extend Kallisto tools (#158)

Brilator · web-flow · commit 810495363e06 · 2025-03-25T08:20:08.000Z
diff --git a/Kallisto/Kallisto-Index.cwl b/Kallisto/Kallisto-Index.cwl
@@ -1,53 +1,77 @@
 #!/usr/bin/env cwl-runner
 cwlVersion: v1.0
 class: CommandLineTool
+label: Kallisto index
+doc: |2
 
-hints:
-  DockerRequirement:
-    dockerPull: quay.io/biocontainers/kallisto:0.45.0--hdcc98e5_0
-  SoftwareRequirement:
-    packages:
-      kallisto:
-        version: [ "0.45.0" ]
-        specs: [ https://identifiers.org/biotools/kallisto ]
+  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)
 
 inputs:
-  InputFiles:
-    type: File[]
-    format: edam:format_1929 # FASTA
-    inputBinding:
-      position: 200
-    
   IndexName:
     type: string
     inputBinding:
-      prefix: "--index="
+      prefix: --index=
+      valueFrom: $(self).kallistoIndex
       separate: false
-      valueFrom: $(self).kl
-
-#Optional arguments
-
+  inputFasta:
+    type: File[]
+    format: edam:format_1929
+    inputBinding:
+      position: 200
   kmerSize:
     type: int?
     inputBinding:
-      prefix: "--kmer-size="
+      prefix: --kmer-size=
       separate: false
-
   makeUnique:
     type: boolean?
     inputBinding:
-      prefix: "--make-unique"
-
-baseCommand: [kallisto, index]
+      prefix: --make-unique
 
 outputs:
-
   index:
     type: File
     outputBinding:
-      glob: $(inputs.IndexName)
+      glob: $(inputs.IndexName).kallistoIndex
+
+baseCommand:
+- kallisto
+- index
+
+hints:
+  DockerRequirement:
+    dockerPull: quay.io/biocontainers/kallisto:0.51.1--ha4fb952_1
+  SoftwareRequirement:
+    packages:
+    - package: kallisto
+      specs:
+      - https://identifiers.org/rrid/RRID:SCR_016582
+      - https://identifiers.org/biotools/kallisto
+      version:
+      - 0.51.1
 
 $namespaces:
-  edam: http://edamontology.org/
+  edam: https://edamontology.org/
+  s: https://schema.org/
 $schemas:
-  - https://edamontology.org/EDAM_1.18.owl
+- https://edamontology.org/EDAM_1.25.owl
+- https://schema.org/version/latest/schemaorg-current-https.rdf
diff --git a/Kallisto/Kallisto-Quant.cwl b/Kallisto/Kallisto-Quant.cwl
@@ -1,151 +1,155 @@
 #!/usr/bin/env cwl-runner
 cwlVersion: v1.0
 class: CommandLineTool
-
-hints:
-  DockerRequirement:
-    dockerPull: quay.io/biocontainers/kallisto:0.45.0--hdcc98e5_0
-  SoftwareRequirement:
-    packages:
-      kallisto:
-        version: [ "0.45.0" ]
-        specs: [ https://identifiers.org/biotools/kallisto ]
+label: Kallisto quant
+doc: |2
+
+  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
 
