Skip to content
Snippets Groups Projects
Commit bc4095f4 authored by Dominik Brilhaus's avatar Dominik Brilhaus
Browse files

Merge branch 'arc-cwl' into 'main'

Arc cwl

See merge request !19
parents 0bf412a4 73782263
No related branches found
No related tags found
1 merge request!19Arc cwl
Pipeline #9529 passed
Showing
with 623 additions and 72 deletions
......@@ -77,5 +77,5 @@ cwltool --parallel run.cwl run.yml > $(date +"%Y-%m-%d_%H-%M")-run.log 2>&1 &
### Print workflow to file
```bash
cwltool --print-dot run.cwl | dot -Tsvg > run.svg
cwltool --print-dot ../arc.cwl | dot -Tsvg > arc-cwl.svg
```
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
<!-- Generated by graphviz version 9.0.0 (0)
-->
<!-- Title: G Pages: 1 -->
<svg width="2781pt" height="325pt"
viewBox="0.00 0.00 2781.00 325.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 321)">
<title>G</title>
<polygon fill="#eeeeee" stroke="none" points="-4,4 -4,-321 2777,-321 2777,4 -4,4"/>
<g id="clust1" class="cluster">
<title>cluster_inputs</title>
<polygon fill="#eeeeee" stroke="black" stroke-dasharray="5,2" points="8,-231.5 8,-309 2765,-309 2765,-231.5 8,-231.5"/>
<text text-anchor="middle" x="2710.5" y="-238.7" font-family="Times,serif" font-size="14.00">Workflow Inputs</text>
</g>
<g id="clust2" class="cluster">
<title>cluster_outputs</title>
<polygon fill="#eeeeee" stroke="black" stroke-dasharray="5,2" points="2217,-8 2217,-85.5 2335,-85.5 2335,-8 2217,-8"/>
<text text-anchor="middle" x="2276" y="-15.2" font-family="Times,serif" font-size="14.00">Workflow Outputs</text>
</g>
<!-- isaSampleToRawDataSeq -->
<g id="node1" class="node">
<title>isaSampleToRawDataSeq</title>
<polygon fill="#f3cea1" stroke="black" points="563.12,-187 563.12,-223 720.88,-223 720.88,-187 563.12,-187"/>
<text text-anchor="middle" x="642" y="-199.95" font-family="Times,serif" font-size="14.00">isaSampleToRawDataSeq</text>
</g>
<!-- sleuth -->
<g id="node2" class="node">
<title>sleuth</title>
<polygon fill="#f3cea1" stroke="black" points="2249,-114 2249,-150 2303,-150 2303,-114 2249,-114"/>
<text text-anchor="middle" x="2275.62" y="-126.95" font-family="Times,serif" font-size="14.00">sleuth</text>
</g>
<!-- isaSampleToRawDataSeq&#45;&gt;sleuth -->
<g id="edge1" class="edge">
<title>isaSampleToRawDataSeq&#45;&gt;sleuth</title>
<path fill="none" stroke="black" d="M721.36,-200.55C1013.99,-187.84 2026.5,-143.84 2237.35,-134.68"/>
<polygon fill="black" stroke="black" points="2237.36,-138.18 2247.2,-134.25 2237.05,-131.19 2237.36,-138.18"/>
</g>
<!-- outdir -->
<g id="node19" class="node">
<title>outdir</title>
<polygon fill="#94ddf4" stroke="black" points="2249,-41 2249,-77 2303,-77 2303,-41 2249,-41"/>
<text text-anchor="middle" x="2275.62" y="-53.95" font-family="Times,serif" font-size="14.00">outdir</text>
</g>
<!-- sleuth&#45;&gt;outdir -->
<g id="edge18" class="edge">
<title>sleuth&#45;&gt;outdir</title>
<path fill="none" stroke="black" d="M2276,-113.81C2276,-106.23 2276,-97.1 2276,-88.54"/>
<polygon fill="black" stroke="black" points="2279.5,-88.54 2276,-78.54 2272.5,-88.54 2279.5,-88.54"/>
</g>
<!-- kallisto -->
<g id="node3" class="node">
<title>kallisto</title>
<polygon fill="#f3cea1" stroke="black" points="1606.12,-187 1606.12,-223 1661.88,-223 1661.88,-187 1606.12,-187"/>
<text text-anchor="middle" x="1634" y="-199.95" font-family="Times,serif" font-size="14.00">kallisto</text>
</g>
<!-- kallisto&#45;&gt;sleuth -->
<g id="edge2" class="edge">
<title>kallisto&#45;&gt;sleuth</title>
<path fill="none" stroke="black" d="M1662,-200.9C1764.43,-189.58 2118.96,-150.37 2237.24,-137.29"/>
<polygon fill="black" stroke="black" points="2237.52,-140.78 2247.07,-136.2 2236.75,-133.82 2237.52,-140.78"/>
</g>
<!-- isaSampleToRawDataSeq_arcPath -->
<g id="node4" class="node">
<title>isaSampleToRawDataSeq_arcPath</title>
<polygon fill="#94ddf4" stroke="black" points="773.5,-264.5 773.5,-300.5 978.5,-300.5 978.5,-264.5 773.5,-264.5"/>
