Merge pull request #121 from uclahs-cds/czhu-fix-resources

Set `ucla_cds` to `false` as default
uclahs-cds · Nov 15, 2024 · 85bdbf0 · 85bdbf0
2 parents 9753546 + 0e38506
commit 85bdbf0
Show file tree

Hide file tree

Showing 19 changed files with 106 additions and 72 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -14,6 +14,8 @@ This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 - Change to group input VEP files by source.
 - Fix issue when `novel_orf_peptide` and `alt_translation_peptide` are not specified.
 - Fix file name collision of VEP files.
+- Set `ucla_cds` to `false` as default. #120
+- Set file path in test cases to environment variables.
 
 ## 1.0.0 - 2024/04/10
 

diff --git a/README.md b/README.md
@@ -206,6 +206,20 @@ Filter fasta can run separately for variant, noncoding, and alternative translat
 | `keep_peptide_nterm` | Whether to keep the peptide N terminus constant. `str`. Default: 'true' Choices: ['true', 'false'] |
 | `keep_peptide_cterm` | no | Whether to keep the peptide C terminus constant. `str` Default: 'true'. Choices: ['true', 'false'] |
 
+### Resource
+
+`callVariant` uses 1 CPU and 2 GB of memory by default. To adjust resource usage for `callVariant`, add the code block below to the bottom of the config file (after `methods.setup()`).
+
+```nextflow
+process {
+    echo = false
+    withName: 'call_VariantPeptide' {
+        cpus = 8
+        memory = '30 GB'
+    }
+}
+```
+
 ---
 
 ## Outputs

diff --git a/config/default.config b/config/default.config
@@ -6,7 +6,7 @@ params {
 
     max_cpus   = SysHelper.getAvailCpus()
     max_memory = SysHelper.getAvailMemory()
-    ucla_cds = true
+    ucla_cds = false
 
     min_cpus = 1
     min_memory = 1.MB

diff --git a/config/template.config b/config/template.config
@@ -13,3 +13,10 @@ params {
 }
 
 methods.setup()
+
+process {
+    withName: 'call_VariantPeptide' {
+        cpus = 8  // Change it to the desired number of CPUs.
+        memory = '30 GB'  // Change it to the desired memory.
+    }
+}
diff --git a/example.env b/example.env
@@ -0,0 +1,5 @@
+NFT_OUTPUT=
+NFT_TEMP=
+NFT_INDEX_DIR=
+NFT_NOVEL_ORF_PEPTIDE=
+NFT_ALT_TRANSLATION_PEPTIDE=
diff --git a/test/test-integration-entrypoint-gvf/input.csv b/test/test-integration-entrypoint-gvf/input.csv
@@ -1,6 +1,6 @@
 path
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_gSNP.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_gINDEL.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/reditools.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/circ_rna.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/fusion.gvf
+test/files/vep_gSNP.gvf
+test/files/vep_gINDEL.gvf
+test/files/reditools.gvf
+test/files/circ_rna.gvf
+test/files/fusion.gvf
diff --git a/test/test-integration-entrypoint-gvf/test.config b/test/test-integration-entrypoint-gvf/test.config
@@ -6,7 +6,7 @@ params {
     output_dir = "${projectDir}/test/output/test-integration-entrypoint-gvf" as String
     input_csv = "${projectDir}/test/test-integration-entrypoint-gvf/input.csv" as String
     sample_id = 'UCLA0001'
-    index_dir = "${projectDir}/test/files/index" as String
+    index_dir = NFT_INDEX_DIR
     ucla_cds = false
     save_intermediate_files = true
     entrypoint = 'gvf'
@@ -18,8 +18,8 @@ params {
 
     exprs_table = "${projectDir}/test/files/rsem.txt" as String
 
-    novel_orf_peptide = '/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/noncoding_peptides.fasta'
-    alt_translation_peptide = '/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development/unreleased/data/alt_translation.fasta'
+    novel_orf_peptide = NFT_NOVEL_ORF_PEPTIDE
+    alt_translation_peptide = NFT_ALT_TRANSLATION_PEPTIDE
 
