comparison antigenic_site_extraction.py @ 3:f5522fa90c03 draft default tip

planemo upload for repository https://github.com/Public-Health-Bioinformatics/flu_classification_suite commit 6f09c69c51ec3d6bd7487f55384b97155355c456

2:f879bf22aa12

        positionList = strippedLine.split(',')
    #Convert string items in positionList from strings to int and add to indexArray
    for item in positionList:
        indexArray.append(int(item))
    #print number of amino acids to extract and array to console as user check
    print "Amino Acid positions to extract: %i " %(len(indexArray))
    print indexArray

with open(args.inFileHandle1,'r') as inFile:
    '''Open fasta of amino acid sequences to parse, uppercase and add to protein Sequence list.'''
    #read in Sequences from fasta file, uppercase and add to seqList
    for record in SeqIO.parse(inFile, "fasta", alphabet=IUPAC.protein):
        record = record.upper()
        seqList.append(record) #add Seq to list of Sequences
    #print number of sequences to be process as user check
    print "\n%i flu sequences will be extracted for antigenic sites..." % len(seqList)
    #parse each target sequence object
    for record in seqList:
        extract_aa_from_sequence(record)

#print original and extracted sequence
for x in range(0, len(seqList)):
    print "Original %s: %i amino acids,\tExtracted: %i" % (seqList[x].id,len(seqList[x]),len(extractedSeqList[x]))

#determine if output format is fasta (default) or csv
if args.csv:
    #write csv file of extracted antigenic sits
    for record in extractedSeqList:
        #outFile.write(record.id),","
        name_part = (record.id).rstrip() + ','
        sequence = str(record.seq).strip()
        csv_seq = ",".join(sequence)
        comma_separated_sequence = name_part + csv_seq + "\n"
        print comma_separated_sequence
        outFile.write(comma_separated_sequence)
else:
    #write fasta file of extracted antigenic sites
    SeqIO.write(extractedSeqList,outFile,"fasta")

3:f5522fa90c03

        positionList = strippedLine.split(',')
    #Convert string items in positionList from strings to int and add to indexArray
    for item in positionList:
        indexArray.append(int(item))
    #print number of amino acids to extract and array to console as user check
    print("Amino Acid positions to extract: %i " %(len(indexArray)))
    print(indexArray)

with open(args.inFileHandle1,'r') as inFile:
    '''Open fasta of amino acid sequences to parse, uppercase and add to protein Sequence list.'''
    #read in Sequences from fasta file, uppercase and add to seqList
    for record in SeqIO.parse(inFile, "fasta", alphabet=IUPAC.protein):
        record = record.upper()
        seqList.append(record) #add Seq to list of Sequences
    #print number of sequences to be process as user check
    print("\n%i flu sequences will be extracted for antigenic sites..." % len(seqList))
    #parse each target sequence object
    for record in seqList:
        extract_aa_from_sequence(record)

#print original and extracted sequence
for x in range(0, len(seqList)):
    print("Original %s: %i amino acids,\tExtracted: %i" % (seqList[x].id,len(seqList[x]),len(extractedSeqList[x])))

#determine if output format is fasta (default) or csv
if args.csv:
    #write csv file of extracted antigenic sits
    for record in extractedSeqList:
        #outFile.write(record.id),","
        name_part = (record.id).rstrip() + ','
        sequence = str(record.seq).strip()
        csv_seq = ",".join(sequence)
        comma_separated_sequence = name_part + csv_seq + "\n"
        print(comma_separated_sequence)
        outFile.write(comma_separated_sequence)
else:
    #write fasta file of extracted antigenic sites
    SeqIO.write(extractedSeqList,outFile,"fasta")