RECoVERY 3.3

RECoVGISAID/zzz_gisaid_uploader.authtoken

@@ -0,0 +1 @@
+{"CoV": "cid-da630018ba06m/EUEURPVKOYLHBNJMPLPGOIQQLTHINKRQGSTOFTHYEGNWRJGXKETAWDWPWCBARFVPCXMOCZYQOBIMSPAFLBJVJQORZQKLIUIXSZDSFHVTHIBVOFUMBVIRNJEAWJYBZPHA"}

RECoVJ/VOCLineages

@@ -1,6 +1,11 @@
 B.1.1.7+E484K
 B.1.351
 P.1
+B.1.617
 B.1.617.1
 B.1.617.2
-B.1.617.3
+B.1.617.3
+B.1.620
+B.1.621
+B.1.622
+B.1.623

RECoVL/recovl.xml

@@ -12,8 +12,7 @@
     #import subprocess
     #set $library = $subprocess.getoutput('cat ' + str($librarytype))
     #if $library == "sang":
-      python 
-      $__tool_directory__/RECoVL.py --variants $variants --strain $strain --lineage $lineage
+      pangolin --min-length 1000 $consensus --outfile $lineage
     #else:
       pangolin --min-length 10000 $consensus --outfile $lineage
     #end if  

tools/ivar_covid_consensus.xml

@@ -1,4 +1,4 @@
-<tool id="ivar_covid_consensus" name="ivar covid consensus" version="3.2+galaxy0">
+<tool id="ivar_covid_consensus" name="ivar covid consensus" version="3.3+galaxy0">
     <description>Call consensus from aligned BAM file</description>
     <requirements>
       <requirement type="package" version="1.2">ivar</requirement>
@@ -29,7 +29,7 @@
         <param name="uploaded_fasta" type="data" format="fasta" label="Uploaded fasta file" />
     </inputs>
     <outputs>
-        <data name="consensus" format="fasta" label="${tool.name} on ${on_string} Consensus" from_work_dir="consensus.fa"/>
+        <data name="first_consensus" format="fasta" label="${tool.name} on ${on_string} first_consensus" from_work_dir="consensus.fa"/>
     </outputs>
     <citations>
       <citation type="doi">10.1186/s13059-018-1618-7</citation>

tools/remove_aa_artifact.py

@@ -20,12 +20,20 @@
     'TAC':'Y', 'TAT':'Y', 'TAA':'_', 'TAG':'_',
     'TGC':'C', 'TGT':'C', 'TGA':'_', 'TGG':'W'}
 
-def finding_errors(err):
+def finding_errors(positions):
     success='NOT_SUCCESS'
     errors={'FRAME_SHIFT','CHROMOSOME_LARGE_DELETION','CODON_CHANGE','CODON_INSERTION','CODON_CHANGE_PLUS_CODON_INSERTION','CODON_DELETION','CODON_CHANGE_PLUS_CODON_DELETION','CODON_INSERTION','CODON_CHANGE_PLUS_CODON_INSERTION','STOP_GAINED', '?', '*', 'STOP_GAINED'}
-    for c in errors:
-        if err.find(c)!=-1:
-            success = 'SUCCESS'
+    degeneration={"R","D","M","N","S","K","W","H","B","V","Y","N"}
+    for error in errors:
+        for p in positions:
+            if p.find(error)!=-1:
+                success = 'SUCCESS'
+                return success
+    for deg in degeneration:
+        for p in positions:
+            if p==deg:
+                success = 'SUCCESS'
+                return success
     return success
 
 def getAABase(AA):
@@ -49,7 +57,7 @@ def __main__():
     read_csv2=[]
     read_csv2.append(['Gene', 'Position', 'Reference', 'Alternative', 'Mutation type', 'Codon change', 'Amino Acid Effect'])
     for line in read_csv[1:]:
-        if len(line)<=8:
+        if len(line)<=8 and line[3]!='N':
             del line[4]
             read_csv2.append(line)
 