<text text-anchor="middle" x="876" y="-277.45" font-family="Times,serif" font-size="14.00">isaSampleToRawDataSeq_arcPath</text>
</g>
<!-- isaSampleToRawDataSeq_arcPath&#45;&gt;isaSampleToRawDataSeq -->
<g id="edge3" class="edge">
<title>isaSampleToRawDataSeq_arcPath&#45;&gt;isaSampleToRawDataSeq</title>
<path fill="none" stroke="black" d="M841.94,-264C820.12,-253.37 790.95,-240.22 764,-231.5 753.73,-228.18 742.83,-225.18 731.94,-222.51"/>
<polygon fill="black" stroke="black" points="733.08,-219.18 722.55,-220.3 731.48,-226 733.08,-219.18"/>
</g>
<!-- isaSampleToRawDataSeq_assayName -->
<g id="node5" class="node">
<title>isaSampleToRawDataSeq_assayName</title>
<polygon fill="#94ddf4" stroke="black" points="528.62,-264.5 528.62,-300.5 755.38,-300.5 755.38,-264.5 528.62,-264.5"/>
<text text-anchor="middle" x="642" y="-277.45" font-family="Times,serif" font-size="14.00">isaSampleToRawDataSeq_assayName</text>
</g>
<!-- isaSampleToRawDataSeq_assayName&#45;&gt;isaSampleToRawDataSeq -->
<g id="edge4" class="edge">
<title>isaSampleToRawDataSeq_assayName&#45;&gt;isaSampleToRawDataSeq</title>
<path fill="none" stroke="black" d="M642,-264.37C642,-255.55 642,-244.57 642,-234.51"/>
<polygon fill="black" stroke="black" points="645.5,-234.84 642,-224.84 638.5,-234.84 645.5,-234.84"/>
</g>
<!-- isaSampleToRawDataSeq_outName -->
<g id="node6" class="node">
<title>isaSampleToRawDataSeq_outName</title>
<polygon fill="#94ddf4" stroke="black" points="295.62,-264.5 295.62,-300.5 510.38,-300.5 510.38,-264.5 295.62,-264.5"/>
<text text-anchor="middle" x="403" y="-277.45" font-family="Times,serif" font-size="14.00">isaSampleToRawDataSeq_outName</text>
</g>
<!-- isaSampleToRawDataSeq_outName&#45;&gt;isaSampleToRawDataSeq -->
<g id="edge5" class="edge">
<title>isaSampleToRawDataSeq_outName&#45;&gt;isaSampleToRawDataSeq</title>
<path fill="none" stroke="black" d="M438.67,-264.07C461.49,-253.47 491.98,-240.32 520,-231.5 530.11,-228.32 540.82,-225.42 551.53,-222.81"/>
<polygon fill="black" stroke="black" points="552.25,-226.24 561.18,-220.55 550.65,-219.42 552.25,-226.24"/>
</g>
<!-- isaSampleToRawDataSeq_startingNodeNum -->
<g id="node7" class="node">
<title>isaSampleToRawDataSeq_startingNodeNum</title>
<polygon fill="#94ddf4" stroke="black" points="16,-264.5 16,-300.5 278,-300.5 278,-264.5 16,-264.5"/>
<text text-anchor="middle" x="147" y="-277.45" font-family="Times,serif" font-size="14.00">isaSampleToRawDataSeq_startingNodeNum</text>
</g>
<!-- isaSampleToRawDataSeq_startingNodeNum&#45;&gt;isaSampleToRawDataSeq -->
<g id="edge6" class="edge">
<title>isaSampleToRawDataSeq_startingNodeNum&#45;&gt;isaSampleToRawDataSeq</title>
<path fill="none" stroke="black" d="M186.6,-264.1C214.19,-252.79 252.15,-238.83 287,-231.5 375.68,-212.84 479.26,-207.19 551.56,-205.77"/>
<polygon fill="black" stroke="black" points="551.44,-209.27 561.38,-205.6 551.32,-202.27 551.44,-209.27"/>
</g>
<!-- kallisto_BootstrapSamples -->
<g id="node8" class="node">
<title>kallisto_BootstrapSamples</title>
<polygon fill="#94ddf4" stroke="black" points="1307.25,-264.5 1307.25,-300.5 1468.75,-300.5 1468.75,-264.5 1307.25,-264.5"/>
<text text-anchor="middle" x="1388" y="-277.45" font-family="Times,serif" font-size="14.00">kallisto_BootstrapSamples</text>
</g>
<!-- kallisto_BootstrapSamples&#45;&gt;kallisto -->
<g id="edge7" class="edge">
<title>kallisto_BootstrapSamples&#45;&gt;kallisto</title>
<path fill="none" stroke="black" d="M1413.65,-264.1C1431.07,-253.09 1455.04,-239.48 1478,-231.5 1516.32,-218.18 1562.41,-211.74 1594.51,-208.68"/>
<polygon fill="black" stroke="black" points="1594.51,-212.19 1604.16,-207.83 1593.89,-205.22 1594.51,-212.19"/>
</g>
<!-- kallisto_FragmentLength -->
<g id="node9" class="node">
<title>kallisto_FragmentLength</title>
<polygon fill="#94ddf4" stroke="black" points="1136.38,-264.5 1136.38,-300.5 1289.62,-300.5 1289.62,-264.5 1136.38,-264.5"/>
<text text-anchor="middle" x="1213" y="-277.45" font-family="Times,serif" font-size="14.00">kallisto_FragmentLength</text>
</g>
<!-- kallisto_FragmentLength&#45;&gt;kallisto -->
