cwl/lightning/fasta2numpy-wf.cwl

   1 # Copyright (C) The Lightning Authors. All rights reserved.
   2 #
   3 # SPDX-License-Identifier: AGPL-3.0
   4
   5 $namespaces:
   6   arv: "http://arvados.org/cwl#"
   7 cwlVersion: v1.2
   8 class: Workflow
   9 requirements:
  10   ScatterFeatureRequirement: {}
  11   SubworkflowFeatureRequirement: {}
  12   StepInputExpressionRequirement: {}
  13   MultipleInputFeatureRequirement: {}
  14 hints:
  15   arv:UsePreemptible:
  16     usePreemptible: true
  17
  18 inputs:
  19   tagset:
  20     type: File
  21   fastadirs:
  22     type:
  23       type: array
  24       items: Directory
  25   refdir:
  26     type: Directory
  27   batchsize:
  28     type: int
  29   regions:
  30     type: File?
  31   matchgenome:
  32     type: string
  33   threads:
  34     type: int
  35   mergeoutput:
  36     type: string
  37   expandregions:
  38     type: int
  39   phenotypesnofamilydir:
  40     type: Directory
  41   phenotypesdir:
  42     type: Directory
  43   trainingsetsize:
  44     type: float
  45   randomseed:
  46     type: int
  47   pcacomponents:
  48     type: int
  49   chrs: string[]
  50   snpeffdatadir: Directory
  51   genomeversion: string
  52   dbsnp:
  53     type: File
  54     secondaryFiles: [.csi]
  55   gnomaddir: Directory
  56   readmeinfo: string[]
  57
  58 outputs:
  59   stagednpydir:
  60     type: Directory
  61     outputSource: stage-output/stagednpydir
  62   stagedonehotnpydir:
  63     type: Directory
  64     outputSource: stage-output/stagedonehotnpydir
  65   stagedannotationdir:
  66     type: Directory
  67     outputSource: stage-output/stagedannotationdir
  68   readme:
  69     type: File
  70     outputSource: genreadme/readme
  71
  72 steps:
  73   batch-dirs:
  74     run: batch-dirs.cwl
  75     in:
  76       dirs: fastadirs
  77       batchsize: batchsize
  78     out: [batches]
  79
  80   lightning-import_data:
  81     run: lightning-import.cwl
  82     scatter: fastadirs
  83     in:
  84       saveincomplete:
  85         valueFrom: "false"
  86       tagset: tagset
  87       fastadirs: batch-dirs/batches
  88     out: [lib]
  89
  90   lightning-import_refs:
  91     run: lightning-import.cwl
  92     in:
  93       saveincomplete:
  94         valueFrom: "true"
  95       tagset: tagset
  96       fastadirs: refdir
  97     out: [lib]
  98
  99   lightning-slice:
 100     run: lightning-slice.cwl
 101     in:
 102       datalibs: lightning-import_data/lib
 103       reflib: lightning-import_refs/lib
 104     out: [libdir]
 105
 106   lightning-tiling-stats:
 107     run: lightning-tiling-stats.cwl
 108     in:
 109       libdir: lightning-slice/libdir
 110     out: [bed]
 111
 112   lightning-choose-samples:
 113     run: lightning-choose-samples.cwl
 114     in:
 115       matchgenome: matchgenome
 116       libdir: lightning-slice/libdir
 117       phenotypesdir: phenotypesnofamilydir
 118       trainingsetsize: trainingsetsize
 119       randomseed: randomseed
 120     out: [samplescsv]
 121
 122   lightning-slice-numpy:
 123     run: lightning-slice-numpy.cwl
 124     in:
 125       matchgenome: matchgenome
 126       libdir: lightning-slice/libdir
 127       regions: regions
 128       threads: threads
 129       mergeoutput: mergeoutput
 130       expandregions: expandregions
 131       samplescsv: lightning-choose-samples/samplescsv
 132     out: [outdir, npys, chunktagoffsetcsv]
 133
 134   lightning-slice-numpy-onehot_chi2:
 135     run: lightning-slice-numpy-onehot.cwl
 136     in:
 137       matchgenome: matchgenome
 138       libdir: lightning-slice/libdir
 139       regions: regions
