CWL Research Objects

Stian Soiland-Reyes

eScience lab, The University of Manchester

ELIXIR Workflow Interoperability implementation study
Hinxton, 2018-01-26

cwlVersion: v1.0
class: Workflow
inputs:
  inp: File
  ex: string

outputs:
  classout:
    type: File
    outputSource: compile/classfile

steps:
  untar:
    run: tar-param.cwl
    in:
      tarfile: inp
      extractfile: ex
    out: [example_out]

  compile:
    run: arguments.cwl
    in:
      src: untar/example_out
    out: [classfile]
{
  "@context" : [ "https://w3id.org/bundle/context" ],
  "id" : "/",
  "manifest" : [ "manifest.json" ],
  "createdOn" : "2017-08-24T10:57:46.325Z",
  "createdBy" : {
    "uri" : "https://view.commonwl.org",
    "name" : "Common Workflow Language Viewer"
  },
  "authoredBy" : [ {
    "uri" : "mailto:peter.amstutz@curoverse.com",
    "name" : "Peter Amstutz"
  }, {
    "uri" : "mailto:luka.stojanovic@sbgenomics.com",
    "name" : "Luka Stojanovic"
  }, {
    "uri" : "mailto:crusoe@ucdavis.edu",
    "name" : "Michael R. Crusoe"
  }, {
    "uri" : "mailto:porter@porter.st",
    "name" : "Andrey Kartashov"
  }, {
    "uri" : "mailto:janko.simonovic@sbgenomics.com",
    "name" : "Janko Simonovic"
  } ],
  "retrievedFrom" : "https://github.com/common-workflow-language/workflows/blob/lobstr-v1/workflows/lobSTR/",
  "retrievedOn" : "2017-08-24T10:57:46.325Z",
  "retrievedBy" : {
    "uri" : "https://view.commonwl.org",
    "name" : "Common Workflow Language Viewer"
  },
  "history" : [ "http:/git2prov.org/git2prov?giturl=https:/github.com/common-workflow-language/workflows.git&serialization=PROV-JSON" ],
  "aggregates" : [ {
    "uri" : "/workflow/tmp_2.fq",
    "mediatype" : "application/octet-stream",
    "createdOn" : "2017-08-24T10:57:46.923Z",
    "authoredBy" : [ {
      "uri" : "mailto:peter.amstutz@curoverse.com",
      "name" : "Peter Amstutz"
    } ],
    "retrievedFrom" : "https://raw.githubusercontent.com/common-workflow-language/workflows/lobstr-v1/workflows/lobSTR/tmp_2.fq",
    "retrievedBy" : {
      "uri" : "https://view.commonwl.org",
      "name" : "Common Workflow Language Viewer"
    },
    "bundledAs" : {
      "uri" : "urn:uuid:61579f3e-63e6-49c2-b780-f67b2df461b7",
      "folder" : "/workflow/"
    }
  }, {
    "uri" : "/workflow/lobSTR-demo.json",
    "mediatype" : "application/json",
    "createdOn" : "2017-08-24T10:57:47.216Z",
    "authoredBy" : [ {
      "uri" : "mailto:peter.amstutz@curoverse.com",
      "name" : "Peter Amstutz"
    } ],
    "retrievedFrom" : "https://raw.githubusercontent.com/common-workflow-language/workflows/lobstr-v1/workflows/lobSTR/lobSTR-demo.json",
    "retrievedBy" : {
      "uri" : "https://view.commonwl.org",
      "name" : "Common Workflow Language Viewer"
    },
    "bundledAs" : {
      "uri" : "urn:uuid:973caa0e-f3bd-45e8-8d29-70123bc8715a",
      "folder" : "/workflow/"
    }
  }, {
    "uri" : "/workflow/models/illumina_v3.pcrfree.stuttermodel",
    "mediatype" : "application/octet-stream",
    "createdOn" : "2017-08-24T10:57:47.239Z",
    "authoredBy" : [ {
      "uri" : "mailto:peter.amstutz@curoverse.com",
      "name" : "Peter Amstutz"
    } ],
    "retrievedFrom" : "https://raw.githubusercontent.com/common-workflow-language/workflows/lobstr-v1/workflows/lobSTR/models/illumina_v3.pcrfree.stuttermodel",
    "retrievedBy" : {
      "uri" : "https://view.commonwl.org",
      "name" : "Common Workflow Language Viewer"
    },
    "bundledAs" : {
      "uri" : "urn:uuid:62bbcbea-f34f-463f-990d-6148f8ed5e5c",
      "folder" : "/workflow/models/"
    }
  }, {
    "uri" : "/workflow/models/illumina_v3.pcrfree.stepmodel",
    "mediatype" : "application/octet-stream",
    "createdOn" : "2017-08-24T10:57:47.266Z",
    "authoredBy" : [ {
      "uri" : "mailto:peter.amstutz@curoverse.com",
      "name" : "Peter Amstutz"
    } ],
    "retrievedFrom" : "https://raw.githubusercontent.com/common-workflow-language/workflows/lobstr-v1/workflows/lobSTR/models/illumina_v3.pcrfree.stepmodel",
