Merge pull request #241 from Delphine-L/VGP6

Addition of the workflow to purge duplication from contigs : Vgp6

workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/.dockstore.yml

@@ -0,0 +1,5 @@
+version: 1.2
+workflows:
+- name: main
+  primaryDescriptorPath: /Purge-duplicate-contigs-VGP6.ga
+  subclass: Galaxy

workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/CHANGELOG.md

@@ -0,0 +1,14 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+## [0.1] - 2023-10-26
+
+### Added
+
+- Workflow for purging duplication in contigs

workflows/VGP-assembly-v2/Purge-duplicate-contigs-VGP6/Purge-duplicate-contigs-VGP-tests.yml

@@ -0,0 +1,76 @@
+- doc: Test outline for Purge-duplicate-contigs-VGP6
+  job:
+    Hifiasm Primary assembly:
+      class: File
+      location: https://zenodo.org/records/10047837/files/Hifiasm%20Primary%20assembly.fasta?download=1
+      filetype: fasta
+    Hifiasm Alternate assembly:
+      class: File
+      location: https://zenodo.org/records/10047837/files/Hifiasm%20Alternate%20assembly.fasta?download=1
+      filetype: fasta
+    Meryl Database:
+      class: File
+      location: https://zenodo.org/records/10047837/files/Meryl%20Database.meryldb?download=1
+      filetype: meryldb
+    Genomescope model parameters:
+      class: File
+      location: https://zenodo.org/records/10047837/files/Genomescope%20model%20parameters.tabular?download=1
+      filetype: tabular
+    Estimated genome size - Parameter File:
+      class: File
+      location: https://zenodo.org/records/10047837/files/Estimated%20genome%20size%20-%20Parameter%20File.expression.json?download=1
+      filetype: expression.json
+    Pacbio Reads Collection - Trimmed:
+      class: Collection
+      collection_type: list
+      elements:
+      - class: File
+        identifier: yeast_reads_sub1.fastq.gz
+        location: https://zenodo.org/records/10047837/files/Pacbio%20Reads%20Collection%20-%20Trimmed_yeast_reads_sub1.fastq.gz.fastq.gz?download=1
+    Busco Lineage: vertebrata_odb10
+    Name of primary assembly: Primary
+    Name of alternate assembly: Alternate
+  outputs:
+    Cutoffs for primary assembly:
+      asserts:
+        has_text:
+          text: "1	15	15	16	16	48"
+    Purged Primary Assembly:
+      asserts:
+        has_n_lines:
+          n: 156
+    Purged Primary Assembly (gfa):
+      asserts:
+        has_n_lines:
+          n: 235
+    'Busco on Purged Primary assembly: short summary':
+      asserts:
+        has_text:
+          text: "C:1.1%[S:1.1%,D:0.0%],F:0.5%,M:98.4%,n:3354"
+    Cutoffs for alternate assembly:
+      asserts:
+        has_text:
+          text: "1	15	15	16	16	48"
+    Purged Alternate assembly:
+      asserts:
+        has_n_lines:
+          n: 144
+    Purged Alternate assembly (gfa):
+      asserts:
+        has_n_lines:
+          n: 217
+    Assembly stats on Primary and alternate assemblies:
+      asserts:
+        has_text:
+          text: "# contigs	78	72"
+    Nx Plot:
+      asserts:
+        has_size: 
+          value : 61000
+          delta: 5000
+    'Merqury on Phased assemblies: stats':
+      element_tests:
+        output_merqury.completeness:
+         asserts:
+          has_text:
+            text: "both	all	1212740	1300032	93.2854"