<g id="edge8" class="edge">
<title>kallisto_FragmentLength&#45;&gt;kallisto</title>
<path fill="none" stroke="black" d="M1235.81,-264.17C1252.18,-252.75 1275.29,-238.62 1298,-231.5 1352.25,-214.5 1517.79,-208.61 1594.37,-206.77"/>
<polygon fill="black" stroke="black" points="1594.43,-210.27 1604.35,-206.54 1594.27,-203.27 1594.43,-210.27"/>
</g>
<!-- kallisto_IndexInput -->
<g id="node10" class="node">
<title>kallisto_IndexInput</title>
<polygon fill="#94ddf4" stroke="black" points="996.12,-264.5 996.12,-300.5 1117.88,-300.5 1117.88,-264.5 996.12,-264.5"/>
<text text-anchor="middle" x="1057" y="-277.45" font-family="Times,serif" font-size="14.00">kallisto_IndexInput</text>
</g>
<!-- kallisto_IndexInput&#45;&gt;kallisto -->
<g id="edge9" class="edge">
<title>kallisto_IndexInput&#45;&gt;kallisto</title>
<path fill="none" stroke="black" d="M1074.93,-264.24C1088.17,-252.69 1107.26,-238.38 1127,-231.5 1170.61,-216.31 1482.71,-208.9 1594.39,-206.71"/>
<polygon fill="black" stroke="black" points="1594.33,-210.21 1604.26,-206.52 1594.2,-203.21 1594.33,-210.21"/>
</g>
<!-- kallisto_StandardDeviation -->
<g id="node11" class="node">
<title>kallisto_StandardDeviation</title>
<polygon fill="#94ddf4" stroke="black" points="1921.12,-264.5 1921.12,-300.5 2084.88,-300.5 2084.88,-264.5 1921.12,-264.5"/>
<text text-anchor="middle" x="2003" y="-277.45" font-family="Times,serif" font-size="14.00">kallisto_StandardDeviation</text>
</g>
<!-- kallisto_StandardDeviation&#45;&gt;kallisto -->
<g id="edge10" class="edge">
<title>kallisto_StandardDeviation&#45;&gt;kallisto</title>
<path fill="none" stroke="black" d="M1977.98,-264.06C1960.37,-252.74 1935.79,-238.78 1912,-231.5 1868.5,-218.19 1739.3,-210.69 1673.49,-207.63"/>
<polygon fill="black" stroke="black" points="1674.01,-204.15 1663.86,-207.2 1673.69,-211.15 1674.01,-204.15"/>
</g>
<!-- kallisto_isSingle -->
<g id="node12" class="node">
<title>kallisto_isSingle</title>
<polygon fill="#94ddf4" stroke="black" points="1797,-264.5 1797,-300.5 1903,-300.5 1903,-264.5 1797,-264.5"/>
<text text-anchor="middle" x="1850" y="-277.45" font-family="Times,serif" font-size="14.00">kallisto_isSingle</text>
</g>
<!-- kallisto_isSingle&#45;&gt;kallisto -->
<g id="edge11" class="edge">
<title>kallisto_isSingle&#45;&gt;kallisto</title>
<path fill="none" stroke="black" d="M1833.47,-264.16C1821.83,-253.02 1805.29,-239.25 1788,-231.5 1751.33,-215.06 1705.47,-209.11 1673.37,-207.01"/>
<polygon fill="black" stroke="black" points="1673.9,-203.54 1663.72,-206.49 1673.51,-210.53 1673.9,-203.54"/>
</g>
<!-- kallisto_resultsFolder -->
<g id="node13" class="node">
<title>kallisto_resultsFolder</title>
<polygon fill="#94ddf4" stroke="black" points="1645.5,-264.5 1645.5,-300.5 1778.5,-300.5 1778.5,-264.5 1645.5,-264.5"/>
<text text-anchor="middle" x="1712" y="-277.45" font-family="Times,serif" font-size="14.00">kallisto_resultsFolder</text>
</g>
<!-- kallisto_resultsFolder&#45;&gt;kallisto -->
<g id="edge12" class="edge">
<title>kallisto_resultsFolder&#45;&gt;kallisto</title>
<path fill="none" stroke="black" d="M1694.3,-264.37C1684.2,-254.59 1671.35,-242.15 1660.11,-231.27"/>
<polygon fill="black" stroke="black" points="1662.61,-228.82 1652.99,-224.38 1657.74,-233.85 1662.61,-228.82"/>
</g>
<!-- kallisto_sampleRecord -->
<g id="node14" class="node">
<title>kallisto_sampleRecord</title>
<polygon fill="#94ddf4" stroke="black" points="1486.75,-264.5 1486.75,-300.5 1627.25,-300.5 1627.25,-264.5 1486.75,-264.5"/>
<text text-anchor="middle" x="1557" y="-277.45" font-family="Times,serif" font-size="14.00">kallisto_sampleRecord</text>
</g>
<!-- kallisto_sampleRecord&#45;&gt;kallisto -->
<g id="edge13" class="edge">
<title>kallisto_sampleRecord&#45;&gt;kallisto</title>
<path fill="none" stroke="black" d="M1574.47,-264.37C1584.44,-254.59 1597.13,-242.15 1608.23,-231.27"/>
<polygon fill="black" stroke="black" points="1610.56,-233.89 1615.25,-224.39 1605.66,-228.89 1610.56,-233.89"/>
</g>
<!-- sleuth_inMetadataDataCol -->
