update tools

Delphine-L · Dec 13, 2024 · e819910 · e819910
1 parent 4be69db
commit e819910
Show file tree

Hide file tree

Showing 3 changed files with 52 additions and 25 deletions.
diff --git a/...s/VGP-assembly-v2/Assembly-Hifi-HiC-phasing-VGP4/Assembly-Hifi-HiC-phasing-VGP4-tests.yml b/...s/VGP-assembly-v2/Assembly-Hifi-HiC-phasing-VGP4/Assembly-Hifi-HiC-phasing-VGP4-tests.yml
@@ -1,13 +1,21 @@
 - doc: Test outline for Assembly-Hifi-HiC-phasing-VGP4
   job:
-    HiC forward reads:
-      class: File
-      location: https://zenodo.org/records/10068595/files/HiC%20forward%20reads.fastqsanger.gz?download=1
-      filetype: fastqsanger.gz
-    HiC reverse reads:
-      class: File
-      location: https://zenodo.org/records/10068595/files/HiC%20reverse%20reads.fastqsanger.gz?download=1
-      filetype: fastqsanger.gz
+    Hi-C Forward reads:
+      class: Collection
+      collection_type: list
+      elements:
+      - class: File
+        identifier: HiC-Forward-reads
+        location: https://zenodo.org/records/10068595/files/HiC%20forward%20reads.fastqsanger.gz?download=1
+        filetype: fastqsanger.gz
+    Hi-C Reverse reads:
+      class: Collection
+      collection_type: list
+      elements:
+      - class: File
+        identifier: HiC-Reverse-reads
+        location: https://zenodo.org/records/10068595/files/HiC%20reverse%20reads.fastqsanger.gz?download=1
+        filetype: fastqsanger.gz
     Genomescope Model Parameters:
       class: File
       path: test-data/Genomescope Model Parameters.tabular
@@ -20,7 +28,7 @@
       class: File
       location: https://zenodo.org/records/10068595/files/Meryl%20Database.meryldb?download=1
       filetype: meryldb
-    Pacbio Reads Collection:
+    Pacbio Reads:
       class: Collection
       collection_type: list
       elements:
@@ -33,26 +41,27 @@
     Name for Haplotype 2: Hap2
     Homozygous Read Coverage: null
     Database for Busco Lineage: v5
+    Trim Hi-C reads?: false
   outputs:
-    Hifiasm HiC hap1:
-      assert: 
-        has_n_line:
-          n: 168
+    Hifiasm Hi-C hap1:
+      asserts: 
+        has_n_lines:
+          n: 114
     Estimated Genome size: 2288021
     Busco Summary Hap1:
       asserts:
         has_text: 
-          text: "C:1.0%[S:1.0%,D:0.0%],F:0.4%,M:98.6%,n:3354"
+          text: "C:0.8%[S:0.8%,D:0.0%],F:0.3%,M:98.9%,n:3354"
     Nx Plot:
       asserts:
         has_size:
           value: 65000
           delta: 10000
     usable hap1 gfa:
-      assert: 
-        has_n_line:
-          n: 173
+      asserts: 
+        has_n_lines:
+          n: 119
     Assembly statistics for Hap1 and Hap2:
       asserts:
         has_text: 
-          text: "# scaffolds	72	35"
+          text: "# scaffolds	57	51"
diff --git a/workflows/VGP-assembly-v2/Assembly-Hifi-HiC-phasing-VGP4/CHANGELOG.md b/workflows/VGP-assembly-v2/Assembly-Hifi-HiC-phasing-VGP4/CHANGELOG.md
@@ -1,5 +1,21 @@
 # Changelog
 
+## [0.2.3] 2024-12-13
+
+### Changes
+
+- Hi-C inputs are now entered as collections instead of single datasets
+- Add optional trimming of Hi-C reads
+
+### Automatic update
+- `toolshed.g2.bx.psu.edu/repos/devteam/column_maker/Add_a_column1/2.0` was updated to `toolshed.g2.bx.psu.edu/repos/devteam/column_maker/Add_a_column1/2.1`
+- `toolshed.g2.bx.psu.edu/repos/iuc/multiqc/multiqc/1.11+galaxy1` was updated to `toolshed.g2.bx.psu.edu/repos/iuc/multiqc/multiqc/1.24.1+galaxy0`
+- `toolshed.g2.bx.psu.edu/repos/bgruening/gfastats/gfastats/1.3.6+galaxy0` was updated to `toolshed.g2.bx.psu.edu/repos/bgruening/gfastats/gfastats/1.3.9+galaxy1`
+- `toolshed.g2.bx.psu.edu/repos/iuc/busco/busco/5.5.0+galaxy0` was updated to `toolshed.g2.bx.psu.edu/repos/iuc/busco/busco/5.8.0+galaxy0`
+- `toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_cut_tool/9.3+galaxy1` was updated to `toolshed.g2.bx.psu.edu/repos/bgruening/text_processing/tp_cut_tool/9.3+galaxy2`
+- `toolshed.g2.bx.psu.edu/repos/bgruening/hifiasm/hifiasm/0.19.9+galaxy0` was updated to `toolshed.g2.bx.psu.edu/repos/bgruening/hifiasm/hifiasm/0.20.0+galaxy0`
+
+
 ## [0.2.2] 2024-08-07
 
 - Expose parameter: Busco lineage database

diff --git a/workflows/VGP-assembly-v2/Assembly-Hifi-HiC-phasing-VGP4/README.md b/workflows/VGP-assembly-v2/Assembly-Hifi-HiC-phasing-VGP4/README.md
@@ -5,8 +5,8 @@ Generate phased assembly based on PacBio Hifi Reads using HiC data from the same
 ## Inputs
 
 1. Hifi long reads [fastq]
-2. HiC forward reads (if multiple input files, concatenated in same order as reverse reads) [fastq]
-3. HiC reverse reads (if multiple input files, concatenated in same order as forward reads) [fastq]
+2. Collection of Hi-C forward reads [fastq]
+3. Collection of Hi-C reverse reads [fastq]
 4. K-mer database [meryldb]
 5. Genome profile summary generated by Genomescope [txt]
 6. Name of first assembly
@@ -16,8 +16,10 @@ Generate phased assembly based on PacBio Hifi Reads using HiC data from the same
 
 1. Haplotype 1 assembly ([fasta] and [gfa])
 2. Haplotype 2 assembly ([fasta] and [gfa])
-3. QC: BUSCO report for both assemblies
-4. QC: Merqury report for both assemblies
-5. QC: Assembly statistics for both assemblies
-6. QC: Nx plot for both assemblies
-7. QC: Size plot for both assemblies
+3. Trimmed Hi-C forward reads collection
+4. Trimmed Hi-C reverse reads collection
+5. QC: BUSCO report for both assemblies
+6. QC: Merqury report for both assemblies
+7. QC: Assembly statistics for both assemblies
+8. QC: Nx plot for both assemblies
+9. QC: Size plot for both assemblies