    "retrievedBy" : {
      "uri" : "https://view.commonwl.org",
      "name" : "Common Workflow Language Viewer"
    },
    "bundledAs" : {
      "uri" : "urn:uuid:03439ae7-cd94-42a3-b5fe-40bfff6882d8",
      "folder" : "/workflow/models/"
    }
  }, {
    "uri" : "/workflow/samtools-sort.cwl",
    "mediatype" : "text/x-yaml",
    "createdOn" : "2017-08-24T10:57:47.269Z",
    "authoredBy" : [ {
      "uri" : "mailto:luka.stojanovic@sbgenomics.com",
      "name" : "Luka Stojanovic"
    }, {
      "uri" : "mailto:crusoe@ucdavis.edu",
      "name" : "Michael R. Crusoe"
    }, {
      "uri" : "mailto:porter@porter.st",
      "name" : "Andrey Kartashov"
    }, {
      "uri" : "mailto:peter.amstutz@curoverse.com",
      "name" : "Peter Amstutz"
    } ],
    "retrievedFrom" : "https://raw.githubusercontent.com/common-workflow-language/workflows/lobstr-v1/workflows/lobSTR/samtools-sort.cwl",
    "retrievedBy" : {
      "uri" : "https://view.commonwl.org",
      "name" : "Common Workflow Language Viewer"
    },
    "conformsTo" : "https://w3id.org/cwl/v1.0",
    "bundledAs" : {
      "uri" : "urn:uuid:2dc07859-efc2-4945-a95f-ba7815b68d07",
      "folder" : "/workflow/"
    }
  }, {
    "uri" : "/workflow/lobSTR-workflow.cwl",
    "mediatype" : "text/x-yaml",
    "createdOn" : "2017-08-24T10:57:47.42Z",
    "authoredBy" : [ {
      "uri" : "mailto:luka.stojanovic@sbgenomics.com",
      "name" : "Luka Stojanovic"
    }, {
      "uri" : "mailto:crusoe@ucdavis.edu",
      "name" : "Michael R. Crusoe"
    }, {
      "uri" : "mailto:peter.amstutz@curoverse.com",
      "name" : "Peter Amstutz"
    } ],
    "retrievedFrom" : "https://raw.githubusercontent.com/common-workflow-language/workflows/lobstr-v1/workflows/lobSTR/lobSTR-workflow.cwl",
    "retrievedBy" : {
      "uri" : "https://view.commonwl.org",
      "name" : "Common Workflow Language Viewer"
    },
    "conformsTo" : "https://w3id.org/cwl/v1.0",
    "bundledAs" : {
      "uri" : "urn:uuid:58bc1895-3460-46d6-91d7-fa1718d09631",
      "folder" : "/workflow/"
    }
  }, {
    "uri" : "/workflow/lobSTR-arvados-demo.json",
    "mediatype" : "application/json",
    "createdOn" : "2017-08-24T10:57:47.453Z",
    "authoredBy" : [ {
      "uri" : "mailto:peter.amstutz@curoverse.com",
      "name" : "Peter Amstutz"
    } ],
    "retrievedFrom" : "https://raw.githubusercontent.com/common-workflow-language/workflows/lobstr-v1/workflows/lobSTR/lobSTR-arvados-demo.json",
    "retrievedBy" : {
      "uri" : "https://view.commonwl.org",
      "name" : "Common Workflow Language Viewer"
    },
    "bundledAs" : {
      "uri" : "urn:uuid:30c683bc-69fb-4d93-8dad-65b663783af5",
      "folder" : "/workflow/"
    }
  }, {
    "uri" : "/workflow/samtools-index.cwl",
    "mediatype" : "text/x-yaml",
    "createdOn" : "2017-08-24T10:57:47.458Z",
    "authoredBy" : [ {
      "uri" : "mailto:luka.stojanovic@sbgenomics.com",
      "name" : "Luka Stojanovic"
    }, {
      "uri" : "mailto:crusoe@ucdavis.edu",
      "name" : "Michael R. Crusoe"
    }, {
      "uri" : "mailto:porter@porter.st",
      "name" : "Andrey Kartashov"
    }, {
      "uri" : "mailto:peter.amstutz@curoverse.com",
      "name" : "Peter Amstutz"
    } ],
    "retrievedFrom" : "https://raw.githubusercontent.com/common-workflow-language/workflows/lobstr-v1/workflows/lobSTR/samtools-index.cwl",
    "retrievedBy" : {
      "uri" : "https://view.commonwl.org",
      "name" : "Common Workflow Language Viewer"
    },
    "conformsTo" : "https://w3id.org/cwl/v1.0",
    "bundledAs" : {
      "uri" : "urn:uuid:8235d3f8-6927-4f73-b160-8521838a1cbb",
      "folder" : "/workflow/"
    }
  }, {
    "uri" : "/workflow/lobSTR-tool.cwl",
    "mediatype" : "text/x-yaml",
    "createdOn" : "2017-08-24T10:57:47.476Z",
    "authoredBy" : [ {
      "uri" : "mailto:luka.stojanovic@sbgenomics.com",
      "name" : "Luka Stojanovic"
    }, {
      "uri" : "mailto:crusoe@ucdavis.edu",