 inputs:
-  InputReads:
-    type: File[]
-    format: edam:format_1930  # FASTA
+  BootstrapSamples:
+    type: int?
     inputBinding:
-      position: 200
-
+      prefix: --bootstrap-samples=
+      separate: false
+  FragmentLength:
+    type: double?
+    inputBinding:
+      prefix: --fragment-length=
+      separate: false
+  GenomeBam:
+    type:
+    - 'null'
+    - name: genome_bam
+      type: record
+      fields:
+        chromosomes:
+          type: File
+          inputBinding:
+            prefix: --chromosomes
+        genomebam:
+          type: boolean
+          inputBinding:
+            prefix: --genomebam
+        gtf:
+          type: File
+          inputBinding:
+            prefix: --gtf
   Index:
     type: File
     inputBinding:
+      prefix: --index
       position: 1
-      prefix: "--index"
-
-  isSingle:
-    type: boolean
-    inputBinding:
-      position: 2
-      prefix: "--single"
-
-  #Optional Inputs
-
-  isBias:
-    type: boolean?
-    inputBinding:
-      prefix: "--bias"
-
-  isFusion:
-    type: boolean?
+  InputReads:
+    type: File[]
+    format: edam:format_1930
     inputBinding:
-      prefix: "--fusion"
-
-  isSingleOverhang:
+      position: 200
+  PseudoBam:
     type: boolean?
     inputBinding:
-      prefix: "--single-overhang"
-  
-  FragmentLength:
-    type: double?
+      prefix: --pseudobam
+  QuantOutfolder:
+    type: string
+  Seed:
+    type: int?
     inputBinding:
-      separate: false
-      prefix: "--fragment-length="
-  
+      prefix: --seed
   StandardDeviation:
     type: double?
     inputBinding:
-      prefix: "--sd"
-  
-  BootstrapSamples:
-    type: int?
-    inputBinding:
-      separate: false
-      prefix: "--bootstrap-samples="
-  
-  Seed:
-    type: int?
-    inputBinding:
-      prefix: "--seed"
-
-#Using record inputs to create mutually exclusive inputs
+      prefix: --sd
   Strand:
     type:
-      - "null"
-      - type: record
-        name: forward
-        fields:
-          forward:
-              type: boolean
-              inputBinding:
-                prefix: "--fr-stranded"
-
-      - type: record
-        name: reverse
-        fields:
-          reverse:
-            type: boolean
-            inputBinding:
-              prefix: "--rf-stranded"
-
-  PseudoBam:
+    - 'null'
+    - name: forward
+      type: record
+      fields:
+        forward:
+          type: boolean
+          inputBinding:
+            prefix: --fr-stranded
+    - name: reverse
+      type: record
+      fields:
+        reverse:
+          type: boolean
+          inputBinding:
+            prefix: --rf-stranded
+  isBias:
     type: boolean?
     inputBinding:
-      prefix: "--pseudobam"
-
-#Using record inputs to create dependent inputs
-  
-  GenomeBam:
-    type:
-      - "null"
-      - type: record
-        name: genome_bam
-        fields:
-          genomebam:
-            type: boolean
-            inputBinding:
-              prefix: "--genomebam"
-
-          gtf:
-            type: File
-            inputBinding:
-              prefix: "--gtf"
-
-          chromosomes:
-            type: File
-            inputBinding:
-              prefix: "--chromosomes"
-
-baseCommand: [ kallisto, quant ]
-
-arguments: [ "--output-dir", out ]
+      prefix: --bias
+  isFusion:
+    type: boolean?
+    inputBinding:
+      prefix: --fusion
+  isSingle:
+    type: boolean
+    inputBinding:
+      prefix: --single
+      position: 2
+  isSingleOverhang:
+    type: boolean?
+    inputBinding:
+      prefix: --single-overhang
 
 outputs:
-
-  quantification_h5:
-    type: File
+  kallistoQuantOutDir:
+    type: Directory
     outputBinding:
-      glob: out/abundances.h5
+      glob: $(runtime.outdir)/$(inputs.QuantOutfolder)
 
-# Long form method for defining optional outputs
+baseCommand:
+- kallisto
+- quant
+arguments:
+- --output-dir
+- $(inputs.QuantOutfolder)
 
-  quantification_tsv:
-    type: File
-    outputBinding:
-      glob: out/abundances.tsv
-
-  bam:
-    type: ["null", File]
-    outputBinding:
-      glob: "out/*.bam"
-
-  fusions:
-    type: ["null", File]
-    outputBinding:
-      glob: "fusion.txt"
+hints:
+  DockerRequirement:
+    dockerPull: quay.io/biocontainers/kallisto:0.51.1--ha4fb952_1
+  SoftwareRequirement:
+    packages:
+    - package: kallisto
+      specs:
+      - https://identifiers.org/biotools/kallisto
+      version:
+      - 0.51.1
 
 $namespaces:
-  edam: http://edamontology.org/
+  edam: https://edamontology.org/
+  s: https://schema.org/
 $schemas:
-  - https://edamontology.org/EDAM_1.18.owl
+- https://edamontology.org/EDAM_1.25.owl
+- https://schema.org/version/latest/schemaorg-current-https.rdf
