Merge branch 'localdata' into master

final-workflow-short.yml

@@ -38,46 +38,60 @@ scientific_name: [
 Saccharomyces, #genus
 eubayanus #species
 ]
-#Genomic fasta name and URL
+#Genomic fasta name and URL. Here, URL is for metadata. If no URL is available, add 'NA'
 genome_fasta_name: [
 GCF_001298625.1_SEUB3.0_genomic.fna
 ]
 url_genomic_fasta: [
 https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/298/625/GCF_001298625.1_SEUB3.0/GCF_001298625.1_SEUB3.0_genomic.fna.gz
 ]
+#file needs to be unzipped!!!
+path_genomic_fasta:
+  class: File
+  path: /app/data/GCF_001298625.1_SEUB3.0_genomic.fna
 #Protein fasta name(s) and url(s)
 protein_fasta_name: [
 GCF_001298625.1_SEUB3.0_translated_cds.faa
 ]
 url_protein_fasta: [
 https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/298/625/GCF_001298625.1_SEUB3.0/GCF_001298625.1_SEUB3.0_translated_cds.faa.gz
 ]
+path_protein_fasta:
+  class: File
+  path: /app/data/GCF_001298625.1_SEUB3.0_translated_cds.faa
 #Transcript fasta name and URL
 transcript_fasta_name: [
 GCF_001298625.1_SEUB3.0_rna_from_genomic.fna
 ]
 url_transcript_fasta: [
 https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/298/625/GCF_001298625.1_SEUB3.0/GCF_001298625.1_SEUB3.0_rna_from_genomic.fna.gz
 ]
+path_transcript_fasta:
+  class: File
+  path: /app/data/GCF_001298625.1_SEUB3.0_rna_from_genomic.fna
 #CDS fasta name and URL
 cds_fasta_name: [
 GCF_001298625.1_SEUB3.0_cds_from_genomic.fna
 ]
 url_cds_fasta: [
 https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/298/625/GCF_001298625.1_SEUB3.0/GCF_001298625.1_SEUB3.0_cds_from_genomic.fna.gz
 ]
+path_cds_fasta: 
+  class: File
+  path: /app/data/GCF_001298625.1_SEUB3.0_cds_from_genomic.fna
 #GFF name and URL
-url_genomic_gff: [
-https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/298/625/GCF_001298625.1_SEUB3.0/GCF_001298625.1_SEUB3.0_genomic.gff.gz
-]
+path_genomic_gff:
+  class: File 
+  path: /app/data/GCF_001298625.1_SEUB3.0_genomic.gff
+
 gff_name: [
 GCF_001298625.1_SEUB3.0_genomic.gff
 ]
-gff_release_number: 100
-#-------------------------------------------------------------------------------
-url_md5checksums: [
-https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/298/625/GCF_001298625.1_SEUB3.0/md5checksums.txt
+url_genomic_gff: [
+https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/298/625/GCF_001298625.1_SEUB3.0/GCF_001298625.1_SEUB3.0_genomic.gff.gz
 ]
+gff_release_number: 100
+
 #-------------------------------------------------------------------------------
 deepPATH_genomic_fasta: [
 scaffold #the containing directory for the assembly. Don't change this unless you have to. 

final-workflow.cwl

@@ -13,72 +13,36 @@ inputs:
   hmmerdb_Path_stage: string[]
   tree: string[]
   scientific_name: string[]
-  url_md5checksums: string[]
   deepPATH_genomic_fasta: string[]
-  url_genomic_fasta: string[]
+  path_genomic_fasta: File
   deepPATH_analyses: string[]
-  url_genomic_gff: string[]
+  path_genomic_gff: File
   gff_release_number: int
-  url_protein_fasta: string[]
-  url_transcript_fasta: string[]
-  url_cds_fasta: string[]
+  path_protein_fasta: File
+  path_transcript_fasta: File
+  path_cds_fasta: File
   deepPATH_apollo2_data: string[]
   deepPATH_bigwig: string[]
   organization: string
   accession: string
   link_to_publication: string
+  url_genomic_fasta: string[]
+  url_genomic_gff: string[]
+  url_protein_fasta: string[]
+  url_transcript_fasta: string[]
+  url_cds_fasta: string[]
 
