add cond to suppress wf and remove empty.sh

Author: KateSakharova

.travis.yml

@@ -8,6 +8,7 @@ services:
 
 env:
   - TOOL="Validate" CONF_SCRIPT="travis/conformance-tests.sh"
+#  - TOOL="SUPPRESS" TEST_SUPPRESS_SUBWF="travis/cwltest.sh"
 
 install:
   - travis/install-nodejs.sh
@@ -19,3 +20,4 @@ before_script:
 
 script:
   - bash ${CONF_SCRIPT}
+#  - bash  ${TEST_SUPPRESS_SUBWF} travis/tests/amplicon-suppress/1.yml

input_examples/amplicon/ERR632171_FASTQ.fasta

@@ -135,14 +135,14 @@ steps:
 
 # gzip embl
   gzipped_embl:
-    run: ../../../../utils/gzip.cwl
+    run: ../../../../utils/pigz/gzip.cwl
     in:
       uncompressed_file: unite_embl/result
     out: [ compressed_file ]
 
 # gzip gbk
   gzipped_gbk:
-    run: ../../../../utils/gzip.cwl
+    run: ../../../../utils/pigz/gzip.cwl
     in:
       uncompressed_file: unite_gbk/result
     out: [ compressed_file ]

tools/Assembly/antismash/chunking_antismash_with_conditionals/antismash_chunking_subwf.cwl

@@ -24,7 +24,7 @@ baseCommand: [ "biom-convert.sh" ]
 
 inputs:
   biom:
-    type: File
+    type: File?
     format: edam:format_3746  # BIOM
     inputBinding:
       prefix: --input-fp

