comparison linelisting.py @ 2:141cbefca027 draft default tip

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

1:8a4ee4be0b7e

    numPos = len(positions)
    empty_indicesLine = ',' * numPos
    #print column headers for sample sequences
    row4 = "Sequence Name,N,Clade,Extra Substitutions," + empty_indicesLine + "Number of Amino Acid Substitutions in Antigenic Sites,% Identity of Antigenic Site Residues\n"
    lineListFile.write(row4)
    print ("\nREFERENCE ANTIGENIC MAP: '%s' (%i amino acids)" % (record.id, len(record)))

with open(cladeDefinitionFile,'r') as cladeFile:
    """Read clade definition file and store clade names in a list."""
    #remove whitespace from the end of each line and split elements at commas
    for line in cladeFile:

    for record in SeqIO.parse(extrAntigMapFile, "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 "\nCOMPARING %i flu antigenic map sequences to the reference..." % len(seqList)
#parse each antigenic map sequence object
for record in seqList:
    #assign Sequence to dictionaries according to location in name
    sort_by_location(record)
#sort dictionary keys that access province-segregated lists
sorted_segregated_list_keys = sorted(segregated_lists.keys())
print "\nSequence Lists Sorted by Province: "
#process each province-segregated SeqRecord list
for listname in sorted_segregated_list_keys:
    #acesss list of sequences by the listname key
    a_list = segregated_lists[listname]
    # sort original SeqRecords by record id (i.e. name)

    for record in a_list:
        #replace matching amino acid symbols with dots
        rec = replace_matching_aa_with_dot(record)
        mod_list.append(rec) #populate a list of modified records
    segregated_lists[listname] =  mod_list
    print "\n'%s' List (Amino Acids identical to Reference Masked): " % (listname)
    #output the list to csv as non-aggregated linelist
    output_linelist(segregated_lists[listname])

extrAntigMapFile.close()
refMapFile.close()

2:141cbefca027

    numPos = len(positions)
    empty_indicesLine = ',' * numPos
    #print column headers for sample sequences
    row4 = "Sequence Name,N,Clade,Extra Substitutions," + empty_indicesLine + "Number of Amino Acid Substitutions in Antigenic Sites,% Identity of Antigenic Site Residues\n"
    lineListFile.write(row4)
    print("\nREFERENCE ANTIGENIC MAP: '%s' (%i amino acids)" % (record.id, len(record)))

with open(cladeDefinitionFile,'r') as cladeFile:
    """Read clade definition file and store clade names in a list."""
    #remove whitespace from the end of each line and split elements at commas
    for line in cladeFile:

    for record in SeqIO.parse(extrAntigMapFile, "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("\nCOMPARING %i flu antigenic map sequences to the reference..." % len(seqList))
#parse each antigenic map sequence object
for record in seqList:
    #assign Sequence to dictionaries according to location in name
    sort_by_location(record)
#sort dictionary keys that access province-segregated lists
sorted_segregated_list_keys = sorted(segregated_lists.keys())
print("\nSequence Lists Sorted by Province: ")
#process each province-segregated SeqRecord list
for listname in sorted_segregated_list_keys:
    #acesss list of sequences by the listname key
    a_list = segregated_lists[listname]
    # sort original SeqRecords by record id (i.e. name)

    for record in a_list:
        #replace matching amino acid symbols with dots
        rec = replace_matching_aa_with_dot(record)
        mod_list.append(rec) #populate a list of modified records
    segregated_lists[listname] =  mod_list
    print("\n'%s' List (Amino Acids identical to Reference Masked): " % (listname))
    #output the list to csv as non-aggregated linelist
    output_linelist(segregated_lists[listname])

extrAntigMapFile.close()
refMapFile.close()