 140       mergeoutput: mergeoutput
 141       expandregions: expandregions
 142       samplescsv: lightning-choose-samples/samplescsv
 143     out: [outdir, npys]
 144
 145   lightning-slice-numpy-onehot_logisticregression:
 146     run: lightning-slice-numpy-onehot.cwl
 147     in:
 148       matchgenome: matchgenome
 149       libdir: lightning-slice/libdir
 150       regions: regions
 151       mergeoutput: mergeoutput
 152       expandregions: expandregions
 153       samplescsv: lightning-slice-numpy-pca/pcasamplescsv
 154     out: [outdir, npys]
 155
 156   lightning-slice-numpy-pca:
 157     run: lightning-slice-numpy-pca.cwl
 158     in:
 159       matchgenome: matchgenome
 160       libdir: lightning-slice/libdir
 161       regions: regions
 162       threads: threads
 163       mergeoutput: mergeoutput
 164       expandregions: expandregions
 165       samplescsv: lightning-choose-samples/samplescsv
 166       pcacomponents: pcacomponents
 167     out: [outdir, pcanpy, pcasamplescsv]
 168
 169   lightning-slice-numpy-onehot:
 170     run: lightning-slice-numpy-onehot.cwl
 171     in:
 172       matchgenome: matchgenome
 173       libdir: lightning-slice/libdir
 174       regions: regions
 175       mergeoutput: mergeoutput
 176       expandregions: expandregions
 177       samplescsv: lightning-choose-samples/samplescsv
 178     out: [outdir, npys]
 179
 180   lightning-plot_1-2:
 181     run: lightning-plot.cwl
 182     in:
 183       pcanpy: lightning-slice-numpy-pca/pcanpy
 184       pcasamplescsv: lightning-slice-numpy-pca/pcasamplescsv
 185       phenotypesdir: phenotypesdir
 186       xcomponent:
 187         valueFrom: "1"
 188       ycomponent:
 189         valueFrom: "2"
 190     out: [png]
 191
 192   lightning-plot_2-3:
 193     run: lightning-plot.cwl
 194     in:
 195       pcanpy: lightning-slice-numpy-pca/pcanpy
 196       pcasamplescsv: lightning-slice-numpy-pca/pcasamplescsv
 197       phenotypesdir: phenotypesdir
 198       xcomponent:
 199         valueFrom: "2"
 200       ycomponent:
 201         valueFrom: "3"
 202     out: [png]
 203
 204   lightning-anno2vcf-onehot:
 205     run: lightning-anno2vcf.cwl
 206     in:
 207       annodir: lightning-slice-numpy-onehot/outdir
 208     out: [vcfdir]
 209
 210   make-libname:
 211     run: make-libname.cwl
 212     in:
 213       matchgenome: matchgenome
 214       genomeversion: genomeversion
 215     out: [libname]
 216
 217   annotate-wf:
 218     run: ../annotation/annotate-wf.cwl
 219     in:
 220       sample: make-libname/libname
 221       chrs: chrs
 222       vcfdir: lightning-anno2vcf-onehot/vcfdir
 223       snpeffdatadir: snpeffdatadir
 224       genomeversion: genomeversion
 225       dbsnp: dbsnp
 226       gnomaddir: gnomaddir
 227     out: [annotatedvcf, summary]
 228
 229   stage-output:
 230     run: stage-output.cwl
 231     in:
 232       libname: make-libname/libname
 233       npyfiles:
 234         source: [lightning-slice-numpy/npys, lightning-slice-numpy/chunktagoffsetcsv]
 235         linkMerge: merge_flattened
 236       onehotnpyfiles: lightning-slice-numpy-onehot/npys
 237       pcapngs:
 238         source: [lightning-plot_1-2/png, lightning-plot_2-3/png]
 239         linkMerge: merge_flattened
 240       bed: lightning-tiling-stats/bed
 241       annotatedvcf: annotate-wf/annotatedvcf
 242       summary: annotate-wf/summary
 243     out: [stagednpydir, stagedonehotnpydir, stagedannotationdir]
 244
 245   genreadme:
 246     run: genreadme.cwl
 247     in:
 248       samplescsv: lightning-choose-samples/samplescsv
 249       readmeinfo: readmeinfo
 250     out: [readme]