      "name" : "Michael R. Crusoe"
    }, {
      "uri" : "mailto:peter.amstutz@curoverse.com",
      "name" : "Peter Amstutz"
    } ],
    "retrievedFrom" : "https://raw.githubusercontent.com/common-workflow-language/workflows/lobstr-v1/workflows/lobSTR/lobSTR-tool.cwl",
    "retrievedBy" : {
      "uri" : "https://view.commonwl.org",
      "name" : "Common Workflow Language Viewer"
    },
    "conformsTo" : "https://w3id.org/cwl/v1.0",
    "bundledAs" : {
      "uri" : "urn:uuid:7fa6fbe4-1fc5-4cb5-9c1a-56b96c5f7aaf",
      "folder" : "/workflow/"
    }
  }, {
    "uri" : "/workflow/allelotype.cwl",
    "mediatype" : "text/x-yaml",
    "createdOn" : "2017-08-24T10:57:47.537Z",
    "authoredBy" : [ {
      "uri" : "mailto:luka.stojanovic@sbgenomics.com",
      "name" : "Luka Stojanovic"
    }, {
      "uri" : "mailto:janko.simonovic@sbgenomics.com",
      "name" : "Janko Simonovic"
    }, {
      "uri" : "mailto:crusoe@ucdavis.edu",
      "name" : "Michael R. Crusoe"
    }, {
      "uri" : "mailto:peter.amstutz@curoverse.com",
      "name" : "Peter Amstutz"
    } ],
    "retrievedFrom" : "https://raw.githubusercontent.com/common-workflow-language/workflows/lobstr-v1/workflows/lobSTR/allelotype.cwl",
    "retrievedBy" : {
      "uri" : "https://view.commonwl.org",
      "name" : "Common Workflow Language Viewer"
    },
    "conformsTo" : "https://w3id.org/cwl/v1.0",
    "bundledAs" : {
      "uri" : "urn:uuid:3706bd2f-e53f-431d-b32a-deb661d9b292",
      "folder" : "/workflow/"
    }
  }, {
    "uri" : "/workflow/README",
    "mediatype" : "application/octet-stream",
    "createdOn" : "2017-08-24T10:57:47.555Z",
    "authoredBy" : [ {
      "uri" : "mailto:crusoe@ucdavis.edu",
      "name" : "Michael R. Crusoe"
    }, {
      "uri" : "mailto:peter.amstutz@curoverse.com",
      "name" : "Peter Amstutz"
    } ],
    "retrievedFrom" : "https://raw.githubusercontent.com/common-workflow-language/workflows/lobstr-v1/workflows/lobSTR/README",
    "retrievedBy" : {
      "uri" : "https://view.commonwl.org",
      "name" : "Common Workflow Language Viewer"
    },
    "bundledAs" : {
      "uri" : "urn:uuid:ed54c4d6-c585-4dc9-b7bc-0cf299e20b91",
      "folder" : "/workflow/"
    }
  }, {
    "uri" : "/workflow/tmp_1.fq",
    "mediatype" : "application/octet-stream",
    "createdOn" : "2017-08-24T10:57:47.738Z",
    "authoredBy" : [ {
      "uri" : "mailto:peter.amstutz@curoverse.com",
      "name" : "Peter Amstutz"
    } ],
    "retrievedFrom" : "https://raw.githubusercontent.com/common-workflow-language/workflows/lobstr-v1/workflows/lobSTR/tmp_1.fq",
    "retrievedBy" : {
      "uri" : "https://view.commonwl.org",
      "name" : "Common Workflow Language Viewer"
    },
    "bundledAs" : {
      "uri" : "urn:uuid:5d431f81-ad0b-4acf-903a-9d5aa03b04df",
      "folder" : "/workflow/"
    }
  }, {
    "uri" : "/visualisation.png",
    "mediatype" : "image/png",
    "createdOn" : "2017-08-24T10:57:47.801Z",
    "retrievedFrom" : "https://view.commonwl.org/graph/png/github.com/common-workflow-language/workflows/blob/lobstr-v1/workflows/lobSTR/lobSTR-workflow.cwl",
    "bundledAs" : {
      "uri" : "urn:uuid:ff9ace37-e76c-49f8-8d36-60f11ff6d257",
      "folder" : "/"
    }
  }, {
    "uri" : "/visualisation.svg",
    "mediatype" : "image/svg+xml",
    "createdOn" : "2017-08-24T10:57:47.821Z",
    "retrievedFrom" : "https://view.commonwl.org/graph/svg/github.com/common-workflow-language/workflows/blob/lobstr-v1/workflows/lobSTR/lobSTR-workflow.cwl",
    "bundledAs" : {
      "uri" : "urn:uuid:a6cfb437-8818-4ab2-9081-efc74c5109e8",
      "folder" : "/"
    }
  } ],
  "annotations" : [ {
    "uri" : "urn:uuid:9f602fff-b280-41c5-9590-ab95a49c85ad",
    "about" : "/",
    "content" : "annotations/merged.cwl"
  }, {
    "uri" : "urn:uuid:0ce4b727-ff61-4534-9afb-e3d676d2782d",
    "about" : "/",
    "content" : "annotations/workflow.ttl"
  } ]
}
#!/usr/bin/env cwl-runner
cwlVersion: v1.0
class: Workflow

