[FIX] h5-merge

modules/local/h5_combine/main.nf

@@ -10,22 +10,8 @@ process COMBINE_HDF {
 
     script:
         """
-        files=("$h5files")
-
-        first_file="\${files[0]}"
-        output="combined_file.h5"
-
-        echo "copying the first file: \${first_file}"
-        cp "\${first_file}" "\$output"
-
-        # Combine the rest of the files with ptrepack
-        for ((i=1; i<\${#files[@]}; i++)); do
-            current_file="\${files[i]}"
-            echo "Combining with: \$current_file"
-
-            # Use ptrepack to combine files
-            ptrepack --keep-source-filters --propindexes "\${current_file}:/" "\$output:/"
-        done
+        rm -f combined_file.h5
+        h5-merge -vv --out combined_file.h5 $h5files
         """
 
     stub:

subworkflows/local/ancestral_go/main.nf

@@ -1,7 +1,7 @@
 #!/usr/bin/env nextflow
 
 // Modules
-include {HOGPROP, HOGPROP_COLLECT} from "./../../../modules/local/hogprop"
+include {HOGPROP; HOGPROP_COLLECT} from "./../../../modules/local/hogprop"
 
 workflow ANCESTRAL_GO {
     take:

subworkflows/local/extract_fastoma/main.nf

@@ -0,0 +1,31 @@
+
+workflow EXTRACT_FASTOMA {
+    take:
+        proteome_folder
+        base_folder
+
+    main:
+        def summaries = base_folder / "Summaries.drw"
+        def taxonomy = genomes_folder / "taxonomy.sqlite"
+        def splice_data = genomes_folder / "Splicings.drw"
+        CONVERT_GS(genomes_folder, matrix_file, summaries)
+        CONVERT_GS.out.gs_tsv
+            | splitCsv(sep: "\t", header: true)
+            | map { row ->
+                def dbfile = file(row.DBpath)
+                return tuple( row, dbfile )
+                }
+            | transpose
+            | set { convert_jobs }
+        CONVERT_PROTEINS(convert_jobs)
+        CONVERT_OMA_GROUPS(matrix_file)
+        CONVERT_SPLICE_MAP(splice_data)
+        CONVERT_TAXONOMY(CONVERT_GS.out.gs_tsv, taxonomy)
+
+
+    emit:
+        gs_file = CONVERT_GS.out.gs_tsv
+        protein_files = CONVERT_PROTEINS.out.prot_json.collect()
+        tax_tsv = CONVERT_TAXONOMY.out.tax_tsv
+        oma_groups = CONVERT_OMA_GROUPS.out.oma_groups_json
+        splice_json = CONVERT_SPLICE_MAP.out.splice_json