Added SEQKIT_RMDUP to detect duplicate sequence and wrap the fasta to…

… 80 characters
Plant-Food-Research-Open · Sep 29, 2024 · c7ebfdc · c7ebfdc
1 parent 504b3a8
commit c7ebfdc
Show file tree

Hide file tree

Showing 12 changed files with 593 additions and 6 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -52,4 +52,7 @@ jobs:
             -params-file \
             ./tests/${{ matrix.TEST_PARAMS }}/params.json \
             ${{ matrix.OPTION_STUB }} \
-            --outdir ./results
+            --outdir ./results \
+            --max_cpus 2 \
+            --max_memory '6.GB' \
+            --max_time '2.h'
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -29,7 +29,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 20. Added a check for input assemblies. If an assembly is smaller than 1 MB (or 300KB in zipped format), the pipeline errors out before starting the downstream processes [#47](https://github.com/plant-food-research-open/genepal/issues/47)
 21. Now `REPEATMASKER` GFF output is saved via `CUSTOM_RMOUTTOGFF3` [#54](https://github.com/plant-food-research-open/genepal/issues/54)
 22. Added `benchmark` column to the input sheet and used `GFFCOMPARE` to perform benchmarking [#63](https://github.com/plant-food-research-open/genepal/issues/63)
-23. Updated modules and sub-workflows
+23. Added `SEQKIT_RMDUP` to detect duplicate sequence and wrap the fasta to 80 characters
+24. Updated modules and sub-workflows
 
 ### `Fixed`
 

diff --git a/conf/modules.config b/conf/modules.config
@@ -11,6 +11,12 @@
 */
 
 process { // SUBWORKFLOW: PREPARE_ASSEMBLY
+
+    withName: '.*:PREPARE_ASSEMBLY:SEQKIT_RMDUP' {
+        ext.args = '--by-seq --ignore-case -w 80'
+        ext.prefix = { "${meta.id}.seqkit.rmdup" }
+    }
+
     withName: '.*:PREPARE_ASSEMBLY:FASTA_EDTA_LAI:EDTA_EDTA' {
         ext.args = [
             params.edta_is_sensitive ? "--sensitive 1" :  "--sensitive 0",

diff --git a/modules.json b/modules.json
@@ -185,6 +185,11 @@
                         "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
                         "installed_by": ["modules"]
                     },
+                    "seqkit/rmdup": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "sortmerna": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",

diff --git a/modules/nf-core/seqkit/rmdup/environment.yml b/modules/nf-core/seqkit/rmdup/environment.yml
diff --git a/modules/nf-core/seqkit/rmdup/main.nf b/modules/nf-core/seqkit/rmdup/main.nf
diff --git a/modules/nf-core/seqkit/rmdup/meta.yml b/modules/nf-core/seqkit/rmdup/meta.yml
diff --git a/modules/nf-core/seqkit/rmdup/tests/main.nf.test b/modules/nf-core/seqkit/rmdup/tests/main.nf.test