     callVariant {
         max_variants_per_node = 7

diff --git a/test/test-integration-entrypoint-parser-multiple-vep/input.csv b/test/test-integration-entrypoint-parser-multiple-vep/input.csv
@@ -1,13 +1,13 @@
 software,alt_splice_type,source,path
-VEP,,Germline,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_snp.txt
-VEP,,Germline,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_indel.txt
-STAR-Fusion,,Fusion,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/star_fusion.txt
-FusionCatcher,,Fusion,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/fusion_catcher.txt
-Arriba,,Fusion,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/arriba.txt
-rMATS,SE,rMATS,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/rmats_se.txt
-rMATS,A5SS,rMATS,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/rmats_a5ss.txt
-rMATS,A3SS,rMATS,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/rmats_a3ss.txt
-rMATS,MXE,rMATS,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/rmats_mxe.txt
-rMATS,RI,rMATS,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/rmats_ri.txt
-CIRCexplorer,,circRNA,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/circexplorer.txt
-REDItools,,RNAEditing,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/reditools_annotated.txt
+VEP,,Germline,test/files/vep_snp.txt
+VEP,,Germline,test/files/vep_indel.txt
+STAR-Fusion,,Fusion,test/files/star_fusion.txt
+FusionCatcher,,Fusion,test/files/fusion_catcher.txt
+Arriba,,Fusion,test/files/arriba.txt
+rMATS,SE,rMATS,test/files/rmats_se.txt
+rMATS,A5SS,rMATS,test/files/rmats_a5ss.txt
+rMATS,A3SS,rMATS,test/files/rmats_a3ss.txt
+rMATS,MXE,rMATS,test/files/rmats_mxe.txt
+rMATS,RI,rMATS,test/files/rmats_ri.txt
+CIRCexplorer,,circRNA,test/files/circexplorer.txt
+REDItools,,RNAEditing,test/files/reditools_annotated.txt
diff --git a/test/test-integration-entrypoint-parser-multiple-vep/test.config b/test/test-integration-entrypoint-parser-multiple-vep/test.config
@@ -6,8 +6,8 @@ params {
     output_dir = "${projectDir}/test/output/test/test-integration-entrypoint-parser-multiple-vep/"  as String
     input_csv = "${projectDir}/test/test-integration-entrypoint-parser-multiple-vep/input.csv" as String
     sample_id = 'UCLA0001'
-    index_dir = "${projectDir}/test/files/index"  as String
-    ucla_cds = true
+    index_dir = NFT_INDEX_DIR
+    ucla_cds = false
     save_intermediate_files = true
     entrypoint = 'parser'
 

diff --git a/test/test-integration-entrypoint-parser/input.csv b/test/test-integration-entrypoint-parser/input.csv
@@ -1,13 +1,13 @@
 software,alt_splice_type,source,path
-VEP,,gSNP,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_snp.txt
-VEP,,gINDEL,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_indel.txt
-STAR-Fusion,,Fusion,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/star_fusion.txt
-FusionCatcher,,Fusion,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/fusion_catcher.txt
-Arriba,,Fusion,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/arriba.txt
-rMATS,SE,rMATS,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/rmats_se.txt
-rMATS,A5SS,rMATS,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/rmats_a5ss.txt
-rMATS,A3SS,rMATS,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/rmats_a3ss.txt
-rMATS,MXE,rMATS,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/rmats_mxe.txt
-rMATS,RI,rMATS,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/rmats_ri.txt
-CIRCexplorer,,circRNA,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/circexplorer.txt
-REDItools,,RNAEditing,/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/reditools_annotated.txt
+VEP,,gSNP,test/files/vep_snp.txt
+VEP,,gINDEL,test/files/vep_indel.txt
+STAR-Fusion,,Fusion,test/files/star_fusion.txt
+FusionCatcher,,Fusion,test/files/fusion_catcher.txt
+Arriba,,Fusion,test/files/arriba.txt
+rMATS,SE,rMATS,test/files/rmats_se.txt
+rMATS,A5SS,rMATS,test/files/rmats_a5ss.txt
+rMATS,A3SS,rMATS,test/files/rmats_a3ss.txt
+rMATS,MXE,rMATS,test/files/rmats_mxe.txt
+rMATS,RI,rMATS,test/files/rmats_ri.txt
+CIRCexplorer,,circRNA,test/files/circexplorer.txt
+REDItools,,RNAEditing,test/files/reditools_annotated.txt
diff --git a/test/test-integration-entrypoint-parser/test.config b/test/test-integration-entrypoint-parser/test.config
@@ -6,8 +6,8 @@ params {
     output_dir = "${projectDir}/test/output/test-integration-entrypoint-parser/"  as String
     input_csv = "${projectDir}/test/test-integration-entrypoint-parser/input.csv" as String
     sample_id = 'UCLA0001'
-    index_dir = "${projectDir}/test/files/index"  as String
-    ucla_cds = true
+    index_dir = NFT_INDEX_DIR
+    ucla_cds = false
     save_intermediate_files = true
     entrypoint = 'parser'
 
