pascal/main.nf edited to extract tarball as nextflow does not support…

… s3 glob support
wsjung · Jan 23, 2024 · 1e422f7 · 1e422f7
1 parent 7be6ed2
commit 1e422f7
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 22 deletions.
diff --git a/modules/local/mmap/mmap/main.nf b/modules/local/mmap/mmap/main.nf
@@ -10,7 +10,6 @@ process MMAP {
     path phenotype_file 
     path pedigree_file
     path covariance_matrix_file
-    val output_dir
 
     output:
     path "*.poly.cov.csv"         , emit: csv

diff --git a/modules/local/pascal/bin/pascal.py b/modules/local/pascal/bin/pascal.py
@@ -17,7 +17,7 @@ def pascal(gwas_file, manhattan_plot_file, gene_annotation, ref_panel, output_fi
 
     #Load reference panel        
     Scorer.load_refpanel(ref_panel, qualityT = None, parallel = 1, keepfile=None)
-    #Scorer.load_refpanel(ref_panel, qualityT = None, parallel = 1, keepfile=None, chrlist=[22]) ## TESTING:: CHR22 ONLY FOR TESTING
+    # Scorer.load_refpanel(ref_panel, qualityT = None, parallel = 1, keepfile=None, chrlist=[1]) ## TESTING:: CHR22 ONLY FOR TESTING
     print("Done importing reference panel")
 
     # import and load genome annotation
@@ -52,19 +52,8 @@ def pascal(gwas_file, manhattan_plot_file, gene_annotation, ref_panel, output_fi
     parser.add_argument('--output_file')
 
     args = parser.parse_args()
-    #print(args)
     pascal(gwas_file = args.gwas_file, manhattan_plot_file = args.manhattan_plot_file, gene_annotation = args.gene_annotation, ref_panel = args.ref_panel, output_file = args.output_file) 
 
-    ## test
-    #output_file = args.gwas_file
-    #manhattan_plot_file = os.path.splitext(args.gwas_file)[0] + "_mp.png"
-    # print(args.output_file)
-    # print(args.manhattan_plot_file)
-    # with open(args.output_file, "w") as f:
-    #   f.write("this is the output file")
-    # with open(args.manhattan_plot_file, "w") as f:
-    #   f.write("this is the manhattan plot file")
-
     print("done")
 
 

diff --git a/modules/local/pascal/main.nf b/modules/local/pascal/main.nf
@@ -8,32 +8,35 @@ process PASCAL {
     input:
     path gwas_file
     path gene_annotation
-    val ref_panel
-    val output_file
-    val manhattan_plot_file
+    path ref_panel
 
     output:
-    path("${output_file}"), emit: tsv
-    path("${manhattan_plot_file}"), emit: manhattan
-    path("versions.yml"), emit: versions
+    path("pascal_out.tsv")        , emit: tsv
+    path("manhattan_plot.png")    , emit: manhattan
+    path("versions.yml")          , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
+    def ref_panel_name = ref_panel.getSimpleName() // get filename without ext
 
     // TODO nf-core: Where possible, a command MUST be provided to obtain the version number of the software e.g. 1.10
     //               If the software is unable to output a version number on the command-line then it can be manually specified
     //               e.g. https://github.com/nf-core/modules/blob/master/modules/nf-core/homer/annotatepeaks/main.nf
     //               Each software used MUST provide the software name and version number in the YAML version file (versions.yml)
+
+    // extract tarball (nextflow does not support s3 glob)
     """
+    tar -xzvf ${ref_panel}
+
     python3 ${moduleDir}/bin/pascal.py \\
       --gwas_file $gwas_file \\
       --gene_annotation $gene_annotation \\
-      --ref_panel $ref_panel \\
-      --manhattan_plot_file $manhattan_plot_file \\
-      --output_file $output_file
+      --ref_panel $ref_panel_name \\
+      --manhattan_plot_file manhattan_plot.png \\
+      --output_file pascal_out.tsv
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":