Merge pull request #142 from NAL-i5K/add-annotation

Add functional annotations to gff files
NAL-i5K · May 26, 2022 · e3b7029 · e3b7029
2 parents 677d79c + a193d47
commit e3b7029
Show file tree

Hide file tree

Showing 9 changed files with 194 additions and 36 deletions.
diff --git a/add-annotation/add_annotation.cwl b/add-annotation/add_annotation.cwl
@@ -0,0 +1,31 @@
+#!/usr/bin/env cwl-runner
+
+cwlVersion: v1.2
+class: CommandLineTool
+
+baseCommand: [add_GO-KEGG_to_RefSeq-gff.pl]
+arguments:
+  - position: 1
+    valueFrom: $(inputs.in_GO)
+  - position: 2
+    valueFrom: $(inputs.in_KEGG)
+  - position: 3
+    valueFrom: $(inputs.in_gff)
+  - position: 4
+    valueFrom: $(inputs.in_table)
+
+inputs:
+  in_GO:
+    type: File
+  in_KEGG:
+    type: File
+  in_gff:
+    type: File
+  in_table:
+    type: File
+outputs:  
+  processed_gff:
+    type: stdout
+stdout: $(inputs.in_gff.nameroot).annotated.gff
+
+
diff --git a/final-workflow-short.yml b/final-workflow-short.yml
@@ -90,6 +90,18 @@ gff_name: [
 GCF_001298625.1_SEUB3.0_genomic.gff
 ]
 gff_release_number: 100
+#NCBI table file URL. If no functional annotation is availble, add 'NA' to the URL field.
+url_table_file: [
+https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/298/625/GCF_001298625.1_SEUB3.0/GCF_001298625.1_SEUB3.0_feature_table.txt.gz
+]
+#GO file path. This path will be ignored if the table file URL is 'NA'. The file needs to be unzipped. With singularity, the local file path needs to be in the mounted /work-dir volume
+path_GO:
+  class: File 
+  path: /app/data/GCF_001298625.1_complete.gaf.tsv
+#KEGG file path. This path will be ignored if the table file URL is 'NA'. The file needs to be unzipped. With singularity, the local file path needs to be in the mounted /work-dir volume
+path_KEGG:
+  class: File 
+  path: /app/data/GCF_001298625.1_KOBAS_acc_pathways.tsv
 #-------------------------------------------------------------------------------
 url_md5checksums: [
 https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/298/625/GCF_001298625.1_SEUB3.0/md5checksums.txt

diff --git a/final-workflow.cwl b/final-workflow.cwl
@@ -31,6 +31,9 @@ inputs:
   deepPATH_bigwig: string[]
   organization: string
   link_to_publication: string
+  url_table_file: string[]
+  path_GO: File?
+  path_KEGG: File?
 