<g id="node15" class="node">
<title>sleuth_inMetadataDataCol</title>
<polygon fill="#94ddf4" stroke="black" points="2103.25,-264.5 2103.25,-300.5 2264.75,-300.5 2264.75,-264.5 2103.25,-264.5"/>
<text text-anchor="middle" x="2184" y="-277.45" font-family="Times,serif" font-size="14.00">sleuth_inMetadataDataCol</text>
</g>
<!-- sleuth_inMetadataDataCol&#45;&gt;sleuth -->
<g id="edge14" class="edge">
<title>sleuth_inMetadataDataCol&#45;&gt;sleuth</title>
<path fill="none" stroke="black" d="M2194.73,-264.17C2210.66,-238.47 2240.68,-190 2259.44,-159.73"/>
<polygon fill="black" stroke="black" points="2262.25,-161.85 2264.54,-151.5 2256.3,-158.16 2262.25,-161.85"/>
</g>
<!-- sleuth_inMetadataFactorList -->
<g id="node16" class="node">
<title>sleuth_inMetadataFactorList</title>
<polygon fill="#94ddf4" stroke="black" points="2283,-264.5 2283,-300.5 2455,-300.5 2455,-264.5 2283,-264.5"/>
<text text-anchor="middle" x="2369" y="-277.45" font-family="Times,serif" font-size="14.00">sleuth_inMetadataFactorList</text>
</g>
<!-- sleuth_inMetadataFactorList&#45;&gt;sleuth -->
<g id="edge15" class="edge">
<title>sleuth_inMetadataFactorList&#45;&gt;sleuth</title>
<path fill="none" stroke="black" d="M2358.15,-264.17C2342.05,-238.47 2311.7,-190 2292.74,-159.73"/>
<polygon fill="black" stroke="black" points="2295.86,-158.12 2287.58,-151.5 2289.93,-161.83 2295.86,-158.12"/>
</g>
<!-- sleuth_inMetadataSample -->
<g id="node17" class="node">
<title>sleuth_inMetadataSample</title>
<polygon fill="#94ddf4" stroke="black" points="2473.12,-264.5 2473.12,-300.5 2630.88,-300.5 2630.88,-264.5 2473.12,-264.5"/>
<text text-anchor="middle" x="2552" y="-277.45" font-family="Times,serif" font-size="14.00">sleuth_inMetadataSample</text>
</g>
<!-- sleuth_inMetadataSample&#45;&gt;sleuth -->
<g id="edge16" class="edge">
<title>sleuth_inMetadataSample&#45;&gt;sleuth</title>
<path fill="none" stroke="black" d="M2522,-264.12C2505.06,-254.39 2483.43,-242.11 2464,-231.5 2412.12,-203.18 2351.44,-171.67 2313.35,-152.1"/>
<polygon fill="black" stroke="black" points="2315.08,-149.05 2304.59,-147.59 2311.88,-155.28 2315.08,-149.05"/>
</g>
<!-- sleuth_outFolder -->
<g id="node18" class="node">
<title>sleuth_outFolder</title>
<polygon fill="#94ddf4" stroke="black" points="2649.25,-264.5 2649.25,-300.5 2756.75,-300.5 2756.75,-264.5 2649.25,-264.5"/>
<text text-anchor="middle" x="2703" y="-277.45" font-family="Times,serif" font-size="14.00">sleuth_outFolder</text>
</g>
<!-- sleuth_outFolder&#45;&gt;sleuth -->
<g id="edge17" class="edge">
<title>sleuth_outFolder&#45;&gt;sleuth</title>
<path fill="none" stroke="black" d="M2685.09,-264C2673.18,-253.24 2656.7,-239.93 2640,-231.5 2529.23,-175.57 2382.96,-148.47 2314.47,-138.16"/>
<polygon fill="black" stroke="black" points="2315.28,-134.74 2304.88,-136.76 2314.27,-141.67 2315.28,-134.74"/>
</g>
</g>
</svg>
......@@ -109,15 +109,15 @@
<path fill="none" stroke="black" d="M79.18,-185.43C89.76,-174.74 104.84,-161.76 121,-155 157.69,-139.66 267.22,-133.56 330.49,-131.27"/>
<polygon fill="black" stroke="black" points="330.73,-134.77 340.61,-130.93 330.49,-127.77 330.73,-134.77"/>
</g>
<!-- finalOut -->
<!-- kallistoOutDir -->
<g id="node9" class="node">
<title>finalOut</title>
<title>kallistoOutDir</title>
<polygon fill="#94ddf4" stroke="black" points="346.06,-38.5 346.06,-74.5 407.94,-74.5 407.94,-38.5 346.06,-38.5"/>
<text text-anchor="middle" x="377" y="-52.3" font-family="Times,serif" font-size="14.00">finalOut</text>
<text text-anchor="middle" x="377" y="-52.3" font-family="Times,serif" font-size="14.00">kallistoOutDir</text>
</g>
<!-- kallisto&#45;&gt;finalOut -->
<!-- kallisto&#45;&gt;kallistoOutDir -->
<g id="edge8" class="edge">
<title>kallisto&#45;&gt;finalOut</title>
<title>kallisto&#45;&gt;kallistoOutDir</title>
<path fill="none" stroke="black" d="M377,-110.93C377,-103.17 377,-93.78 377,-85.06"/>
<polygon fill="black" stroke="black" points="380.5,-84.9 377,-74.9 373.5,-84.9 380.5,-84.9"/>
</g>
......