label: "Hello World"
doc: "Outputs a message using echo"

inputs: []

outputs:
  response:
    outputSource: step0/response
    type: File

steps:
  step0:
    run:
      class: CommandLineTool
      inputs:
        message:
          type: string
          doc: "The message to print"
          default: "Hello World"
          inputBinding:
            position: 1
      baseCommand: echo
      stdout: response.txt
      outputs:
        response:
          type: stdout
    in: []
    out: [response]

https://doi.org/10.7490/f1000research.1114781.1

Farah Z Khan
BOSC hackathon 2017

Prototype PROV+RO export
CWL reference implementation

 

Copyright © 2013 W3C® (MIT, ERCIM, Keio, Beihang), All Rights Reserved. W3C liability, trademark and document use rules apply.

PROV Model Primer

W3C Working Group Note 30 April 2013

Which PROV format?

<prov:wasGeneratedBy>
  <prov:entity prov:ref="ex:ent1"/>
  <prov:activity prov:ref="ex:act1"/>
  <prov:time>2017-10-26T21:32:52Z</prov:time>
  <ex:port>p1</ex:port>
</prov:wasGeneratedBy>
wasGeneratedBy(ent1, act1, 
  2017-10-26T21:32:52Z, ex:port="p1")
:ent1
  a prov:Entity;
  prov:wasGeneratedBy :act1;
  prov:generatedAtTime "2017-10-26T21:32:52Z"^^xsd:dateTime ;
  ex:port "p1" .
    "wasGeneratedBy": {
        "ex:gen1": {
            "prov:entity": "ent1",
            "prov:activity": "act1",
            "prov:time": "2017-10-26T21:32:52Z",
            "ex:port": "p1"
        },
    },
{ "@context": { .. }, 
  "@id": "ent1",
  "@type": "prov:Entity",
  "ex:port": "p1",
  "prov:generatedAtTime":  "2017-10-26T21:32:52Z",
  "prov:wasGeneratedBy": {
    "@id": "act1",
    "@type": "prov:Activity"
  } 
}

PROV-N

PROV-XML

PROV-JSON

PROV-O Turtle

PROV-O JSON-LD

Nested workflows

A single activity unrolled to multiple steps

 

 

activity(run:2e1287e0-6dfb-11e7-8acf-0242ac110002, , , 
   [prov:type='wfprov:WorkflowRun', prov:label="Run of workflow/packed.cwl#main"])    
    // main workflow run started outside somehow (we're don't know how)
    wasStartedBy(run:4305467e-6dfb-11e7-885d-0242ac110002, -, -, 
                 -, 2017-10-27T15:00:00Z)
    // ...
    // step is a nested workflow, so also a WorkflowRun
    activity(run:4305467e-6dfb-11e7-885d-0242ac110002, -, -, 
      [prov:type='wfprov:WorkflowRun', prov:label="Run of workflow/packed.cwl#main/nested1"])
        // started by the mother activity
        wasStartedBy(run:4305467e-6dfb-11e7-885d-0242ac110002, -, -, 
                     run:2e1287e0-6dfb-11e7-8acf-0242ac110002, 2017-10-27T15:00:30Z)
    
        // inner step of nested workflow, ProcessRun as this is a command line execution
        activity(run:c42dc36e-6dfd-11e7-bc24-0242ac110002, -, - 
          [prov:type='wfprov:ProcessRun', prov:label="Run of workflow/packed.cwl#nested/innerStep1"])
            
        wasStartedBy(run:c42dc36e-6dfd-11e7-bc24-0242ac110002, -, -, 
                     run:4305467e-6dfb-11e7-885d-0242ac110002, 2017-10-27T15:01:00Z)
        // ...

