Build branch build/main with version build_main (491efce)

Build pipeline: openpipelines-bio.openpipeline-spatial.build-main-kj8js

Source commit: 491efceaaf

Source message: deploy: 7f820d2607f3e1fabc0183915d1bb427715e18ae

target/executable/mapping/spaceranger_count/.config.vsh.yaml

@@ -0,0 +1,457 @@
+name: "spaceranger_count"
+namespace: "mapping"
+version: "build_main"
+authors:
+- name: "Jakub Majercik"
+  roles:
+  - "author"
+  info:
+    role: "Contributor"
+    links:
+      email: "jakub@data-intuitive.com"
+      github: "jakubmajercik"
+      linkedin: "jakubmajercik"
+    organizations:
+    - name: "Data Intuitive"
+      href: "https://www.data-intuitive.com"
+      role: "Bioinformatics Engineer"
+argument_groups:
+- name: "Inputs"
+  arguments:
+  - type: "file"
+    name: "--gex_reference"
+    description: "Path of folder containing 10x-compatible reference"
+    info: null
+    example:
+    - "/path/to/refdata-gex-GRCh38-2020-A"
+    must_exist: true
+    create_parent: true
+    required: true
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "file"
+    name: "--input"
+    description: "Path to a directory containing input FASTQ data. Individual FASTQ\
+      \ files should follow the naming convention of 10x Genomics:\n[Sample Name]_S[Sample\
+      \ Number]_L[Lane Number]_[Read Type]_001.fastq.gz\n\nWhere:\n[Sample Name] is\
+      \ the name assigned during sample preparation/sequencing\nS[Sample Number] is\
+      \ the sample index (usually S1, S2, etc.)\nL[Lane Number] identifies the sequencing\
+      \ lane (L001, L002, etc.)\n\n[Read Type] will be one of:\nR1 - Read 1 (contains\
+      \ the spatial barcode and UMI)\nR2 - Read 2 (contains the actual cDNA sequence)\n\
+      I1 - Index Read 1 (if applicable)\nI2 - Index Read 2 (if applicable)\n"
+    info: null
+    example:
+    - "/path/to/fastq_folder"
+    must_exist: true
+    create_parent: true
+    required: true
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "file"
+    name: "--probe_set"
+    description: "CSV file specifying the probe set used"
+    info: null
+    example:
+    - "Visium_Human_Transcriptome_Probe_Set_v2.0_GRCh38-2020-A.csv"
+    must_exist: true
+    create_parent: true
+    required: true
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "file"
+    name: "--cytaimage"
+    description: "Brightfield image generated by the CytAssist instrument. \nWhen\
+      \ using CytAssist workflow, either this or --image must be provided.\n"
+    info: null
+    example:
+    - "cyta_image.tif"
+    must_exist: true
+    create_parent: true
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "file"
+    name: "--image"
+    description: "H&E or fluorescence microscope image in TIFF or JPG format. \nRequired\
+      \ for standard Visium workflow, optional when using --cytaimage for CytAssist\
+      \ workflow.\n"
+    info: null
+    example:
+    - "brightfield.tif"
+    must_exist: true
+    create_parent: true
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+- name: "Outputs"
+  arguments:
+  - type: "file"
+    name: "--output"
+    description: "The folder to store the alignment results"
+    info: null
+    example:
+    - "/path/to/output"
+    must_exist: true
+    create_parent: true
+    required: true
+    direction: "output"
+    multiple: false
+    multiple_sep: ";"
+- name: "Slide Information"
+  arguments:
+  - type: "string"
+    name: "--slide"
+    description: "Visium slide serial number (e.g., 'V10J25-015')"
+    info: null
+    example:
+    - "V10J25-015"
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--area"
+    description: "Visium capture area identifier (e.g., 'A1')"
+    info: null
+    example:
+    - "A1"
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--unknown_slide"
+    description: "Use this option if the slide serial number and area were entered\
+      \ incorrectly on the CytAssist \ninstrument and the correct values are unknown.\
+      \ Not compatible with --slide, --area, or \n--slide-file options\n"
+    info: null
+    required: false