......@@ -37,15 +37,15 @@
<path fill="none" stroke="black" d="M491.95,-193.08C456.78,-182.13 394.44,-162.71 348.49,-148.4"/>
<polygon fill="black" stroke="black" points="349.25,-144.97 338.66,-145.34 347.16,-151.66 349.25,-144.97"/>
</g>
<!-- finalOut -->
<!-- kallistoOutDir -->
<g id="node11" class="node">
<title>finalOut</title>
<title>kallistoOutDir</title>
<polygon fill="#94ddf4" stroke="black" points="260.06,-38.5 260.06,-74.5 321.94,-74.5 321.94,-38.5 260.06,-38.5"/>
<text text-anchor="middle" x="291" y="-52.3" font-family="Times,serif" font-size="14.00">finalOut</text>
<text text-anchor="middle" x="291" y="-52.3" font-family="Times,serif" font-size="14.00">kallistoOutDir</text>
</g>
<!-- collectResults&#45;&gt;finalOut -->
<!-- collectResults&#45;&gt;kallistoOutDir -->
<g id="edge12" class="edge">
<title>collectResults&#45;&gt;finalOut</title>
<title>collectResults&#45;&gt;kallistoOutDir</title>
<path fill="none" stroke="black" d="M291,-111.31C291,-103.29 291,-93.55 291,-84.57"/>
<polygon fill="black" stroke="black" points="294.5,-84.53 291,-74.53 287.5,-84.53 294.5,-84.53"/>
</g>
......
......@@ -5,15 +5,29 @@ The [Talinum Genome Draft](./studies/TalinumGenomeDraft) originates from <https:
## Table of Contents
1. [Description](#description)
2. [Publication](#publication)
3. Studies
- [TalinumGenomeDraft](#study--talinumgenomedraft)
- [TalinumSamples-STRI](#study--TalinumSamples-STRI)
4. Assays
- [MassHunter_targets](#assay--masshunter_targets)
- [GCqTOF_targets](#assay--gcqtof_targets)
- [RNASeq](#assay--RNASeq)
- [Table of Contents](#table-of-contents)
- [Description](#description)
- [Relationships between Assays and Studies](#relationships-between-assays-and-studies)
- [Workflow Overview](#workflow-overview)
- [Additional details](#additional-details)
- [Publication](#publication)
- [Study : *TalinumGenomeDraft*](#study--talinumgenomedraft)
- [Additional details](#additional-details-1)
- [Annotation headers](#annotation-headers)
- [Study : *TalinumSamples-STRI*](#study--talinumsamples-stri)
- [Additional details](#additional-details-2)
- [Annotation headers](#annotation-headers-1)
- [Assay : *MassHunter\_targets*](#assay--masshunter_targets)
- [Additional details](#additional-details-3)
- [Annotation headers](#annotation-headers-2)
- [Assay : *RNASeq*](#assay--rnaseq)
- [Additional details](#additional-details-4)
- [Annotation headers](#annotation-headers-3)
- [Assay : *GCqTOF\_targets*](#assay--gcqtof_targets)
- [Additional details](#additional-details-5)
- [Annotation headers](#annotation-headers-4)
### Description
......@@ -67,7 +81,12 @@ class ASSAY_MassHunter_targets,ASSAY_RNASeq,ASSAY_GCqTOF_targets assayStyle;
class TalinumGenomeDraft,plant_material,mh-quant-results,mh-quant-report,rna_extraction,illumina,metabolite_extraction,gas_chromatography,mass_spec processStyle;
```
### Additional details
## Workflow Overview
![arc.cwl](.cwl/arc-cwl.svg)
## Additional details
| Meta Data | Description |
| --------- | ----------- |
......