Identifying intermediate data

Output 1B file is also Input 2C and Input 3D downstream

Simple filenames -> duplications

  ./data/step1/outputB.txt 
./data/step2/inputC.txt
./data/step3/inputD.txt

 

Content-adressable

SHA-256 hash of bytes as filename:

./data/51/51fb8af0c4ae0422fbe88340d91880ecb9d7537cf57339c1cf1256b7ca58f32d

RFC6920 URI as global identifier:

nih:sha-256;51fb8af0c4ae0422fbe88340d91880ecb9d7537cf57339c1cf1256b7ca58f32d

prov:alternateOf

Relating global identifier to local paths

used(run:2e1287e0-6dfb-11e7-8acf-0242ac110002, 
     data:5891b5b522d5df086d0ff0b110fbd9d21bb4fc7163af34d08286a2e846f6be03, 
     2017-10-27T14:29:00+01:00, [prov:role='wf:main/input1']))

entity(data:5891b5b522d5df086d0ff0b110fbd9d21bb4fc7163af34d08286a2e846f6be03)

   // which we have stored a copy of within the research object
   specializationOf(./data/58/5891b5b522d5df086d0ff0b110fbd9d21bb4fc7163af34d08286a2e846f6be03,
                    data:5891b5b522d5df086d0ff0b110fbd9d21bb4fc7163af34d08286a2e846f6be03)

Large data would not have a ./data/ file,

but might be referenced externally

Workflow provenance profiles

How to tie it all together?

id:        doi:10.15490/seek.1.investigation.56
createdOn: 2015-07-10T16:46:00Z
createdBy: http://orcid.org/0000-0001-9842-9718

aggregates:
 - id:         data/sequence/specimen5.bam
   conformsTo: http://gemrb.org/iesdp/file_formats/ie_formats/bam_v1.htm

 - id:         http://example.com/blog/about-specimen5
   authoredBy: http://orcid.org/0000-0001-7066-3350

 - id:         http://www.myexperiment.org/workflows/3355
   history:    provenance/workflow-evolution.ttl

annotations:
 - about:       data/sequence/specimen5.bam
   content:     annotations/specimen5-properties.jsonld
   createdBy:   http://orcid.org/0000-0001-7066-3350

 - about:       data/sequence/specimen5.bam
   content:     http://example.com/blog/about-specimen5
   motivatedBy: oa:questioning

Research Object manifest

(simplified)

Reuse standards:
OAI-ORE, BagIt, W3C JSON-LD, PROV, Web Annotation Model

metadata/manifest.json
data/sequence/specimen5.bam
provenance/workflow-evolution.ttl
http://example.com/blog/about-specimen5
http://www.myexperiment.org/workflows/335

http://orcid.org/0000-0001-7066-3350
http://gemrb.org/iesdb/
   file_formats_ie_formats_bam_v1.html

Who is using Research Objects?

Structure of CWL run Research Object:

 

  • data: content-adressable by sha256 hash
  • workflow: input object (json file) with relativised paths, packed.cwl
    executable workflow containing the workflow specification and tool specifications with relativised paths to re-run inside an RO.
  • snapshot: This directory contains copies of the original workflow and tool specifications files as-is (warning: might contain absolute paths or be host-specific).
  • metadata: provenance about the workflow run, its data products and manifest for this Research Object.

 

document
prefix wfprov <http://purl.org/wf4ever/wfprov#>
prefix prov <http://www.w3.org/ns/prov#>
prefix wfdesc <http://purl.org/wf4ever/wfdesc#>
prefix wf <https://w3id.org/cwl/view/git/933bf2a1a1cce32d88f88f136275535da9df0954/workflows/hello/hello.cwl#>
prefix input <app://579c1b74-b328-4da6-80a8-a2ffef2ac9b5/workflow/input.json#>
prefix run <urn:uuid:>
prefix engine <urn:uuid:>
prefix data <nih:sha-256;>

default <app://579c1b74-b328-4da6-80a8-a2ffef2ac9b5/>

// Level 1 provenance of workflow run

activity(run:2e1287e0-6dfb-11e7-8acf-0242ac110002, , , [prov:type='wfprov:WorkflowRun', prov:label="Run of workflow/packed.cwl#main"])    
    wasStartedBy(run:2e1287e0-6dfb-11e7-8acf-0242ac110002, -, -, -, 2017-10-27T14:24:00+01:00)  

