Merge pull request #244 from Delphine-L/VGP2-update

Update of VGP WF2 : kmer profiling for Trio Data

workflows/VGP-assembly-v2/kmer-profiling-hifi-trio-VGP2/.dockstore.yml

@@ -0,0 +1,7 @@
+version: 1.2
+workflows:
+- name: main
+  primaryDescriptorPath: /kmer-profiling-hifi-trio-VGP2.ga
+  subclass: Galaxy
+  testParameterFiles:
+  - /kmer-profiling-hifi-trio-VGP2-tests.yml

workflows/VGP-assembly-v2/VGP-meryldb-creation-trio/CHANGELOG.md → workflows/VGP-assembly-v2/kmer-profiling-hifi-trio-VGP2/CHANGELOG.md

@@ -6,6 +6,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.1] - 2023-10-30
+
+### Added
+- Clearer labels
+
+### Removed
+- Interlacing step that was unneccessary
+- Requirement for paired list inputs for the Illumina parental reads. A dataset collection list is sufficient now.
+- Unnecessary workflow intputs
 
 ## [0.1] - 2021-08-26
 ### Added

workflows/VGP-assembly-v2/VGP-meryldb-creation-trio/README.md → workflows/VGP-assembly-v2/kmer-profiling-hifi-trio-VGP2/README.md

@@ -4,9 +4,9 @@ This workflow collects the metrics on the properties of the genome under conside
 
 ### Inputs
 
--   Collection of Hifi long reads in FASTQ format
--   Paternal short-read Illumina sequencing reads in FASTQ format
--   Maternal short-read Illumina sequencing reads in FASTQ format
+-   Collection of Hifi long reads [fastq] (Collection)
+-   Paternal short-read Illumina sequencing reads [fastq] (Collection)
+-   Maternal short-read Illumina sequencing reads [fastq] (Collection)
 
 ### Outputs
 

workflows/VGP-assembly-v2/kmer-profiling-hifi-trio-VGP2/kmer-profiling-hifi-trio-VGP2-tests.yml

@@ -0,0 +1,73 @@
+- doc: Test outline for kmer-profiling-hifi-trio-VGP2.ga
+  job:
+    Maternal reads:
+      class: Collection
+      collection_type: list
+      elements:
+      - class: File
+        identifier: forward
+        location: https://zenodo.org/record/6603774/files/paternal.fastq?download=1
+        filetype: fastqsanger
+      - class: File
+        identifier: reverse
+        location: https://zenodo.org/record/6603774/files/paternal.fastq?download=1
+        filetype: fastqsanger
+    Paternal reads:
+      class: Collection
+      collection_type: list
+      elements:
+      - class: File
+        identifier: forward
+        location: https://zenodo.org/record/6603774/files/maternal.fastq?download=1
+        filetype: fastqsanger
+      - class: File
+        identifier: reverse
+        location: https://zenodo.org/record/6603774/files/maternal.fastq?download=1
+        filetype: fastqsanger
+    Pacbio Hifi reads:
+      class: Collection
+      collection_type: list
+      elements:
+      - class: File
+        identifier: pacbio_dataset
+        location: https://zenodo.org/record/6603774/files/child.fastq?download=1
+        filetype: fastqsanger
+    'K-mer length': 9
+    Ploidy: 1
+  outputs:
+    GenomeScope linear plot (maternal):
+      class: File
+      file: test-data/GenomeScope_Linear_plot_maternal.png
+      compare: sim_size
+      delta: 15000
+    GenomeScope linear plot (paternal):
+      class: File
+      file: test-data/GenomeScope_Linear_plot_paternal.png
+      compare: sim_size
+      delta: 15000
+    GenomeScope linear plot (child):
+      class: File
+      file: test-data/GenomeScope_Linear_plot_child.png
+      compare: sim_size
+      delta: 15000
+    GenomeScope summary (child):
+      asserts:
+        has_text:
+          text: '39,419 bp'
+        has_text:
+          text: '43,763 bp'
+    'Meryl database : Child':
+      asserts:
+        has_size:
+          value: 205051
+          delta: 1000
+    'Meryl database : paternal':
+      asserts:
+        has_size:
+          value: 40338
+          delta: 1000
+    'Meryl database : maternal':
+      asserts:
+        has_size:
+          value: 49534
+          delta: 1000