tools/RNA_prediction/biom-convert/biom-convert.cwl

@@ -0,0 +1,131 @@
+#!/usr/bin/python3
+import glob
+import argparse
+import sys
+import os
+from Bio import SeqIO
+import gzip
+import shutil
+
+
+def get_avg_length(masked_its):  # get average length of longest ITS sequences - separated by 'N'
+    if masked_its is not None:
+        if os.path.exists(masked_its):
+            all_lengths = []
+            with gzip.open(masked_its, 'rt') as unzipped_file:
+                for record in SeqIO.parse(unzipped_file, 'fasta'):
+                    sequences = [x for x in record.seq.split('N') if x and x != '']
+                    longest_seq = {'num': 0, 'letters': ''}
+                    for seq in sequences:
+                        length = len(seq)
+                        if length > longest_seq['num']:
+                            longest_seq['num'] = length
+                            longest_seq['letters'] = seq
+                    all_lengths.append(longest_seq['num'])
+            return int(sum(all_lengths) / len(all_lengths))
+        else:
+            return 0
+    else:
+        return 0
+
+
+def hits_to_num_ratio(fasta, input_folder):  # ratio of mapseq hits to number of total seqs LSU/SSU
+    rna_sum, rna_num = [0 for _ in range(2)]
+    rna = os.path.join(input_folder, '*.tsv')
+    if 'empty' not in os.path.relpath(fasta):
+        with open(glob.glob(rna)[0], 'r') as rna_hits:
+            for line in rna_hits:
+                if not line.startswith('#'):
+                    rna_sum += float(line.split('\t')[1])
+        rna_num = len([1 for line in gzip.open(fasta, 'rt') if line.startswith('>')])
+        return float(rna_sum / rna_num)
+    else:
+        return 0
+
+
+def validate_hits(ssu_fasta, lsu_fasta, ssu_folder, lsu_folder, len_avg):  # check length and ratio and assign tag
+    ssu_ratio = hits_to_num_ratio(ssu_fasta, ssu_folder) if ssu_folder is not None else 0
+    lsu_ratio = hits_to_num_ratio(lsu_fasta, lsu_folder) if lsu_folder is not None else 0
+    if len_avg > 200:
+        if ssu_ratio or lsu_ratio > 0.1:
+            return 'both'
+        else:
+            return 'ITS'
+    elif 120 <= len_avg <= 199:
+        if ssu_ratio or lsu_ratio > 0.1:
+            return 'rRNA'
+        else:
+            return 'ITS'
+    else:
+        return 'rRNA'
+
+
+def suppress_dir(flag, lsu, ssu, its, its_file, ssu_file, lsu_file):
+    suppressed_folder = 'suppressed'
+    os.mkdir('suppressed')
+    taxonomy_summary = 'taxonomy-summary'
+    os.mkdir('taxonomy-summary')
+
+    its_filename = os.path.basename(its_file) if its is not None else ''
+    lsu_filename = os.path.basename(lsu_file) if lsu is not None else ''
+    ssu_filename = os.path.basename(ssu_file) if ssu is not None else ''
+
+    # move dir by tag
+    list_folders, list_files = [[] for _ in range(2)]
+    addition = ''
+    for folder, name, cur_file, filename in zip([lsu, ssu, its],
+                                                ['/LSU', '/SSU', '/its'],
+                                                [lsu_file, ssu_file, its_file],
+                                                [lsu_filename, ssu_filename, its_filename]):
+        if folder is not None:
+            if flag == 'ITS':
+                if name == '/its':
+                    list_folders.append((folder, taxonomy_summary + name))
+                    list_files.append((cur_file, filename))
+                else:
+                    list_folders.append((folder, suppressed_folder + name))
+                    list_files.append((cur_file, suppressed_folder))
+            elif flag == 'rRNA':
+                if name == '/its':
+                    list_folders.append((folder, suppressed_folder + name))
+                    list_files.append((cur_file, suppressed_folder))
+                else:
+                    list_folders.append((folder, taxonomy_summary + name))
+                    list_files.append((cur_file, filename))
+            elif flag == 'both':
+                list_folders.append((folder, name))
+                list_files.append((cur_file, filename))
+                addition = taxonomy_summary
+
+    [shutil.copytree(src, addition + dest) for src, dest in list_folders]
+    [shutil.copy(src, dest) for src, dest in list_files]
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description="get average length of ITS sequences and suppress unwanted folders")
+    parser.add_argument("--lsu-file", dest="lsu_file", help="lsu fasta", required=False, default=None)
+    parser.add_argument("--ssu-file", dest="ssu_file", help="ssu fasta", required=False, default=None)
+    parser.add_argument("--its-file", dest="its_file", help="its fasta", required=False, default=None)
+    parser.add_argument("--lsu-dir", dest="lsu_directory", help="directory in path taxonomy-summary/LSU",
+                        required=False, default=None)
+    parser.add_argument("--ssu-dir", dest="ssu_directory", help="directory in path taxonomy-summary/SSU",
+                        required=False, default=None)
+    parser.add_argument("--its-dir", dest="its_directory", help="directory in path taxonomy-summary/its",
+                        required=False, default=None)
+
+
+    if len(sys.argv) < 3:
+        parser.print_help()
+    else:
+        args = parser.parse_args()
+        avg = get_avg_length(args.its_file)
+        print('average ITS length is ' + str(avg))
+        print('suppressing...')
+        suppress_flag = validate_hits(args.ssu_file, args.lsu_file, args.ssu_directory, args.lsu_directory, avg)
+        print(suppress_flag)
+        suppress_dir(suppress_flag, args.lsu_directory, args.ssu_directory, args.its_directory, args.its_file,
+                     args.ssu_file, args.lsu_file)
+        if len(os.listdir('suppressed')) == 0:
+            os.rmdir('suppressed')
+        if len(os.listdir('taxonomy-summary')) == 0:
+            os.rmdir('taxonomy-summary')

tools/mask-for-ITS/its-length-new.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env /hps/nobackup2/production/metagenomics/pipeline/tools-v5/miniconda3-4.6.14/bin/python3
+#!/usr/bin/python3
 import glob
 import argparse
 import sys
@@ -25,7 +25,7 @@ def get_avg_length(masked_its):  # get average length of longest ITS sequences -
     else:
         return 0
 
-def hits_to_num_ratio(fasta, input_folder):  # ratio of mapseq hits to number of total seqs LSU/SSU                 
+def hits_to_num_ratio(fasta, input_folder):  # ratio of mapseq hits to number of total seqs LSU/SSU
     rna_sum, rna_num = [0 for _ in range(2)]
     rna = os.path.join(input_folder, '*.tsv')
     if 'empty' not in os.path.relpath(fasta):
@@ -93,5 +93,4 @@ def suppress_dir(flag, lsu, ssu, its, its_file, ssu_file, lsu_file):
         validate_hits(args.ssu_file, args.lsu_file, args.ssu_directory, args.lsu_directory, avg)
         print('suppressing...')
         suppress_flag = validate_hits(args.ssu_file, args.lsu_file, args.ssu_directory, args.lsu_directory, avg)
-        suppress_dir(suppress_flag, args.lsu_directory, args.ssu_directory, args.its_directory, args.its_file, args.ssu_file, args.lsu_file)
-
+        suppress_dir(suppress_flag, args.lsu_directory, args.ssu_directory, args.its_directory, args.its_file, args.ssu_file, args.lsu_file)