    // The engine is the SoftwareAgent that is executing our Workflow plan
    wasAssociatedWith(run:2e1287e0-6dfb-11e7-8acf-0242ac110002, engine:b2210211-8acb-4d58-bd28-2a36b18d3b4f, wf:main)
        agent(engine:b2210211-8acb-4d58-bd28-2a36b18d3b4f, prov:type='prov:SoftwareAgent', prov:type='wfprov:WorkflowEngine', prov:label="cwltool v1.2.5")
        // prov has no term to relate sub-plans - we'll use wfdesc:hasSubProcess
        entity(wf:main,[prov:type='wfdesc:Workflow', prov:type='prov:Plan', wfdesc:hasSubProcess='wf:main/step1', wfdesc:hasSubProcess='wf:main/step2'])
            alternateOf(wf:main, workflow/packed.cwl)
            entity(wf:main/step1,[prov:type='wfdesc:Process', prov:type='prov:Plan'])
            entity(wf:main/step2,[prov:type='wfdesc:Process', prov:type='prov:Plan'])            

    // First the workflow uses some data; here with a sha256 identifier
    used(run:2e1287e0-6dfb-11e7-8acf-0242ac110002, data:5891b5b522d5df086d0ff0b110fbd9d21bb4fc7163af34d08286a2e846f6be03, 2017-10-27T14:29:00+01:00, [prov:role='wf:main/input1']))
        entity(data:5891b5b522d5df086d0ff0b110fbd9d21bb4fc7163af34d08286a2e846f6be03, [prov:type='wfprov:Artifact'])
            // which we have stored a copy of within the research object
            specializationOf(data/58/5891b5b522d5df086d0ff0b110fbd9d21bb4fc7163af34d08286a2e846f6be03, data:5891b5b522d5df086d0ff0b110fbd9d21bb4fc7163af34d08286a2e846f6be03)

    // Then there was another activity - wfprov:ProcessRun indicating a command line tool
    activity(run:4305467e-6dfb-11e7-885d-0242ac110002, -, -, [prov:type='wfprov:ProcessRun', prov:label="Run of workflow/packed.cwl#main/step1"])
        // started by the mother activity
        wasStartedBy(run:4305467e-6dfb-11e7-885d-0242ac110002, -, -, run:2e1287e0-6dfb-11e7-8acf-0242ac110002, 2017-10-27T15:00:00+01:00)
        // same engine using step1 as plan. In a distributed scenario there might be a different engine
        wasAssociatedWith(run:4305467e-6dfb-11e7-885d-0242ac110002, engine:b2210211-8acb-4d58-bd28-2a36b18d3b4f, wf:main/step1)
        // This activity also use the same data, but in a different role (e.g. input parameter)
        used(run:4305467e-6dfb-11e7-885d-0242ac110002, data:5891b5b522d5df086d0ff0b110fbd9d21bb4fc7163af34d08286a2e846f6be03, 2017-10-27T14:00:00+01:00, [prov:role='wf:main/step1/in1'])

        // And we generate some new data
        wasGeneratedBy(data:00688350913f2f292943a274b57019d58889eda272370af261c84e78e204743c, run:4305467e-6dfb-11e7-885d-0242ac110002, 2017-10-27T16:00:00+01:00, [prov:role='wf:main/step1/out1']))
            entity(data:00688350913f2f292943a274b57019d58889eda272370af261c84e78e204743c, [prov:type='wfprov:Artifact'])
                // again stored in the RO
                specializationOf(data/00/00688350913f2f292943a274b57019d58889eda272370af261c84e78e204743c, data:00688350913f2f292943a274b57019d58889eda272370af261c84e78e204743c)

        // step1 finished
        wasEndedBy(run:4305467e-6dfb-11e7-885d-0242ac110002, -, -, run:2e1287e0-6dfb-11e7-8acf-0242ac110002, 2017-10-27T15:30:00+01:00)

    // the master workflow then "generate" that same value, but now at a different time and role (the resultA master workflow output)
    wasGeneratedBy(data:00688350913f2f292943a274b57019d58889eda272370af261c84e78e204743c, run:2e1287e0-6dfb-11e7-8acf-0242ac110002, 2017-10-27T15:00:00+01:00, [prov:role='wf:main/resultA'])

    // next step activity
    activity(run:c42dc36e-6dfd-11e7-bc24-0242ac110002, -, - [prov:type='wfprov:ProcessRun', prov:label="Run of workflow/packed.cwl#main/step2"])
        wasStartedBy(run:c42dc36e-6dfd-11e7-bc24-0242ac110002, -, -, run:2e1287e0-6dfb-11e7-8acf-0242ac110002, 2017-10-27T16:00:00+01:00)
        // associated with step2
        wasAssociatedWith(run:c42dc36e-6dfd-11e7-bc24-0242ac110002, engine:b2210211-8acb-4d58-bd28-2a36b18d3b4f, wf:main/step2)
        
