name: "densmap"
namespace: "dimred"
version: "fix-integration-tests"
authors:
- name: "Jakub Majercik"
  roles:
  - "maintainer"
  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: "--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"
    info: null
    default:
    - "rna"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--uns_neighbors"
    description: "The `.uns` neighbors slot as output by the `find_neighbors` component."
    info: null
    default:
    - "neighbors"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--obsm_pca"
    description: "The slot in `.obsm` where the PCA results are stored.\n"
    info: null
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--obsm_knn_indices"
    description: "The slot in `.obsm` where the kNN indices are stored.\n"
    info: null
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--obsm_knn_distances"
    description: "The slot in `.obsm` where the kNN distances are stored.\n"
    info: null
    required: true
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Outputs"
  arguments:
  - type: "file"
    name: "--output"
    alternatives:
    - "-o"
    description: "Output h5mu file."
    info: null
    example:
    - "output.h5mu"
    must_exist: true
    create_parent: true
    required: true
    direction: "output"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--output_compression"
    description: "The compression format to be used on the output h5mu object."
    info: null
    example:
    - "gzip"
    required: false
    choices:
    - "gzip"
    - "lzf"
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--obsm_output"
    description: "The .obsm key to use for storing the densMAP results.."
    info: null
    default:
    - "X_densmap"
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Arguments UMAP"
  arguments:
  - type: "double"
    name: "--min_dist"
    description: "The effective minimum distance between embedded points. Smaller\
      \ values will result \nin a more clustered/clumped embedding where nearby points\
      \ on the manifold are drawn \ncloser together, while larger values will result\
      \ on a more even dispersal of points. \nThe value should be set relative to\
      \ the spread value, which determines the scale at \nwhich embedded points will\
      \ be spread out. \n"
    info: null
    default:
    - 0.5
    required: false
    min: 0.0
    max: 10.0
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "double"
    name: "--spread"
    description: "The effective scale of embedded points. In combination with `min_dist`\
      \ this \ndetermines how clustered/clumped the embedded points are.\n"
    info: null
    default:
    - 1.0
    required: false
    min: 0.0
    max: 10.0
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--num_components"
    description: "The number of dimensions of the embedding."
    info: null
    default:
    - 2
    required: false
    min: 1
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--max_iter"
    description: "The number of iterations (epochs) of the optimization. Called `n_epochs`\
      \ \nin the original UMAP. Default is set to 500 if \nneighbors['connectivities'].shape[0]\
      \ <= 10000, else 200.\n"
    info: null
    default:
    - 0
    required: false
    min: 0
    max: 1000
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "double"
    name: "--alpha"
    description: "The initial learning rate for the embedding optimization."
    info: null
    default:
    - 1.0
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "double"
    name: "--gamma"
    description: "Weighting applied to negative samples in low dimensional embedding\
      \ optimization. \nValues higher than one will result in greater weight being\
      \ given to negative samples.\n"
    info: null
    default:
    - 1.0
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "integer"
    name: "--negative_sample_rate"
    description: "The number of negative samples to select per positive sample\nin\
      \ the optimization process. Increasing this value will result\nin greater repulsive\
      \ force being applied, greater optimization\ncost, but slightly more accuracy.\n"
    info: null
    default:
    - 5
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "string"
    name: "--init_pos"
    description: "How to initialize the low dimensional embedding. Called `init` in\
