolean"
name: "--cells_labels"
description: "Whether to read cell labels (raster). The polygonal version of the\
\ cell labels are simplified for visualization purposes, and using the raster\
\ version is recommended for analysis."
info: null
default:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--transcripts"
description: "Whether to read transcripts."
info: null
default:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--nucleus_labels"
description: "Whether to read nucleus labels (raster). The polygonal version of\
\ the nucleus labels are simplified for visualization purposes, and using the\
\ raster version is recommended for analysis."
info: null
default:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--morphology_mip"
description: "Whether to read the morphology mip image (available in versions\
\ < 2.0.0)."
info: null
default:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--morphology_focus"
description: "Whether to read the morphology focus image."
info: null
default:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--aligned_images"
description: "Whether to also parse, when available, additional H&E or IF aligned\
\ images. For more control over the aligned images being read, in particular,\
\ to specify the axes of the aligned images, please set this parameter to False\
\ and use the xenium_aligned_image function directly."
info: null
default:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "boolean"
name: "--cells_table"
description: "Whether to read the cell annotations in the AnnData table."
info: null
default:
- true
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--n_jobs"
info: null
default:
- 1
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: "nextflow_labels.config"
dest: "nextflow_labels.config"
description: "Converts the output from 10X Genomics Xenium dataset into a SpatialData\
\ objcet.\nBy default, the following files will be converted:\n - `experiment.xenium`:\
\ File containing specifications.\n - `nucleus_boundaries.parquet`: Polygons of\
\ nucleus boundaries.\n - `cell_boundaries.parquet`: Polygons of cell boundaries.\n\
\ - `transcripts.parquet`: File containing transcripts.\n - `cell_feature_matrix.h5`:\
\ File containing cell feature matrix.\n - `cells.parquet`: File containing cell\
\ metadata.\n - `morphology_mip.ome.tif`: File containing morphology mip.\n -\
\ `morphology_focus.ome.tif`: File containing morphology focus.\n \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: "github"
name: "openpipeline"
repo: "openpipelines-bio/openpipeline"
tag: "main_build"
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: "build_main"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "spatialdata-io~=0.1.7"
upgrade: true
test_setup:
- type: "apt"
packages:
- "git"
interactive: false
- type: "python"
user: false
packages:
- "viashpy==0.8.0"
- "spatialdata~=0.3.0"
github:
- "openpipelines-bio/core#subdirectory=packages/python/openpipeline_testutils"
upgrade: true
entrypoint: []
cmd: null
- type: "native"
id: "native"
build_info:
config: "src/convert/from_xenium_to_spatialdata/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/convert/from_xenium_to_spatialdata"
executable: "target/executable/convert/from_xenium_to_spatialdata/from_xenium_to_spatialdata"
viash_version: "0.9.3"
git_commit: "4e9723127ddb6353bf8f7f2ed65f880f77cbe764"
git_remote: "https://github.com/openpipelines-bio/openpipeline_spatial"
package_config:
name: "incubator"
version: "build_main"
info:
test_resources:
- type: "s3"
path: "s3://openpipelines-bio/openpipeline_spatial/resources_test"
dest: "resources_test"
repositories:
- type: "github"
name: "openpipeline"
repo: "openpipelines-bio/openpipeline"
tag: "main_build"
viash_version: "0.9.3"
source: "src"
target: "target"
config_mods:
- ".resources += {path: '/src/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 := 'build_main'"
organization: "vsh"
links:
repository: "https://github.com/openpipelines-bio/openpipeline_spatial"
docker_registry: "ghcr.io"

1449
target/executable/convert/from_xenium_to_spatialdata/from_xenium_to_spatialdata Executable file
View File

File diff suppressed because it is too large Load Diff

68
target/executable/convert/from_xenium_to_spatialdata/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_spatialdata/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