        // Uses two data artifacts; one which came from previous step, other as workflow input
        used(run:4305467e-6dfb-11e7-885d-0242ac110002, data:5891b5b522d5df086d0ff0b110fbd9d21bb4fc7163af34d08286a2e846f6be03, 2017-10-27T15:00:00+01:00, [prov:role='wf:main/step2/valueA'])
        used(run:4305467e-6dfb-11e7-885d-0242ac110002, data:00688350913f2f292943a274b57019d58889eda272370af261c84e78e204743c, 2017-10-27T15:00:00+01:00, [prov:role='wf:main/step2/valueB'])
        
        // and generate two new data artifacts
        wasGeneratedBy(data:952f537d1f3116db56703787ace248fe00ae46fa77ea3803aa3d8dc01d221a9d, run:c42dc36e-6dfd-11e7-bc24-0242ac110002,  2017-10-27T16:34:20+01:00, [prov:role='wf:main/step2/out1'])))
            entity(data:952f537d1f3116db56703787ace248fe00ae46fa77ea3803aa3d8dc01d221a9d, [prov:type='wfprov:Artifact'])
                specializationOf(data/95/2f537d1f3116db56703787ace248fe00ae46fa77ea3803aa3d8dc01d221a9d, data:952f537d1f3116db56703787ace248fe00ae46fa77ea3803aa3d8dc01d221a9d)

        wasGeneratedBy(data:3deb00bd0decd1f21d015a178c4f23a5eb537588c08eeee9d55059ec29637be0, run:c42dc36e-6dfd-11e7-bc24-0242ac110002,  2017-10-27T16:34:20+01:00, [prov:role='wf:main/step2/out2'])))
            entity(data:3deb00bd0decd1f21d015a178c4f23a5eb537588c08eeee9d55059ec29637be0, [prov:type='wfprov:Artifact'])
                specializationOf(data/3d/eb00bd0decd1f21d015a178c4f23a5eb537588c08eeee9d55059ec29637be0, data:3deb00bd0decd1f21d015a178c4f23a5eb537588c08eeee9d55059ec29637be0)
        // step2 ends
        wasEndedBy(run:c42dc36e-6dfd-11e7-bc24-0242ac110002, -, -, run:2e1287e0-6dfb-11e7-8acf-0242ac110002, 2017-10-27T16:30:00+01:00)

    // only step output out1 captured by mother workflow, sent to resultB workflow output
    wasGeneratedBy(data:952f537d1f3116db56703787ace248fe00ae46fa77ea3803aa3d8dc01d221a9d, run:2e1287e0-6dfb-11e7-8acf-0242ac110002, 2017-10-27T15:00:00+01:00, [prov:role='wf:main/resultB'])

    // mother workflow ends
    wasEndedBy(run:2e1287e0-6dfb-11e7-8acf-0242ac110002, -, -, run:2e1287e0-6dfb-11e7-8acf-0242ac110002, 2017-10-27T16:34:40+01:00)

endDocument

New for this implementation study?

Portal-level provenance

Which portal?

Who submitted the job?

Where did the data come from?

Which samples?

Job-level provenance

(Workflow) job submission

Nested jobs?

 

Cluster/grid/cloud execution

 

Workflow references

Indirect data references

 

Performance statistics

Usage Records

"Previous runs" annotations

Estimates for memory/cores/disk/time

 

Correlate with dataset stats

 

Links to research objects / provenance

 

Multiple estimation annotations or dynamically modify Requirements?

Enriches visualization

Extend CWL viewer to show Requirements

 

Show previous runs annotations

 

Expose deep annotations (e.g. EDAM typing)

 

Links to previous runs Research Objects

(discovered by Linked Data Notifications?)

 

Visualize run RO?

References to large data?

How to describe
Resource Usage?