@@ -18,8 +18,8 @@ params {
 
     exprs_table = "${projectDir}/test/files/rsem.txt" as String
 
-    novel_orf_peptide = '/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/noncoding_peptides.fasta'
-    alt_translation_peptide = '/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development/unreleased/data/alt_translation.fasta'
+    novel_orf_peptide = NFT_NOVEL_ORF_PEPTIDE
+    alt_translation_peptide = NFT_ALT_TRANSLATION_PEPTIDE
 
     parseREDItools {
         transcript_id_column = 17
@@ -95,4 +95,10 @@ params {
 
 methods.setup()
 
-process.echo = false
+process {
+    echo = false
+    withName: 'call_VariantPeptide' {
+        cpus = 2
+        memory = '3 GB'
+    }
+}
diff --git a/test/test-integration-merge/input.csv b/test/test-integration-merge/input.csv
@@ -1,6 +1,6 @@
 path
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_gSNP.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_gINDEL.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/reditools.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/circ_rna.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/fusion.gvf
+test/files/vep_gSNP.gvf
+test/files/vep_gINDEL.gvf
+test/files/reditools.gvf
+test/files/circ_rna.gvf
+test/files/fusion.gvf
diff --git a/test/test-integration-merge/test.config b/test/test-integration-merge/test.config
@@ -6,7 +6,7 @@ params {
     output_dir = "${projectDir}/test/output/test-integration-merge" as String
     input_csv = "${projectDir}/test/test-integration-merge/input.csv" as String
     sample_id = 'UCLA0001'
-    index_dir = "${projectDir}/test/files/index" as String
+    index_dir = NFT_INDEX_DIR
     ucla_cds = false
     save_intermediate_files = true
     entrypoint = 'gvf'
@@ -18,8 +18,8 @@ params {
 
     exprs_table = "${projectDir}/test/files/rsem.txt" as String
 
-    novel_orf_peptide = '/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/noncoding_peptides.fasta'
-    alt_translation_peptide = '/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development/unreleased/data/alt_translation.fasta'
+    novel_orf_peptide = NFT_NOVEL_ORF_PEPTIDE
+    alt_translation_peptide = NFT_ALT_TRANSLATION_PEPTIDE
 
     callVariant {
         max_variants_per_node = 7

diff --git a/test/test-integration-no-encode/input.csv b/test/test-integration-no-encode/input.csv
@@ -1,6 +1,6 @@
 path
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_gSNP.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_gINDEL.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/reditools.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/circ_rna.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/fusion.gvf
+test/files/vep_gSNP.gvf
+test/files/vep_gINDEL.gvf
+test/files/reditools.gvf
+test/files/circ_rna.gvf
+test/files/fusion.gvf
diff --git a/test/test-integration-no-encode/test.config b/test/test-integration-no-encode/test.config
@@ -6,7 +6,7 @@ params {
     output_dir = "${projectDir}/test/output/test-integration-no-encode" as String
     input_csv = "${projectDir}/test/test-integration-no-encode/input.csv" as String
     sample_id = 'UCLA0001'
-    index_dir = "${projectDir}/test/files/index" as String
+    index_dir = NFT_INDEX_DIR
     ucla_cds = false
     save_intermediate_files = true
     entrypoint = 'gvf'
@@ -18,8 +18,8 @@ params {
 