+    choices:
+    - "visium-1"
+    - "visium-2"
+    - "visium-2-large"
+    - "visium-hd"
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "file"
+    name: "--slidefile"
+    description: "Slide design file for offline use"
+    info: null
+    example:
+    - "slide_design.gpr"
+    must_exist: true
+    create_parent: true
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "boolean_true"
+    name: "--override_id"
+    description: "Overrides the slide serial number and capture area provided in the\
+      \ Cytassist image metadata"
+    info: null
+    direction: "input"
+- name: "Image Options"
+  arguments:
+  - type: "file"
+    name: "--darkimage"
+    description: "Multi-channel, dark-background fluorescence image"
+    info: null
+    example:
+    - "fluorescence.tif"
+    must_exist: true
+    create_parent: true
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "file"
+    name: "--colorizedimage"
+    description: "Color image representing pre-colored dark-background fluorescence\
+      \ images"
+    info: null
+    example:
+    - "colored_fluorescence.tif"
+    must_exist: true
+    create_parent: true
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--dapi_index"
+    description: "Index of DAPI channel (1-indexed) of fluorescence image"
+    info: null
+    example:
+    - 1
+    required: false
+    min: 1
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "double"
+    name: "--image_scale"
+    description: "Microns per microscope image pixel"
+    info: null
+    example:
+    - 0.65
+    required: false
+    min: 0.01
+    max: 10.0
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "boolean"
+    name: "--reorient_images"
+    description: "Whether to rotate and mirror image to align fiducial pattern"
+    info: null
+    default:
+    - true
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+- name: "Processing Options"
+  arguments:
+  - type: "boolean"
+    name: "--create_bam"
+    description: "Enable or disable BAM file generation"
+    info: null
+    default:
+    - true
+    required: true
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "boolean_true"
+    name: "--nosecondary"
+    description: "Disable secondary analysis (e.g., clustering)"
+    info: null
+    direction: "input"
+  - type: "integer"
+    name: "--r1_length"
+    description: "Hard trim the input Read 1 to this length before analysis"
+    info: null
+    required: false
+    min: 1
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--r2_length"
+    description: "Hard trim the input Read 2 to this length before analysis"
+    info: null
+    required: false
+    min: 1
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "boolean"
+    name: "--filter_probes"
+    description: "Whether to filter the probe set using the \"included\" column"
+    info: null
+    default:
+    - true
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--custom_bin_size"
+    description: "Bin Visium HD data to specified size in microns (4-100, even values\
+      \ only) in addition to the standard binning size (2 µm, 8 µm, 16 µm)"
+    info: null
+    required: false
+    min: 4
+    max: 100
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+- name: "Input Selection"
+  arguments:
+  - type: "string"
+    name: "--project"
+    description: "Project folder name within mkfastq output"
+    info: null
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "string"
+    name: "--sample"
+    description: "Prefix of FASTQ filenames to select"
+    info: null
+    required: false
+    direction: "input"
+    multiple: false
+    multiple_sep: ";"
+  - type: "integer"
+    name: "--lanes"
+    description: "Only use FASTQs from selected lanes"
+    info: null
+    example:
+    - 1
+    - 2
+    - 3
+    required: false
+    direction: "input"
+    multiple: true
+    multiple_sep: ";"
+resources:
+- type: "bash_script"
+  path: "script.sh"
+  is_executable: true
+- type: "file"
+  path: "nextflow_labels.config"
+  dest: "nextflow_labels.config"