################################################################################
### runs/kallisto
################################################################################
## Genome file to build kallisto Index
kallisto_IndexInput:
- class: File
path: ./studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa
format: edam:format_1929 # FASTA
## Fastq files to be mapped
# The `readsOfOneSample` looks more complicated than needed
# It's an array of records (each with one or mupltiple files and a sample name) to generically allow multiple fastq files per sample
kallisto_sampleRecord:
- readsOfOneSample:
- class: File
path: ./assays/RNASeq/dataset/DB_097_CAMMD_CAGATC_L001_R1_001.fastq.gz
format: edam:format_1930
sampleName: 'DB_097'
- readsOfOneSample:
- class: File
path: ./assays/RNASeq/dataset/DB_163_reC3MD_GTGAAA_L001_R1_001.fastq.gz
format: edam:format_1930
sampleName: 'DB_163'
- readsOfOneSample:
- class: File
path: ./assays/RNASeq/dataset/DB_099_CAMMD_CTTGTA_L001_R1_001.fastq.gz
format: edam:format_1930
sampleName: 'DB_099'
- readsOfOneSample:
- class: File
path: ./assays/RNASeq/dataset/DB_103_CAMMD_AGTCAA_L001_R1_001.fastq.gz
format: edam:format_1930
sampleName: 'DB_103'
- readsOfOneSample:
- class: File
path: ./assays/RNASeq/dataset/DB_161_reC3MD_GTCCGC_L001_R1_001.fastq.gz
format: edam:format_1930
sampleName: 'DB_161'
- readsOfOneSample:
- class: File
path: ./assays/RNASeq/dataset/DB_165_re-C3MD_GTGAAA_L002_R1_001.fastq.gz
format: edam:format_1930
sampleName: 'DB_165'
### Kallisto quant Parameters
kallisto_isSingle: true
kallisto_FragmentLength: 200
kallisto_StandardDeviation: 20
kallisto_BootstrapSamples: 30
kallisto_resultsFolder: kallisto_results
$namespaces:
edam: https://edamontology.org/
################################################################################
### runs/isaSampleToRawDataSeq
################################################################################
isaSampleToRawDataSeq_arcPath:
class: Directory
path: ./
isaSampleToRawDataSeq_assayName: "RNASeq"
isaSampleToRawDataSeq_outName: rnaseq-samples
isaSampleToRawDataSeq_startingNodeNum: 0
################################################################################
### runs/sleuth
################################################################################
sleuth_inMetadataSample: "Input [Source Name]"
sleuth_inMetadataFactorList:
- "Factor [Photosynthesis mode]"
sleuth_inMetadataDataCol: "Output [Data]"
sleuth_outFolder: results
arc.cwl 0 → 100644
cwlVersion: v1.2
class: Workflow
requirements:
SubworkflowFeatureRequirement: {}
ScatterFeatureRequirement: {}
MultipleInputFeatureRequirement: {}
inputs:
#### runs/kallisto
kallisto_IndexInput: File[]
kallisto_sampleRecord:
type:
type: array
items:
type: record
fields:
readsOfOneSample:
type: File[]
sampleName:
type: string?
kallisto_isSingle: boolean
kallisto_FragmentLength: double?
kallisto_StandardDeviation: double?
kallisto_BootstrapSamples: int?
kallisto_resultsFolder: string
#### runs/isaSampleToRawDataSeq
isaSampleToRawDataSeq_arcPath: Directory
isaSampleToRawDataSeq_assayName: string
isaSampleToRawDataSeq_startingNodeNum: int
isaSampleToRawDataSeq_outName: string
#### runs/sleuth
# sleuth_inKallistoResults: Directory
# sleuth_inMetadataFile: File
sleuth_inMetadataSample: string
sleuth_inMetadataFactorList: string[]
sleuth_inMetadataDataCol: string
sleuth_outFolder: string
steps:
kallisto:
run: runs/kallisto/run.cwl
in:
IndexInput: kallisto_IndexInput
sampleRecord: kallisto_sampleRecord
isSingle: kallisto_isSingle
FragmentLength: kallisto_FragmentLength
StandardDeviation: kallisto_StandardDeviation
BootstrapSamples: kallisto_BootstrapSamples
resultsFolder: kallisto_resultsFolder
out: [kallistoOutDir]
isaSampleToRawDataSeq:
run: runs/isaSampleToRawDataSeq/run.cwl
in:
arcPath: isaSampleToRawDataSeq_arcPath
assayName: isaSampleToRawDataSeq_assayName
startingNodeNum: isaSampleToRawDataSeq_startingNodeNum
outName: isaSampleToRawDataSeq_outName
out: [sampleseqCsv, sampleseqXlsx]
sleuth:
run: runs/sleuth/run.cwl
in:
inKallistoResults: kallisto/kallistoOutDir
inMetadataFile: isaSampleToRawDataSeq/sampleseqCsv
inMetadataSample: sleuth_inMetadataSample
inMetadataFactorList: sleuth_inMetadataFactorList
inMetadataDataCol: sleuth_inMetadataDataCol
outFolder: sleuth_outFolder
out: [outdir]
outputs:
outdir:
type: Directory[]
outputSource: sleuth/outdir
\ No newline at end of file
......@@ -16,9 +16,9 @@ steps:
in:
fastq: fastq
finaloutdir: finaloutdir
out: [outdir]
out: [fastqc_outdir]
outputs:
outdir:
fastqc_outdir:
type: Directory
outputSource: fastqc/outdir
\ No newline at end of file
outputSource: fastqc/fastqc_outdir
\ No newline at end of file
No preview for this file type
......@@ -15,10 +15,14 @@ steps:
assayName: assayName
startingNodeNum: startingNodeNum
outName: outName
out: [output]
out:
- sampleseqCsv
- sampleseqXlsx
outputs:
output:
type: File[]
outputSource: isaSampleToRawDataSeq/output
sampleseqCsv:
type: File
outputSource: isaSampleToRawDataSeq/sampleseqCsv
sampleseqXlsx:
type: File
outputSource: isaSampleToRawDataSeq/sampleseqXlsx
\ No newline at end of file
......@@ -35,9 +35,9 @@ steps:
StandardDeviation: StandardDeviation
BootstrapSamples: BootstrapSamples
resultsFolder: resultsFolder
out: [finalOut]
out: [kallistoOutDir]
outputs:
finalOut:
type: Directory[]
outputSource: kallisto/finalOut
kallistoOutDir:
type: Directory
outputSource: kallisto/kallistoOutDir
......@@ -12,7 +12,7 @@ inputs:
outFolder: string
steps:
collectResults:
sleuth:
run: ../../workflows/sleuth/workflow.cwl
in:
inKallistoResults: inKallistoResults
......@@ -26,4 +26,4 @@ steps:
outputs:
outdir:
type: Directory[]
outputSource: collectResults/outdir
outputSource: sleuth/outdir
......@@ -2,12 +2,14 @@
cwlVersion: v1.2
class: CommandLineTool
label: Run fastqc on raw reads in FASTQ format (single or paired end) or aligned reads in BAM.