     exprs_table = "${projectDir}/test/files/rsem.txt" as String
 
-    novel_orf_peptide = '/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/noncoding_peptides.fasta'
-    alt_translation_peptide = '/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development/unreleased/data/alt_translation.fasta'
+    novel_orf_peptide = NFT_NOVEL_ORF_PEPTIDE
+    alt_translation_peptide = NFT_ALT_TRANSLATION_PEPTIDE
 
     callVariant {
         max_variants_per_node = 7

diff --git a/test/test-integration-no-filter/input.csv b/test/test-integration-no-filter/input.csv
@@ -1,6 +1,6 @@
 path
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_gSNP.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_gINDEL.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/reditools.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/circ_rna.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/fusion.gvf
+test/files/vep_gSNP.gvf
+test/files/vep_gINDEL.gvf
+test/files/reditools.gvf
+test/files/circ_rna.gvf
+test/files/fusion.gvf
diff --git a/test/test-integration-no-filter/test.config b/test/test-integration-no-filter/test.config
@@ -6,7 +6,7 @@ params {
     output_dir = "${projectDir}/test/output/test-integration-no-filter" as String
     input_csv = "${projectDir}/test/test-integration-no-filter/input.csv" as String
     sample_id = 'UCLA0001'
-    index_dir = "${projectDir}/test/files/index" as String
+    index_dir = NFT_INDEX_DIR
     ucla_cds = false
     save_intermediate_files = true
     entrypoint = 'gvf'
@@ -17,8 +17,8 @@ params {
 
     database_processing_modes = ['merge', 'plain']
 
-    novel_orf_peptide = '/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/noncoding_peptides.fasta'
-    alt_translation_peptide = '/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development/unreleased/data/alt_translation.fasta'
+    novel_orf_peptide = NFT_NOVEL_ORF_PEPTIDE
+    alt_translation_peptide = NFT_ALT_TRANSLATION_PEPTIDE
 
 
     callVariant {

diff --git a/test/test-integration-no-split/input.csv b/test/test-integration-no-split/input.csv
@@ -1,6 +1,6 @@
 path
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_gSNP.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/vep_gINDEL.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/reditools.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/circ_rna.gvf
-/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/fusion.gvf
+test/files/vep_gSNP.gvf
+test/files/vep_gINDEL.gvf
+test/files/reditools.gvf
+test/files/circ_rna.gvf
+test/files/fusion.gvf
diff --git a/test/test-integration-no-split/test.config b/test/test-integration-no-split/test.config
@@ -6,7 +6,7 @@ params {
     output_dir = "${projectDir}/test/output/test-integration-no-split" as String
     input_csv = "${projectDir}/test/test-integration-no-split/input.csv" as String
     sample_id = 'UCLA0001'
-    index_dir = "${projectDir}/test/files/index" as String
+    index_dir = NFT_INDEX_DIR
     ucla_cds = false
     save_intermediate_files = true
     entrypoint = 'gvf'
@@ -19,8 +19,8 @@ params {
 
     exprs_table = "${projectDir}/test/files/rsem.txt" as String
 
-    novel_orf_peptide = '/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development//unreleased/data/noncoding_peptides.fasta'
-    alt_translation_peptide = '/hot/software/pipeline/pipeline-call-NonCanonicalPeptide/Nextflow/development/unreleased/data/alt_translation.fasta'
+    novel_orf_peptide = NFT_NOVEL_ORF_PEPTIDE
+    alt_translation_peptide = NFT_ALT_TRANSLATION_PEPTIDE
 
 
     callVariant {