<?xml version="1.0" encoding="UTF-8"?>
<ur:UsageRecord xmlns="http://schema.ogf.org/urf/2013/04/urf"
	xmlns:ur="http://schema.ogf.org/urf/2013/04/urf" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xsi:schemaLocation="http://schema.ogf.org/urf/2013/04/urf">
	<ur:RecordIdentityBlock>
		<ur:RecordId>urn:uuid:4350d583-61a5-45e8-a229-957aa81e8014</ur:RecordId>
		<ur:CreateTime>2018-05-09T09:06:52Z</ur:CreateTime>
		<ur:Site>EMBL-EBI</ur:Site>
		<ur:Infrastructure>Embassy</ur:Infrastructure>
	</ur:RecordIdentityBlock>
	<ur:SubjectIdentityBlock>
		<ur:LocalUserId>stain</ur:LocalUserId>
		<ur:LocalGroupId>ELIXIRCWLImplStudy</ur:LocalGroupId>
		<ur:GlobalUserId>https://orcid.org/0000-0001-9842-9718</ur:GlobalUserId>
	</ur:SubjectIdentityBlock>
	<ur:ComputeUsageBlock>
		<ur:CpuDuration>PT3600S</ur:CpuDuration>
		<ur:WallDuration>PT3600S</ur:WallDuration>
		<ur:StartTime>2018-05-31T11:00:00</ur:StartTime>
		<ur:EndTime>2018-05-31T12:00:00</ur:EndTime>
		<ur:ExecutionHost>
			<ur:Hostname>compute-0-1.example.com</ur:Hostname>
			<ur:ProcessId>1042</ur:ProcessId>
			<ur:Benchmark ur:type="si2k">3.14</ur:Benchmark>
		</ur:ExecutionHost>
		<ur:Processors>4</ur:Processors>
		<ur:NodeCount>1</ur:NodeCount>
	</ur:ComputeUsageBlock>
	<ur:JobUsageBlock>
		<ur:GlobalJobId>host.example.org/ab1234</ur:GlobalJobId>
		<ur:LocalJobId>ab1234</ur:LocalJobId>
		<ur:JobName>MetaGenomics1337</ur:JobName>
		<ur:Queue ur:description="execution">"Bigmem"</ur:Queue>
		<ur:TimeInstant ur:type="Ctime">2018-05-31T10:30:00</ur:TimeInstant>
		<ur:TimeInstant ur:type="Qtime">2018-05-31T10:31:00</ur:TimeInstant>
		<ur:TimeInstant ur:type="Etime">2018-05-31T10:59:42</ur:TimeInstant>
	</ur:JobUsageBlock>
	<ur:MemoryUsageBlock>
		<ur:MemoryClass>"RAM"</ur:MemoryClass>
		<ur:MemoryResourceCapacityUsed>14728</ur:MemoryResourceCapacityUsed>
		<ur:MemoryResourceCapacityAllocated>56437</ur:MemoryResourceCapacityAllocated>
		<ur:MemoryResourceCapacityRequested>42000</ur:MemoryResourceCapacityRequested>
		<ur:StartTime>2018-05-31T11:00:00</ur:StartTime>
		<ur:EndTime>2018-05-31T12:00:00</ur:EndTime>
	</ur:MemoryUsageBlock>
	<ur:StorageUsageBlock>
		<ur:StorageShare>pool-003</ur:StorageShare>
		<ur:StorageMedia>disk</ur:StorageMedia>
		<ur:StorageClass>replicated</ur:StorageClass>
		<ur:DirectoryPath>/projectA</ur:DirectoryPath>
		<ur:FileCount>42</ur:FileCount>
		<ur:StorageResourceCapacityUsed>14728</ur:StorageResourceCapacityUsed>
		<ur:StorageLogicalCapacityUsed>13617</ur:StorageLogicalCapacityUsed>
		<ur:StorageResourceCapacityAllocated>14624
		</ur:StorageResourceCapacityAllocated>
		<ur:StartTime>2018-05-07T09:31:40Z</ur:StartTime>
		<ur:EndTime>2018-05-08T09:29:42Z</ur:EndTime>
		<ur:Host>host.example.org</ur:Host>
	</ur:StorageUsageBlock>
	<ur:CloudUsageBlock>
		<ur:LocalVirtualMachineId>ab1234</ur:LocalVirtualMachineId>
		<ur:GlobalVirtualMachineId>
			host.example.org/ab1234/2018-05-09T09:06:52Z
		</ur:GlobalVirtualMachineId>
		<ur:Status>started</ur:Status>
		<ur:SuspendDuration>PT3600S</ur:SuspendDuration>
		<ur:ImageId>UbuntuImage2013</ur:ImageId>
		<ur:MachineName>cloud.example.org</ur:MachineName>
		<ur:SubmitHost>
			cloud-name=cloud.example.org,Mds-Vo-name=local,o=cloud
		</ur:SubmitHost>
		<ur:TimeInstant ur:type="Ctime">2018-05-31T10:30:00</ur:TimeInstant>
		<ur:TimeInstant ur:type="Qtime">2018-05-31T10:31:00</ur:TimeInstant>
		<ur:TimeInstant ur:type="Etime">2018-05-31T10:59:42</ur:TimeInstant>
		<ur:ServiceLevel>Premium</ur:ServiceLevel>
	</ur:CloudUsageBlock>
	<ur:NetworkUsageBlock>
		<ur:NetworkClass ur:NetworkResourceBandwidth="100000000">"Ethernet"</ur:NetworkClass>
		<ur:NetworkInboundUsed ur:SourceAddress=192.168.1.12>14728</ur:NetworkInboundUsed>
		<ur:NetworkOutboundUsed ur:DestinationAddress=192.168.1.21>14728</ur:NetworkOutboundUsed>
	</ur:NetworkUsageBlock>
</ur:UsageRecord>

2018-01-26 Research Objects and CWL

By Stian Soiland-Reyes

2018-01-26 Research Objects and CWL

Presented at ELIXIR CWL Implementation Study meeting, Hinxton 2018-01-16

  • 3,367