@@ -62,25 +70,26 @@ def __main__():
             riga=''
             non_trovato=0
             if read_csv2[index][1]!=read_csv2[index+1][1]:
+                position = [read_csv2[index][3], read_csv2[index][4], read_csv2[index][6], read_csv2[index + 1][3], read_csv2[index + 1][4], read_csv2[index + 1][6]]
                 if finding_errors(read_csv2[index][4])=='NOT_SUCCESS' and finding_errors(read_csv2[index+1][4])=='NOT_SUCCESS':
-                    if finding_errors(read_csv2[index][6])=='NOT_SUCCESS' and finding_errors(read_csv2[index+1][6])=='NOT_SUCCESS':
+                    if finding_errors(position)=='NOT_SUCCESS':
                         if aa==getAABase(read_csv2[index+1][6]) and aa!='' and read_csv2[index][0]==read_csv2[index+1][0]:
                             codone.append(read_csv2[index])
                             codone.append(read_csv2[index+1])
                             index += 1
                             non_trovato+=1
                         if read_csv2[index][1]!=read_csv2[index+1][1]:
-                            if finding_errors(read_csv2[index][4]) == 'NOT_SUCCESS' and finding_errors(read_csv2[index + 1][4]) == 'NOT_SUCCESS':
-                                if finding_errors(read_csv2[index][6]) == 'NOT_SUCCESS' and finding_errors(read_csv2[index + 1][6]) == 'NOT_SUCCESS':
-                                    if aa==getAABase(read_csv2[index+1][6]) and aa!='' and read_csv2[index][0]==read_csv2[index+1][0]:
-                                        codone.append(read_csv2[index+1])
-                                        index += 1
-                                        non_trovato+=1
+                            position = [read_csv2[index][3], read_csv2[index][4], read_csv2[index][6], read_csv2[index + 1][3], read_csv2[index + 1][4], read_csv2[index + 1][6]]
+                            if finding_errors(position) == 'NOT_SUCCESS':
+                                if aa==getAABase(read_csv2[index+1][6]) and aa!='' and read_csv2[index][0]==read_csv2[index+1][0]:
+                                    codone.append(read_csv2[index+1])
+                                    index += 1
+                                    non_trovato+=1
             if non_trovato==0:
                 l=len(read_csv2[index][2])-1
                 if args.minmax == 'max':
                     out_file.write('\t'.join(read_csv2[index])+'\n')
-                elif read_csv2[index][4].find('FRAME_SHIFT')!=0:
+                elif read_csv2[index][4].find('FRAME_SHIFT')==-1:
                     out_file.write('\t'.join(read_csv2[index]) + '\n')
                 elif l%3==0 and l>=3:
                     out_file.write('\t'.join(read_csv2[index]) + '\n')       
@@ -116,9 +125,10 @@ def __main__():
                 mutations=''
                 if gencode.get(codon[0:-4].upper())==gencode.get(codon[4:].upper()):
                     mutations+='SYNONYMOUS_CODING'
+                    riga += cod1 + '\t' + cod2 + '\t' + mutations + '\t' + codon + '\t' + gencode.get(codon[0:-4].upper()) + str(aa) + '\n'
                 else:
                     mutations+='NON_SYNONYMOUS_CODING'
-                riga+=cod1+'\t'+cod2+'\t'+mutations+'\t'+codon+'\t'+gencode.get(codon[0:-4].upper())+aa+gencode.get(codon[4:].upper())+'\n'
+                    riga += cod1 + '\t' + cod2 + '\t' + mutations + '\t' + codon + '\t' + gencode.get(codon[0:-4].upper()) + str(aa) + gencode.get(codon[4:].upper()) + '\n'
                 out_file.write(riga)
             if non_trovato==2:
                 mutations=''
@@ -130,7 +140,8 @@ def __main__():
                 riga+=codone[0][0]+'\t'+codone[0][1]+'\t'+read_csv2[index][5][0:3].upper()+'\t'+newcodon+'\t'+mutations+'\t'+read_csv2[index][5][0:3].upper()+'/'+newcodon+'\t'+gencode.get(read_csv2[index][5][0:3].upper())+aa+gencode.get(newcodon)+'\n'
                 out_file.write(riga)
             index+=1
-        out_file.write('\t'.join(read_csv2[len(read_csv2)-1])+'\n')
+        if read_csv2[len(read_csv2)-1][4].find('FRAME_SHIFT')==-1:
+            out_file.write('\t'.join(read_csv2[len(read_csv2)-1])+'\n')
     else:
         out_file.write('error: no variants detected\n')
     out_file.close