 steps:
   #step1 
-  download:
-    run: flow_download/workflow.cwl
-    in:
-      url_md5checksums: url_md5checksums
-      url_genomic_fasta: url_genomic_fasta
-      url_genomic_gff: url_genomic_gff
-      url_protein_fasta: url_protein_fasta
-      url_transcript_fasta: url_transcript_fasta
-      url_cds_fasta: url_cds_fasta
-    out:
-      [OUT_md5checksums,   #'*.txt'
-       OUT_genomic_fasta,  #'*.gz'
-       OUT_genomic_gff,    #'*.gz'
-       OUT_protein_fasta,            #'*.gz'
-       OUT_transcript_fasta,         #'*.gz'
-       OUT_cds_fasta]                #'*.gz'
-  #step2  
-  md5checksums:
-    run: flow_md5checksums/workflow.cwl
-    in:
-      in_md5checksums: download/OUT_md5checksums
-      in_genomic_fasta: download/OUT_genomic_fasta
-      in_genomic_gff: download/OUT_genomic_gff
-      in_protein_fasta: download/OUT_protein_fasta
-      in_transcript_fasta: download/OUT_transcript_fasta
-      in_cds_fasta: download/OUT_cds_fasta
-    out:
-      [
-       OUT_extract,  #'*.txt2', extracted from *.txt
-       OUT_check,    #'*.log', log file for execution of md5sum -c
-       OUT_genomic_fasta, #'*.fa, '*.fna', '*.faa'
-       OUT_genomic_gff,   #'*.gff', '*.gff3'
-       OUT_protein_fasta,
-       OUT_transcript_fasta, 
-       OUT_cds_fasta
-      ]
-
-  #verify:
-  #fasta_diff,gff3_QC......
-  #step3
   apollo2_data_processing:
     run: flow_apollo2_data_processing/processing/workflow.cwl
     in:
       tree: tree
       scientific_name: scientific_name
       gff_release_number: gff_release_number
       url_genomic_gff: url_genomic_gff
-      in_fasta: md5checksums/OUT_genomic_fasta
-      in_gff: md5checksums/OUT_genomic_gff
+      in_fasta: path_genomic_fasta
+      in_gff: path_genomic_gff
     out:
       [OUT_2bi,
       OUT_seq,
@@ -90,7 +54,7 @@ steps:
       OUT_trackList_json,
       OUT_trackList_json_bak,
       ]
-  #step4
+  #step2
   create_assembly_readme:
     run: flow_create_readme/readme-assembly-workflow.cwl
     in: 
@@ -101,7 +65,7 @@ steps:
       accession: accession
       link_to_publication: link_to_publication
     out: [readme_file]
-  #step5
+  #step3
   create_genePrediction_readme:
     run: flow_create_readme/readme-genePrediction-workflow.cwl
     in:
@@ -113,25 +77,22 @@ steps:
       url_transcript_fasta: url_transcript_fasta
       link_to_publication: link_to_publication
     out: [readme_file] 
-  #step6     
+  #step4     
   dispatch:
     run: flow_dispatch/workflow.cwl
     in:
       PATH: PATH
       tree: tree
       deepPATH_genomic_fasta: deepPATH_genomic_fasta
-      in_genomic_fasta: md5checksums/OUT_genomic_fasta
+      in_genomic_fasta: path_genomic_fasta
       deepPATH_analyses: deepPATH_analyses
-      in_genomic_gff: md5checksums/OUT_genomic_gff
+      in_genomic_gff: path_genomic_gff
       #
-      in_protein_fasta: md5checksums/OUT_protein_fasta
-      in_transcript_fasta: md5checksums/OUT_transcript_fasta
-      in_cds_fasta: md5checksums/OUT_cds_fasta
+      in_protein_fasta: path_protein_fasta
+      in_transcript_fasta: path_transcript_fasta
+      in_cds_fasta: path_cds_fasta
       in_assembly_readme: create_assembly_readme/readme_file
       in_genePrediction_readme: create_genePrediction_readme/readme_file
-      in_md5checksums: download/OUT_md5checksums
-      in_extract: md5checksums/OUT_extract
-      in_check: md5checksums/OUT_check
       #
       deepPATH_apollo2_data: deepPATH_apollo2_data
       deepPATH_bigwig: deepPATH_bigwig
@@ -147,6 +108,4 @@ steps:
     out:
       [out_dummy]
 
-
-
 outputs:  []

flow_dispatch/2other_species/workflow.cwl

@@ -16,7 +16,7 @@ inputs:
   in_genomic_fasta: File
   deepPATH_analyses: string[]
   in_genomic_gff: File
-  in_protein_fasta: File[]
+  in_protein_fasta: File
   in_transcript_fasta: File
   in_cds_fasta: File
   in_assembly_readme: File
@@ -55,7 +55,6 @@ steps:
     out: []
   cp_protein_fasta:
     run: cp_file_4_annotation.cwl
-    scatter: in_data
     in:
       PATH: PATH
       deepPATH_1: deepPATH_genomic_fasta

flow_dispatch/workflow.cwl

@@ -15,14 +15,11 @@ inputs:
   deepPATH_analyses: string[]
   in_genomic_gff: File
   #
-  in_protein_fasta: File[]
+  in_protein_fasta: File
   in_transcript_fasta: File
   in_cds_fasta: File
   in_assembly_readme: File
   in_genePrediction_readme: File
-  in_md5checksums: File
-  in_extract: File
-  in_check: File
   #
   in_2bi: File
   #
@@ -46,7 +43,7 @@ steps:
       tree: tree
       deepPATH_genomic_fasta: deepPATH_genomic_fasta
       deepPATH_analyses: deepPATH_analyses
-    out: [out_dummy]  
+    out: [out_dummy]
   #To other_species
   2other_species: 
     run: 2other_species/workflow.cwl
@@ -76,17 +73,6 @@ steps:
       in_gaps_bigwig: in_gaps_bigwig
       in_gc_bigwig: in_gc_bigwig
     out: []
-  #To working_files
-  2working_files:
-    run: 2working_files/workflow.cwl
-    in:
-      in_dummy: setup_folder/out_dummy
-      PATH: PATH
-      tree: tree
-      in_md5checksums: in_md5checksums
-      in_extract: in_extract
-      in_check: in_check
-    out: [] 
   #To blat/db/
   2blat:
     run: 2blat/workflow.cwl