248
target/executable/filter/subset_cosmx/.config.vsh.yaml Normal file
View File

@@ -0,0 +1,248 @@
name: "subset_cosmx"
namespace: "filter"
version: "build_main"
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"
- name: "Weiwei Schultz"
roles:
- "contributor"
info:
role: "Contributor"
organizations:
- name: "Janssen R&D US"
role: "Associate Director Data Sciences"
argument_groups:
- name: "Arguments"
arguments:
- type: "file"
name: "--input"
alternatives:
- "-i"
description: "Input folder. Must contain the output from a NanoString CosMx run."
info: null
example:
- "cosmx_data"
must_exist: true
create_parent: true
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "string"
name: "--dataset_id"
description: "ID of the dataset. By default expects the following file structure:\n\
path/to/dataset/\n├── CellComposite/\n├── CellLabels/\n├── CellOverlay/\n├──\
\ CompartmentLabels/\n├── <dataset_id>_exprMat_file.csv\n├── <dataset_id>_fov_positions_file.csv\n\
├── <dataset_id>_metadata_file.csv\n└── <dataset_id>_tx_file.csv \n"
info: null
required: false
direction: "input"
multiple: false
multiple_sep: ";"
- type: "integer"
name: "--num_fovs"
description: "Number of fields of views to keep. Will keep only the first <num_fovs>\
\ fields of view."
info: null
required: true
direction: "input"
multiple: false
multiple_sep: ";"
- type: "file"
name: "--output"
alternatives:
- "-o"
description: "The directory where the subset data will be stored."
info: null
example:
- "cosmx_data_tiny"
must_exist: true
create_parent: true
required: false
direction: "output"
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: "Filters the output from NanoString experiment to keep only a subset\
\ of the fields of view.\nExpected input folder structure:\npath/to/dataset/\n \
\ ├── CellComposite/\n ├── CellLabels/\n ├── CellOverlay/\n ├── CompartmentLabels/\n\
\ ├── <dataset_id>_exprMat_file.csv\n ├── <dataset_id>_fov_positions_file.csv\n\
\ ├── <dataset_id>_metadata_file.csv\n └── <dataset_id>_tx_file.csv \n"
test_resources:
- type: "python_script"
path: "test.py"
is_executable: true
- type: "file"
path: "Lung5_Rep2_tiny"
info: null
status: "enabled"
scope:
image: "public"
target: "public"
repositories:
- type: "github"
name: "openpipeline"
repo: "openpipelines-bio/openpipeline"
tag: "main_build"
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: "build_main"
namespace_separator: "/"
setup:
- type: "apt"
packages:
- "procps"
interactive: false
- type: "python"
user: false
packages:
- "squidpy~=1.6.5"
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_cosmx/config.vsh.yaml"
runner: "executable"
engine: "docker|native"
output: "target/executable/filter/subset_cosmx"
executable: "target/executable/filter/subset_cosmx/subset_cosmx"
viash_version: "0.9.3"
git_commit: "4e9723127ddb6353bf8f7f2ed65f880f77cbe764"
git_remote: "https://github.com/openpipelines-bio/openpipeline_spatial"
package_config:
name: "incubator"
version: "build_main"
info:
test_resources:
- type: "s3"
path: "s3://openpipelines-bio/openpipeline_spatial/resources_test"
dest: "resources_test"
repositories:
- type: "github"
name: "openpipeline"
repo: "openpipelines-bio/openpipeline"
tag: "main_build"
viash_version: "0.9.3"
source: "src"
target: "target"
config_mods:
- ".resources += {path: '/src/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 := 'build_main'"
organization: "vsh"
links:
repository: "https://github.com/openpipelines-bio/openpipeline_spatial"
docker_registry: "ghcr.io"

68
target/executable/filter/subset_cosmx/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/filter/subset_cosmx/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

1232
target/executable/filter/subset_cosmx/subset_cosmx Executable file
View File

File diff suppressed because it is too large Load Diff