+description: "Count gene expression and protein expression reads from a single capture\
+  \ area."
+test_resources:
+- type: "bash_script"
+  path: "test.sh"
+  is_executable: true
+- type: "file"
+  path: "visium"
+- type: "file"
+  path: "GRCh38"
+info: null
+status: "enabled"
+scope:
+  image: "public"
+  target: "public"
+repositories:
+- type: "github"
+  name: "openpipeline"
+  repo: "openpipelines-bio/openpipeline"
+  tag: "main_build"
+keywords:
+- "spaceranger"
+links:
+  repository: "https://github.com/openpipelines-bio/openpipeline_spatial"
+  docker_registry: "ghcr.io"
+  documentation: "https://www.10xgenomics.com/support/software/space-ranger/latest/analysis/running-pipelines/space-ranger-count"
+runners:
+- type: "executable"
+  id: "executable"
+  docker_setup_strategy: "ifneedbepullelsecachedbuild"
+- type: "nextflow"
+  id: "nextflow"
+  directives:
+    tag: "$id"
+  auto:
+    simplifyInput: true
+    simplifyOutput: false
+    transcript: false
+    publish: false
+  config:
+    labels:
+      mem1gb: "memory = 1000000000.B"
+      mem2gb: "memory = 2000000000.B"
+      mem5gb: "memory = 5000000000.B"
+      mem10gb: "memory = 10000000000.B"
+      mem20gb: "memory = 20000000000.B"
+      mem50gb: "memory = 50000000000.B"
+      mem100gb: "memory = 100000000000.B"
+      mem200gb: "memory = 200000000000.B"
+      mem500gb: "memory = 500000000000.B"
+      mem1tb: "memory = 1000000000000.B"
+      mem2tb: "memory = 2000000000000.B"
+      mem5tb: "memory = 5000000000000.B"
+      mem10tb: "memory = 10000000000000.B"
+      mem20tb: "memory = 20000000000000.B"
+      mem50tb: "memory = 50000000000000.B"
+      mem100tb: "memory = 100000000000000.B"
+      mem200tb: "memory = 200000000000000.B"
+      mem500tb: "memory = 500000000000000.B"
+      mem1gib: "memory = 1073741824.B"
+      mem2gib: "memory = 2147483648.B"
+      mem4gib: "memory = 4294967296.B"
+      mem8gib: "memory = 8589934592.B"
+      mem16gib: "memory = 17179869184.B"
+      mem32gib: "memory = 34359738368.B"
+      mem64gib: "memory = 68719476736.B"
+      mem128gib: "memory = 137438953472.B"
+      mem256gib: "memory = 274877906944.B"
+      mem512gib: "memory = 549755813888.B"
+      mem1tib: "memory = 1099511627776.B"
+      mem2tib: "memory = 2199023255552.B"
+      mem4tib: "memory = 4398046511104.B"
+      mem8tib: "memory = 8796093022208.B"
+      mem16tib: "memory = 17592186044416.B"
+      mem32tib: "memory = 35184372088832.B"
+      mem64tib: "memory = 70368744177664.B"
+      mem128tib: "memory = 140737488355328.B"
+      mem256tib: "memory = 281474976710656.B"
+      mem512tib: "memory = 562949953421312.B"
+      cpu1: "cpus = 1"
+      cpu2: "cpus = 2"
+      cpu5: "cpus = 5"
+      cpu10: "cpus = 10"
+      cpu20: "cpus = 20"
+      cpu50: "cpus = 50"
+      cpu100: "cpus = 100"
+      cpu200: "cpus = 200"
+      cpu500: "cpus = 500"
+      cpu1000: "cpus = 1000"
+    script:
+    - "includeConfig(\"nextflow_labels.config\")"
+  debug: false
+  container: "docker"
+engines:
+- type: "docker"
+  id: "docker"
+  image: "ghcr.io/data-intuitive/spaceranger:3.1"
+  target_registry: "images.viash-hub.com"
+  target_tag: "build_main"
+  namespace_separator: "/"
+  setup:
+  - type: "docker"
+    run:
+    - "DEBIAN_FRONTEND=noninteractive apt update && \\\napt upgrade -y && apt install\
+      \ -y procps && rm -rf /var/lib/apt/lists/*\n"
+  entrypoint: []
+  cmd: null
+- type: "native"
+  id: "native"
+build_info:
+  config: "src/mapping/spaceranger_count/config.vsh.yaml"
+  runner: "executable"
+  engine: "docker|native"
+  output: "target/executable/mapping/spaceranger_count"
+  executable: "target/executable/mapping/spaceranger_count/spaceranger_count"
+  viash_version: "0.9.3"
+  git_commit: "491efceaaf171f50aaa1d28f690c1e974cffc456"
+  git_remote: "https://github.com/openpipelines-bio/openpipeline_spatial"
+package_config:
+  name: "openpipeline_spatial"
+  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"

target/executable/mapping/spaceranger_count/nextflow_labels.config

@@ -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)
+  }
+}