      \ the original UMAP. Options are:\n  \n* Any key from `.obsm`\n* `'paga'`: positions\
      \ from `paga()`\n* `'spectral'`: use a spectral embedding of the graph\n* `'random'`:\
      \ assign initial embedding positions at random.\n"
    info: null
    default:
    - "spectral"
    required: false
    choices:
    - "paga"
    - "spectral"
    - "random"
    direction: "input"
    multiple: false
    multiple_sep: ";"
- name: "Arguments densMAP"
  arguments:
  - type: "double"
    name: "--lambda"
    description: "Controls the regularization weight of the density correlation term\
      \ in densMAP. \nHigher values prioritize density preservation over the UMAP\
      \ objective, and vice versa \nfor values closer to zero. Setting this parameter\
      \ to zero is equivalent to running \nthe original UMAP algorithm.\n"
    info: null
    default:
    - 2.0
    required: false
    min: 0.01
    max: 10.0
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "double"
    name: "--fraction"
    description: "Controls the fraction of epochs (between 0 and 1) where the density-augmented\
      \ objective \nis used in densMAP. The first (1 - dens_frac) fraction of epochs\
      \ optimize the original \nUMAP objective before introducing the density correlation\
      \ term.\n"
    info: null
    default:
    - 0.3
    required: false
    direction: "input"
    multiple: false
    multiple_sep: ";"
  - type: "double"
    name: "--var_shift"
    description: "A small constant added to the variance of local radii in the embedding\
      \ when calculating \nthe density correlation objective to prevent numerical\
      \ instability from dividing by a \nsmall number.\n"
    info: null
    default:
    - 0.1
    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: "A modification of UMAP that adds an extra cost term in order to preserve\
  \ information \nabout the relative local density of the data. It is performed on\
  \ the same inputs as UMAP.\n"
test_resources:
- type: "python_script"
  path: "test.py"
  is_executable: true
- type: "file"
  path: "pbmc_1k_protein_v3"
- type: "file"
  path: "openpipelinetestutils"
  dest: "openpipelinetestutils"
info: null
status: "enabled"
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:
    - "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:3.12-slim"
  target_registry: "images.viash-hub.com"
  target_tag: "fix-integration-tests"
  namespace_separator: "/"
  setup:
  - type: "apt"
    packages:
    - "procps"
    interactive: false
  - type: "python"
    user: false
    packages:
    - "anndata==0.10.8"
    - "mudata~=0.2.4"
    - "pandas!=2.1.2"
    - "numpy<2.0.0"
    - "umap-learn"
    upgrade: true
  test_setup:
  - type: "docker"
    copy:
    - "openpipelinetestutils /opt/openpipelinetestutils"
  - type: "python"
    user: false
    packages:
    - "/opt/openpipelinetestutils"
    upgrade: true
  - type: "python"
    user: false
    packages:
    - "viashpy==0.8.0"
    upgrade: true
  entrypoint: []
  cmd: null
- type: "native"
  id: "native"
build_info:
  config: "src/dimred/densmap/config.vsh.yaml"
  runner: "executable"
  engine: "docker|native"
  output: "target/executable/dimred/densmap"
  executable: "target/executable/dimred/densmap/densmap"
  viash_version: "0.9.0"
  git_commit: "5e3f3231456facaf14da57fa563d4de58492ca82"
  git_remote: "https://x-access-token:ghs_EujrUcz58S6J44CLSvromEPEcaMxTc30MU1j@github.com/openpipelines-bio/openpipeline"
  git_tag: "0.2.0-1942-g5e3f3231"
package_config:
  name: "openpipeline"
  version: "fix-integration-tests"
  info:
    test_resources:
    - type: "s3"
      path: "s3://openpipelines-data"
      dest: "resources_test"
  viash_version: "0.9.0"
  source: "src"
  target: "target"
  config_mods:
  - ".test_resources += {path: '/src/base/openpipelinetestutils', dest: 'openpipelinetestutils'}\n\
    .resources += {path: '/src/workflows/utils/labels.config', dest: 'nextflow_labels.config'}\n\
    .runners[.type == 'nextflow'].directives.tag := '$id'\n.runners[.type == 'nextflow'].config.script\
    \ := 'includeConfig(\"nextflow_labels.config\")'\n"
  - ".engines += { type: \"native\" }"
  - ".engines[.type == 'docker'].target_registry := 'images.viash-hub.com'"
  - ".engines[.type == 'docker'].target_tag := 'fix-integration-tests'"
  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"