tools/remove_nucleotide_deletions.py

@@ -0,0 +1,76 @@
+#remove deletion/insertion caused by homopolymers and NGS errors
+from Bio import SeqIO
+import subprocess
+import csv
+import sys
+import argparse
+
+def __main__():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--first_consensus', dest='first_consensus', help='first_consensus file')
+    parser.add_argument('--reference_fasta', dest='reference_fasta', help='reference_fasta file')
+    parser.add_argument('--minority_variants', dest='minority_variants', help='minority_variants file')
+    parser.add_argument('--majority_variants', dest='majority_variants', help='majority_variants file')
+    args = parser.parse_args()
+
+    subprocess.call("cat " + args.reference_fasta + " " + args.first_consensus + " > sequences.fasta", shell=True)
+    subprocess.call("mafft --quiet --auto sequences.fasta > all.fasta", shell=True)
+
+    records=list(SeqIO.parse("all.fasta", "fasta"))
+    reference=records[0].seq
+    sequence=records[1].seq
+    name_sequence=records[1].id
+
+    csv_max_file = open(args.majority_variants)
+    read_csv_max = list(csv.reader(csv_max_file, delimiter="\t"))
+    csv_min_file= open(args.minority_variants)
+    read_csv_min = list(csv.reader(csv_min_file, delimiter="\t"))
+
+    read_csv_minmax=[]
+    for line in read_csv_max[1:]:
+        if line[5].find("FRAME_SHIFT")!=-1:
+            read_csv_minmax.append(line)
+    for line in read_csv_min[1:]:
+        if line[5].find("FRAME_SHIFT")!=-1:
+            read_csv_minmax.append(line)
+
+    new_sequence=''
+    i=0
+    lunghezza=len(sequence)-1
+    while i<lunghezza:
+        if sequence[i-1]!='-' and sequence[i+1]!='-' and sequence[i]=='-':
+            position_tab=i
+            for line in read_csv_minmax:
+                if position_tab==int(line[1]) and read_csv_minmax[read_csv_minmax.index(line)][1]!=read_csv_minmax[read_csv_minmax.index(line)-1][1]:
+                    nucleotide=line[2][1].lower()
+                    new_sequence+=nucleotide
+            i+=1
+        else:
+            new_sequence+=sequence[i]
+            i+=1
+
+    i=0
+    lunghezza=len(reference)
+    to_remove=[]
+    while i<lunghezza-1:
+        if reference[i-1]!='-' and reference[i+1]!='-' and reference[i]=='-':
+            to_remove.append(i)
+            i+=1
+        else:
+            i+=1
+
+    if len(to_remove)>=1:
+        to_remove.sort(reverse=True)
+        for i in to_remove:
+            for line in read_csv_minmax:
+                if i == int(line[1]):
+                    new_sequence=new_sequence[:i]+new_sequence[i+1:]
+
+    new_sequence=new_sequence.replace("-","")
+    fasta=open("consensus.fasta", "w")
+    fasta.write(">"+name_sequence+"\n")
+    fasta.write(new_sequence.upper())
+    fasta.close
+
+if __name__ == "__main__":
+    __main__()

tools/remove_nucleotide_deletions.xml

@@ -0,0 +1,29 @@
+<tool id="remove_nucleotide_deletions" name="remove nucleotide deletions" version="3.3">
+    <description>Removes deletions/insertions caused by homopolymers and NGS errors</description>
+    <requirements>
+      <requirement type="package" version="1.79">biopython</requirement>
+      <requirement type="package" version="7.480">mafft</requirement>
+      <yield />
+    </requirements>
+    <command detect_errors="exit_code">
+<![CDATA[
+    python $__tool_directory__/remove_nucleotide_deletions.py 
+	  --first_consensus $first_consensus
+	  --reference_fasta $reference_fasta
+	  --minority_variants $minority_variants
+	  --majority_variants $majority_variants
+]]>
+    </command>
+    <inputs>
+        <param name="first_consensus" type="data" format="fasta" label="first consensus file" />
+		<param name="reference_fasta" type="data" format="fasta" label="Reference fasta file" />
+		<param name="minority_variants" type="data" format="tabular" label="minority variants" />
+		<param name="majority_variants" type="data" format="tabular" label="majority variants" />
+    </inputs>
+    <outputs>
+        <data name="consensus" format="fasta" label="Final consensus" from_work_dir="consensus.fasta" />
+    </outputs>
+</tool>
+
+
+