Benchmark_001.yaml

---
id: Benchmark_001
description: simple benchmark, somewhat explicit, simple params
version: 1.0
benchmarker: "John Doe at Robinsons lab, john.doe@uzh.ch"
storage: https://storage.github.com/
storage_api: S3
storage_bucket_name: benchmark001
benchmark_yaml_spec: 0.01
software_backend: envmodules
software_environments:
  R:
    description: "R 4.3.3 with gfbf-2023 toolchain"
    easyconfig: R_4.3.3-gfbf-2023b.eb
    envmodule: R/4.3.3-gfbf-2023b
    conda: R_4.3.3_try.yaml # or perhaps not
    apptainer: http://registry.ch/R_4.3.3-gfbf-2023b.sif
  python:
    description: "Ppython3.12.0 with gfbf-2023 toolchain"
    easyconfig: python_vX-gfbf-2023b.eb
    envmodule: python/vX-gfbf-2023b
    conda: python_vX_test.yaml
    apptainer: http://registry.ch/python_vX-gfbf-2023b.sif
stages:
  - id: data
    modules:
      - id: D1
        name: "Dataset 1"
        software_environment: "python"
        repository:
          url: https://github.com/omnibenchmark-example/data.git
          commit: 061a981
      - id: D2
        name: "Dataset 2"
        software_environment: "python"
        repository:
          url: https://github.com/omnibenchmark-example/data.git
          commit: 061a981
    outputs:
      - id: data.counts
        path: "{in}/{stage}/{module}/{params}/{dataset}.txt.gz"
      - id: data.meta
        path: "{in}/{stage}/{module}/{params}/{dataset}.meta.json"
      - id: data.data_specific_params
        path: "{in}/{stage}/{module}/{params}/{dataset}_params.txt"

  - id: process
    modules:
      - id: P1
        software_environment: "R"
        parameters:
          - values: ["-a 0", "-b 0.1"]
          - values: ["-a 1", "-b 0.1"]
        repository:
          url: https://github.com/omnibenchmark-example/process.git
          commit: 24579a8
      - id: P2
        software_environment: "R"
        parameters:
          - values: ["-a 0", "-c 0"]
          - values: ["-a 1", "-c 0.1"]
        repository:
          url: https://github.com/omnibenchmark-example/process.git
          commit: 24579a8
    inputs:
      - entries: [
          data.counts,
          data.meta
        ]
    outputs:
      - id: process.filtered
        path: "{in}/{stage}/{module}/{params}/{dataset}.txt.gz"

  - id: methods
    modules:
      - id: M1
        software_environment: "python"
        exclude: [ D2 ]
        repository:
          url: https://github.com/omnibenchmark-example/method.git
          commit: 709e114
      - id: M2
        software_environment: "python"
        parameters:
          - values: ["-d1", "-e 1"]
          - values: ["-d1", "-e 2"]
        exclude:
          - D1
        repository:
          url: https://github.com/omnibenchmark-example/method.git
          commit: 709e114
    inputs:
      - entries: [
          data.counts,
          data.meta,
          data.data_specific_params
        ]
      - entries: [
          process.filtered,
          data.meta,
          data.data_specific_params
        ]
    outputs:
      - id: methods.mapping
        path: "{in}/{stage}/{module}/{params}/{dataset}.model.out.gz"

  - id: metrics
    modules:
      - id: m1
        software_environment: "python"
        repository:
          url: git@github.com:omnibenchmark-example/metric.git
          commit: ba781d7
      - id: m2
        software_environment: "python"
        repository:
          url: git@github.com:omnibenchmark-example/metric.git
          commit: ba781d7
      - id: m3
        software_environment: "python"
        repository:
          url: git@github.com:omnibenchmark-example/metric.git
          commit: ba781d7
    inputs:
      - entries: [
          methods.mapping,
          data.meta,
          data.data_specific_params
      ]
    outputs:
      - id: metrics.mapping
        path: "{in}/{stage}/{module}/{params}/{dataset}.results.txt"