 steps:
   #step1 
@@ -48,14 +51,17 @@ steps:
       path_transcript_fasta: path_transcript_fasta
       url_cds_fasta: url_cds_fasta
       path_cds_fasta: path_cds_fasta
+      url_table_file: url_table_file
     out:
       [OUT_md5checksums,   #'*.txt'
        OUT_genomic_fasta,  #'*.gz'
        OUT_genomic_gff,    #'*.gz'
        OUT_protein_fasta,            #'*.gz'
        OUT_transcript_fasta,         #'*.gz'
        OUT_cds_fasta,                #'*.gz'
-       url_string]                
+       OUT_table,                    #'*.gz'
+       url_string
+       ]                
   #step2  
   md5checksums:
     run: flow_md5checksums/workflow.cwl
@@ -66,6 +72,7 @@ steps:
       in_protein_fasta: download/OUT_protein_fasta
       in_transcript_fasta: download/OUT_transcript_fasta
       in_cds_fasta: download/OUT_cds_fasta
+      in_table: download/OUT_table
       path_genomic_fasta: path_genomic_fasta
       path_genomic_gff: path_genomic_gff
       path_protein_fasta: path_protein_fasta
@@ -77,17 +84,32 @@ steps:
       url_protein_fasta: url_protein_fasta
       url_transcript_fasta: url_transcript_fasta
       url_cds_fasta: url_cds_fasta
+      url_table_file: url_table_file
     out:
-      [
-       OUT_extract,  #'*.txt2', extracted from *.txt
+      [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
+       OUT_cds_fasta,
+       OUT_table
       ]
   #step3
+  add_annotation:
+    run: add-annotation/add_annotation.cwl
+    when: $(inputs.url_table_file != "NA")
+    in:
+      url_table_file: url_table_file
+      in_GO: path_GO
+      in_KEGG: path_KEGG
+      in_gff: 
+        source: [md5checksums/OUT_genomic_gff, path_genomic_gff]
+        pickValue: first_non_null
+      in_table: md5checksums/OUT_table
+    out:
+      [processed_gff]
+  #step4
   gaps_or_not:
     run: gaps_or_not.cwl
     in:
@@ -98,7 +120,7 @@ steps:
       [gap_lines]
   #verify:
   #fasta_diff,gff3_QC......
-  #step4
+  #step5
   apollo2_data_processing:
     run: flow_apollo2_data_processing/processing/workflow.cwl
     in:
@@ -110,8 +132,8 @@ steps:
       in_fasta: 
         source: [md5checksums/OUT_genomic_fasta, path_genomic_fasta]
         pickValue: first_non_null
-      in_gff: 
-        source: [md5checksums/OUT_genomic_gff, path_genomic_gff]
+      in_gff:
+        source: [add_annotation/processed_gff, md5checksums/OUT_genomic_gff, path_genomic_gff]
         pickValue: first_non_null
     out:
       [OUT_2bi,
@@ -124,7 +146,7 @@ steps:
       OUT_trackList_json,
       OUT_trackList_json_bak,
       ]
-  #step5
+  #step6
   create_assembly_readme:
     run: flow_create_readme/readme-assembly-workflow.cwl
     in: 
@@ -134,7 +156,7 @@ steps:
       url_genomic_fasta: url_genomic_fasta
       link_to_publication: link_to_publication
     out: [readme_file]
-  #step6
+  #step7
   create_genePrediction_readme:
     run: flow_create_readme/readme-genePrediction-workflow.cwl
     in:
@@ -145,8 +167,13 @@ steps:
       url_cds_fasta: url_cds_fasta
       url_transcript_fasta: url_transcript_fasta
       link_to_publication: link_to_publication
+      original_gff: 
+        source: [md5checksums/OUT_genomic_gff, path_genomic_gff]
+        pickValue: first_non_null
+      processed_gff: add_annotation/processed_gff
+      url_table_file: url_table_file
     out: [readme_file] 
-  #step7
+  #step8
   dispatch:
     run: flow_dispatch/workflow.cwl
     in:
@@ -159,8 +186,8 @@ steps:
         source: [md5checksums/OUT_genomic_fasta, path_genomic_fasta]
         pickValue: first_non_null
       deepPATH_analyses: deepPATH_analyses
-      in_genomic_gff: 
-        source: [md5checksums/OUT_genomic_gff, path_genomic_gff]
+      in_genomic_gff:
+        source: [add_annotation/processed_gff, md5checksums/OUT_genomic_gff, path_genomic_gff]
         pickValue: first_non_null
       #
       in_protein_fasta: 
@@ -189,6 +216,11 @@ steps:
       in_gc_bigwig: apollo2_data_processing/OUT_gc_bigwig
       in_trackList_json: apollo2_data_processing/OUT_trackList_json
       in_trackList_json_bak: apollo2_data_processing/OUT_trackList_json_bak
+      processed_gff: add_annotation/processed_gff
+      original_gff: 
+        source: [md5checksums/OUT_genomic_gff, path_genomic_gff]
+        pickValue: first_non_null
+      url_table_file: url_table_file
     out:
       [out_dummy]
 

diff --git a/flow_create_readme/readme-genePrediction-workflow.cwl b/flow_create_readme/readme-genePrediction-workflow.cwl
@@ -11,6 +11,9 @@ inputs:
   url_cds_fasta: string[]
   url_transcript_fasta: string[]
   link_to_publication: string
+  original_gff: File
+  processed_gff: File?
+  url_table_file: string[]
 
 steps:
   #step1 create_yml_File
@@ -69,12 +72,24 @@ steps:
     out:
       [out_readme_file]  
   #step5 write last line
-  writeLastLine:
+  writeLastLine_v1:
     run: writeLastLine-genePred.cwl
+    when: $(inputs.url_table_file == "NA")
     in: 
+      url_table_file: url_table_file
       readme_file: writeInfo/out_readme_file
     out:
       [out_readme_file]
+  writeLastLine_v2:
+    run: writeLastLine-genePred_annotation.cwl
+    when: $(inputs.url_table_file != "NA")
+    in: 
+      url_table_file: url_table_file
+      readme_file: writeInfo/out_readme_file
+      original_gff: original_gff
+      processed_gff: processed_gff
+    out:
+      [out_readme_file]
 
 outputs:
   readme_file:

diff --git a/flow_create_readme/writeLastLine-genePred_annotation.cwl b/flow_create_readme/writeLastLine-genePred_annotation.cwl
@@ -0,0 +1,31 @@
+#!/usr/bin/env cwl-runner
+
+cwlVersion: v1.2
+class: CommandLineTool
+baseCommand: [bash, -c] 
+requirements:
+  - class: InlineJavascriptRequirement
+  - class: InitialWorkDirRequirement
+    listing:
+      ${
+        var LIST = [(inputs.readme_file)];
+        return LIST;
+      }
+
+inputs:
+  readme_file:
+    type: File
+  original_gff:
+    type: File
+  processed_gff:
+    type: File
+
+arguments:
+  - position: 1
+    valueFrom: "echo -e '\nThe file $(inputs.original_gff.basename) was post-processed to add functional annotations from the AgBase functional annotation pipeline (https://github.com/agbase). The resulting file is: $(inputs.processed_gff.basename). This file was used for all operations within the i5k Workspace.' >> readme.txt"
+
+outputs: 
+  out_readme_file:
+    type: File
+    outputBinding:
+      glob: "readme.txt"
diff --git a/flow_dispatch/2other_species/workflow.cwl b/flow_dispatch/2other_species/workflow.cwl
@@ -15,7 +15,8 @@ inputs:
   deepPATH_genomic_fasta: string[]
   in_genomic_fasta: File
   deepPATH_analyses: string[]
-  in_genomic_gff: File
+  processed_gff: File?
+  original_gff: File
   in_protein_fasta: File
   in_transcript_fasta: File
   in_cds_fasta: File
@@ -34,6 +35,7 @@ inputs:
   deepPATH_bigwig: string[]
   in_gaps_bigwig: File?  # this will be null if there are no gaps
   in_gc_bigwig: File
+  url_table_file: string[]
 
 steps:
   cp_genomic_fasta:
@@ -44,14 +46,25 @@ steps:
       deepPATH: deepPATH_genomic_fasta
       in_data: in_genomic_fasta
     out: []
-  cp_genomic_gff:
+  cp_original_genomic_gff:
     run: cp_file_4_annotation.cwl
     in:
       PATH: PATH
       deepPATH_1: deepPATH_genomic_fasta
       deepPATH_2: deepPATH_analyses
       tree: tree
-      in_data: in_genomic_gff
+      in_data: original_gff
+    out: []
+  cp_annotated_genomic_gff:
+    run: cp_file_4_annotation.cwl
+    when: $(inputs.url_table_file != "NA")
+    in:
+      url_table_file: url_table_file
+      PATH: PATH
+      deepPATH_1: deepPATH_genomic_fasta
+      deepPATH_2: deepPATH_analyses
+      tree: tree
+      in_data: processed_gff
     out: []
   cp_protein_fasta:
     run: cp_file_4_annotation.cwl

diff --git a/flow_dispatch/workflow.cwl b/flow_dispatch/workflow.cwl
@@ -39,6 +39,9 @@ inputs:
   deepPATH_bigwig: string[]
   in_gaps_bigwig: File?  # this will be null if there are no gaps
   in_gc_bigwig: File
+  processed_gff: File?
+  original_gff: File
+  url_table_file: string[]
 
 steps:
   setup_folder:
@@ -60,7 +63,8 @@ steps:
       deepPATH_genomic_fasta: deepPATH_genomic_fasta
       in_genomic_fasta: in_genomic_fasta
       deepPATH_analyses: deepPATH_analyses
-      in_genomic_gff: in_genomic_gff
+      processed_gff: processed_gff
+      original_gff: original_gff
       in_protein_fasta: in_protein_fasta
       in_transcript_fasta: in_transcript_fasta
       in_cds_fasta: in_cds_fasta
@@ -78,11 +82,12 @@ steps:
       deepPATH_bigwig: deepPATH_bigwig
       in_gaps_bigwig: in_gaps_bigwig  # this will be null if there are no gaps
       in_gc_bigwig: in_gc_bigwig
+      url_table_file: url_table_file
     out: []
   #To working_files
   2working_files:
     run: 2working_files/workflow.cwl
-    when: $(inputs.url_string != "NA NA NA NA NA\n" ) 
+    when: $(inputs.url_string != "NA NA NA NA NA NA\n" ) 
     in:
       url_string: url_string
       in_dummy: setup_folder/out_dummy
@@ -118,4 +123,4 @@ steps:
 outputs: 
   out_dummy:
     type: File
-    outputSource: setup_folder/out_dummy
+    outputSource: setup_folder/out_dummy