label: FastQC - A high throughput sequence QC analysis tool
doc: |
simplified from: https://github.com/common-workflow-library/bio-cwl-tools/blob/66f620da5b0a11e934a6da83272205a2516bcd91/fastqc/fastqc_1.cwl
Original docs: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
Run fastqc on raw reads in FASTQ format (single or paired end) or aligned reads in BAM.
This CWL was adapted from: https://github.com/common-workflow-library/bio-cwl-tools/blob/66f620da5b0a11e934a6da83272205a2516bcd91/fastqc/fastqc_1.cwl
hints:
ResourceRequirement:
......@@ -18,11 +20,13 @@ hints:
SoftwareRequirement:
packages:
fastqc:
specs: [ https://identifiers.org/biotools/fastqc ]
specs:
- https://identifiers.org/biotools/fastqc
- - https://identifiers.org/rrid/RRID:SCR_014583
version: [ "0.11.9" ]
baseCommand: "fastqc"
arguments:
- valueFrom: $(runtime.outdir)
prefix: "-o"
......@@ -46,3 +50,13 @@ outputs:
outputBinding:
glob: "*_fastqc.html"
$namespaces:
edam: https://edamontology.org/
s: https://schema.org/
$schemas:
- https://edamontology.org/EDAM_1.18.owl
s:license: https://spdx.org/licenses/GPL-3.0-or-later
cwlVersion: v1.2
class: ExpressionTool
label: Collect files in a directory
label: Gather files
doc: |
Takes Files (e.g. from a workflow step) and yields them in a desired directory.
Helper tool to organize workflow outputs
Takes an array of files (e.g. from a workflow step) and yields them in a destination directory.
Adapted from: https://github.com/common-workflow-language/cwl-v1.1/blob/a22b7580c6b50e77c0a181ca59d3828dd5c69143/tests/dir7.cwl
requirements:
- class: InlineJavascriptRequirement
inputs:
files: File[]
inFiles: File[]
destination: string
expression: |
${
return {"outDir": {
"class": "Directory",
"basename": inputs.destination,
"listing": inputs.files
"listing": inputs.inFiles
} };
}
outputs:
......
......@@ -18,15 +18,17 @@ steps:
fastq: fastq
out: [fastqc_zip, fastqc_html]
collectFiles:
run: ./collectFilesInDir.cwl
run: ./gather-files.cwl
in:
destination: finaloutdir
files:
source: [fastqc/fastqc_html, fastqc/fastqc_zip]
inFiles:
source:
- fastqc/fastqc_html
- fastqc/fastqc_zip
linkMerge: merge_flattened
destination: finaloutdir
out: [outDir]
outputs:
outdir:
fastqc_outdir:
type: Directory
outputSource: collectFiles/outDir
\ No newline at end of file
......@@ -39,9 +39,13 @@ inputs:
position: 4
outputs:
output:
type: File[]
sampleseqCsv:
type: File
outputBinding:
glob:
- "*.csv"
sampleseqXlsx:
type: File
outputBinding:
glob:
- "*.xlsx"
cwlVersion: v1.2
class: ExpressionTool
label: Gather directories
doc: |
Takes a directory (e.g. from a workflow step) and yields it in a desired directory.
Helper tool to organize workflow outputs
Takes an array of directories (e.g. from a workflow step) and yields them in a destination directory.