tools/mask-for-ITS/its-length.py

@@ -11,51 +11,49 @@ requirements:
 
 inputs:
     ssu_file:
-      type: File
+      type: File?
       inputBinding:
         prefix: --ssu-file
     lsu_file:
-      type: File
+      type: File?
       inputBinding:
         prefix: --lsu-file
     its_file:
-      type: File
+      type: File?
       inputBinding:
         prefix: --its-file
     lsu_dir:
-      type: Directory
-      default: "LSU"
+      type: Directory?
+      # default: "LSU"
       inputBinding:
         prefix: --lsu-dir
     ssu_dir:
-      type: Directory
-      default: "SSU"
+      type: Directory?
+      # default: "SSU"
       inputBinding:
         prefix: --ssu-dir
     its_dir:
-      type: Directory
-      default: "its"
+      type: Directory?
+      # default: "its"
       inputBinding:
         prefix: --its-dir
 
 
-baseCommand: [its-length.py]
+baseCommand: [ its-length-new.py ]
 stdout: ITS_LENGTH
 
 outputs:
-    stdout: stdout
+    its_length: stdout
     out_tax:
-       type: Directory
+       type: Directory?
        outputBinding:
         glob: "taxonomy-summary"
     out_suppress:
-       type: Directory
+       type: Directory?
        outputBinding:
         glob: "suppressed"
-    out_fastas:
-       type:
-        type: array
-        items: File
+    out_fastas_tax:
+       type: File[]?
        outputBinding:
         glob: "*.fasta.gz"
 

tools/mask-for-ITS/suppress_tax.cwl

@@ -1,18 +1,19 @@
 ssu_file:
   class: File
-  path: SSU.fasta.gz
+  path: test-input/SSU/SSU.fasta.gz
 lsu_file:
   class: File
-  path: LSU.fasta.gz
+  path: test-input/LSU/LSU.fasta.gz
 its_file:
   class: File
-  path: ITS_masked.fasta.gz
+  path: test-input/its/its.fasta.gz
 lsu_dir:
   class: Directory
-  path: taxonomy-summary/LSU
+  path: test-input/LSU
 ssu_dir:
   class: Directory
-  path: taxonomy-summary/SSU
+  path: test-input/SSU
 its_dir:
   class: Directory
-  path: taxonomy-summary/its
+  path: test-input/its
+

tools/mask-for-ITS/suppress_tax_test.yml

@@ -0,0 +1,12 @@
+# Constructed from biom file
+# OTU ID	LSU_rRNA	taxonomy	taxid
+25676	3.0	sk__Eukaryota	2759
+16424	1.0	sk__Eukaryota;k__Fungi	4751
+20472	2.0	sk__Eukaryota;k__Fungi;p__Ascomycota;c__Leotiomycetes	147548
+1400	1.0	sk__Eukaryota;k__Fungi;p__Ascomycota;c__Sordariomycetes	147550
+4544	2.0	sk__Eukaryota;k__Fungi;p__Ascomycota;c__Sordariomycetes;o__Hypocreales	5125
+15497	6.0	sk__Eukaryota;k__Fungi;p__Basidiomycota;c__Agaricomycetes	155619
+2195	1.0	sk__Eukaryota;k__Fungi;p__Mucoromycota;c__Glomeromycetes	214506
+14320	1.0	sk__Eukaryota;k__Fungi;p__Mucoromycota;c__Glomeromycetes;o__Glomerales;f__Glomeraceae;g__Rhizophagus	1129544
+19603	1.0	sk__Eukaryota;k__Fungi;p__Mucoromycota;c__Glomeromycetes;o__Glomerales;f__Glomeraceae;g__Rhizophagus;s__Rhizophagus_intraradices	4876
+17712	3.0	sk__Eukaryota;k__Viridiplantae;p__Streptophyta;c__Magnoliopsida	3398