Adapted from: https://github.com/common-workflow-language/cwl-v1.1/blob/a22b7580c6b50e77c0a181ca59d3828dd5c69143/tests/dir7.cwl
requirements:
- class: InlineJavascriptRequirement
inputs:
inDir: Directory
inDirs: Directory[]
destinationDir: string
expression: |
${
return {"outDir": {
"class": "Directory",
"basename": inputs.destinationDir,
"listing": [inputs.inDir]
"listing": inputs.inDirs
} };
}
outputs:
outDir: Directory
\ No newline at end of file
......@@ -2,17 +2,47 @@
cwlVersion: v1.2
class: CommandLineTool
label: Kallisto index
doc: |
Docs: https://pachterlab.github.io/kallisto/
Builds a kallisto index
Usage: kallisto index [arguments] FASTA-files
Required argument:
-i, --index=STRING Filename for the kallisto index to be constructed
Optional argument:
-k, --kmer-size=INT k-mer (odd) length (default: 31, max value: 63)
-t, --threads=INT Number of threads to use (default: 1)
-d, --d-list=STRING Path to a FASTA-file containing sequences to mask from quantification
--make-unique Replace repeated target names with unique names
--aa Generate index from a FASTA-file containing amino acid sequences
--distinguish Generate index where sequences are distinguished by the sequence name
-T, --tmp=STRING Temporary directory (default: tmp)
-m, --min-size=INT Length of minimizers (default: automatically chosen)
-e, --ec-max-size=INT Maximum number of targets in an equivalence class (default: no maximum)
This CWL was adapted from: https://github.com/common-workflow-library/bio-cwl-tools/commit/91c42fb809ce18eafe16155cca0abf362270c0fe
hints:
DockerRequirement:
dockerPull: quay.io/biocontainers/kallisto:0.51.1--ha4fb952_1
SoftwareRequirement:
packages:
kallisto:
version: [ "0.50.0" ]
specs: [ https://identifiers.org/biotools/kallisto ]
version: [ "0.51.1" ]
specs:
- https://identifiers.org/rrid/RRID:SCR_016582
- https://identifiers.org/biotools/kallisto
requirements:
- class: InlineJavascriptRequirement
InlineJavascriptRequirement: {}
baseCommand: [kallisto, index]
inputs:
InputFiles:
......@@ -41,8 +71,6 @@ inputs:
inputBinding:
prefix: "--make-unique"
baseCommand: [kallisto, index]
outputs:
index:
type: File
......@@ -51,5 +79,8 @@ outputs:
$namespaces:
edam: https://edamontology.org/
s: https://schema.org/
$schemas:
- https://edamontology.org/EDAM_1.18.owl
s:license: https://spdx.org/licenses/BSD-2-Clause
......@@ -2,13 +2,51 @@
cwlVersion: v1.2
class: CommandLineTool
label: Kallisto quant
doc: |
Docs: https://pachterlab.github.io/kallisto/
Computes equivalence classes for reads and quantifies abundances
Usage: kallisto quant [arguments] FASTQ-files
Required arguments:
-i, --index=STRING Filename for the kallisto index to be used for
quantification
-o, --output-dir=STRING Directory to write output to
Optional arguments:
-b, --bootstrap-samples=INT Number of bootstrap samples (default: 0)
--seed=INT Seed for the bootstrap sampling (default: 42)
--plaintext Output plaintext instead of HDF5
--single Quantify single-end reads
--single-overhang Include reads where unobserved rest of fragment is
predicted to lie outside a transcript
--fr-stranded Strand specific reads, first read forward
--rf-stranded Strand specific reads, first read reverse
-l, --fragment-length=DOUBLE Estimated average fragment length
-s, --sd=DOUBLE Estimated standard deviation of fragment length
(default: -l, -s values are estimated from paired
end data, but are required when using --single)
-p, --priors Priors for the EM algorithm, either as raw counts or as
probabilities. Pseudocounts are added to raw reads to
prevent zero valued priors. Supplied in the same order
as the transcripts in the transcriptome
-t, --threads=INT Number of threads to use (default: 1)
--verbose Print out progress information every 1M proccessed reads
This CWL was adapted from: https://github.com/common-workflow-library/bio-cwl-tools/commit/91c42fb809ce18eafe16155cca0abf362270c0fe
hints:
DockerRequirement:
dockerPull: quay.io/biocontainers/kallisto:0.51.1--ha4fb952_1
SoftwareRequirement:
packages:
kallisto:
version: [ "0.50.0" ]
version: [ "0.51.1" ]
specs: [ https://identifiers.org/biotools/kallisto ]
inputs:
......@@ -126,12 +164,16 @@ arguments: [ "--output-dir", $(inputs.QuantOutfolder) ]
outputs:
outFolder:
kallistoQuantOutDir:
type: Directory
outputBinding:
glob: $(runtime.outdir)/$(inputs.QuantOutfolder)
$namespaces:
edam: https://edamontology.org/
s: https://schema.org/
$schemas:
- https://edamontology.org/EDAM_1.18.owl
s:license: https://spdx.org/licenses/BSD-2-Clause
#!/usr/bin/env cwl-runner
cwlVersion: v1.2
class: CommandLineTool
hints:
DockerRequirement:
dockerPull: quay.io/biocontainers/kallisto:0.50.1--h6de1650_2
SoftwareRequirement:
packages:
kallisto:
version: [ "0.50.0" ]
specs: [ https://identifiers.org/biotools/kallisto ]
inputs: []
baseCommand: [kallisto]
outputs: []
\ No newline at end of file
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment