def ReadReferenceFromFile(File):
'''Read in all sequences in the reference file; check there is only one.'''
AllSequences, ReferenceLength = ReadSequencesFromFile(File,False)
if len(AllSequences) != 1:
print('Found', len(AllSequences), 'sequences in', ReferenceFile+\
'; expected 1.\nQuitting.', file=sys.stderr)
exit(1)
return AllSequences.items(), ReferenceLength
GapChars = ['-','.','?'] # Check this file is called from the command line with one argument if len(sys.argv[1:]) != 1: print 'Incorrect number of arguments given.' print 'Usage:\n', sys.argv[0], 'NameOfYourFastaFile.fasta' exit(1) DataFile = sys.argv[1] # Check that the argument exists and is a file if not os.path.isfile(DataFile): print DataFile, 'does not exist or is not a file.' exit(1) # Read in all the sequences as a dictionary AllSequences, SequenceLength = ReadSequencesFromFile(DataFile) SequenceNames = AllSequences.keys() sequences = AllSequences.values() NumSequences = len(AllSequences) DataFromAllPositions = [] SetOfAllBasesEncountered = [] # For brevity acgt = ['A','C','G','T'] AllExpectedBases = acgt + IUPACdict.keys() + GapChars
for GapChar in GapChars:
if GapChar in PrimerList[i]:
print('SubSeq', PrimerList[i], 'contains a gap. This is unexpected.'+\
'\nQuitting.', file=sys.stderr)
exit(1)
CounterObject = collections.Counter(PrimerList)
DuplicatedPrimers = [i for i in CounterObject if CounterObject[i] > 1]
if len(DuplicatedPrimers) != 0:
for DuplicatedPrimer in DuplicatedPrimers:
print('SubSeq', DuplicatedPrimer, 'was specified twice with the same',\
'option.', file=sys.stderr)
print('Quitting.', file=sys.stderr)
exit(1)
# Read in the sequences from the alignment file (into a dictionary)
SeqDict, AlignmentLength = ReadSequencesFromFile(AlignmentFile)
# Check the chosen reference is in the alignment
if not ChosenRef in SeqDict:
print('Could not find',
ChosenRef,
'in',
AlignmentFile + '.\nQuitting.',
file=sys.stderr)
exit(1)
ChosenRefSeq = SeqDict[ChosenRef]
# Define the set of unique primers, i.e. StartPrimers+EndPrimers but not
# double counting those that appear in both. Record their lengths in a dict.
AllUniquePrimers = StartPrimers + \
[primer for primer in EndPrimers if not primer in StartPrimers]
DuplicatedContigNames = [i for i in CounterObject if CounterObject[i]>1]
if len(DuplicatedContigNames) != 0:
for ContigName in DuplicatedContigNames:
print('Contig name', ContigName, 'was duplicated in the arguments.', \
file=sys.stderr)
print('All contig names should be unique. Exiting.', file=sys.stderr)
exit(1)
# Check the consensus name does not match one fo the contig names.
if ConsensusName != None and ConsensusName in ContigNames:
print('The consensus name should not be the same as one of the contig', \
'names. Quitting.', file=sys.stderr)
exit(1)
# Read in the sequences from the alignment file (into a dictionary)
AllSeqsDict, AlignmentLength = ReadSequencesFromFile(AlignmentFile)
# Check the consensus is found
if ConsensusName != None:
if not ConsensusName in AllSeqsDict:
print(ConsensusName, 'not found in', AlignmentFile + '. Quitting.', \
file=sys.stderr)
exit(1)
ConsensusSeq = AllSeqsDict[ConsensusName]
# Separate sequences into references and contigs
RefDict = {}
ContigDict = {}
for SeqName in AllSeqsDict:
if SeqName in ContigNames:
ContigDict[SeqName] = AllSeqsDict[SeqName]
# Check this file is called from the command line with one argument
if len(sys.argv[1:]) != 1:
print 'Incorrect number of arguments given.'
print 'Usage:\n', sys.argv[0], 'NameOfYourFastaFile.fasta'
exit(1)
DataFile = sys.argv[1]
# Check that the argument exists and is a file
if not os.path.isfile(DataFile):
print DataFile, 'does not exist or is not a file.'
exit(1)
# Read in the sequences as a dictionary. They are (nominally) not aligned.
Aligned=False
SeqDict, FirstSeqLength = ReadSequencesFromFile(DataFile, Aligned)
# We are expecting two sequences.
if len(SeqDict) != 2:
print 'Expected 2 sequences;', DataFile, 'contains', str(len(SeqDict)) +\
'.\nQuitting.'
exit(1)
SeqNames = SeqDict.keys()
Seqs = SeqDict.values()
# If the two sequences are the same length, there is no shuffling to do. Print
# them as they are.
if len(Seqs[0]) == len(Seqs[1]):
for SeqName, seq in SeqDict.items():
print '>'+SeqName
'specified.', file=sys.stderr)
exit(1)
# Rename arguments for brevity / clarity.
MainAlnFile = args.MainAlignmentFile
PairedAlnFile = args.PairedAlignmentFile
ExciseUniqueInsertionsOfRefInMainAlignment = args.excise
# Check that the arguments exist and are files
for InputFile in [MainAlnFile, PairedAlnFile]:
if not os.path.isfile(InputFile):
print(InputFile, 'does not exist or is not a file.', file=sys.stderr)
exit(1)
# Read in the sequences from the main alignment file (into a dictionary)
MainAlnSeqDict, MainAlnSeqLength = ReadSequencesFromFile(MainAlnFile)
MainAlnSeqNames = MainAlnSeqDict.keys()
MainAlnSeqs = MainAlnSeqDict.values()
# Read in the sequences from the paired alignment file
PairedAlnSeqDict, PairedAlnSeqLength = ReadSequencesFromFile(PairedAlnFile)
# Check it has two sequences
if len(PairedAlnSeqDict) != 2:
print('File', PairedAlnFile, 'contains', len(PairedAlnSeqDict),\
'sequences; two were expected.\nQuitting.', file=sys.stderr)
exit(1)
Seq1name, Seq2name = PairedAlnSeqDict.keys()
# Check that one of the sequences is in the main alignment file (the 'Ref')
# and one is not (the 'SeqToAdd').
for GapChar in GapChars:
if GapChar in PrimerList[i]:
print 'Primer', PrimerList[i], 'contains a gap. This is unexpected.'+\
'\nQuitting.'
exit(1)
CounterObject = collections.Counter(PrimerList)
DuplicatedPrimers = [i for i in CounterObject if CounterObject[i]>1]
if len(DuplicatedPrimers) != 0:
for DuplicatedPrimer in DuplicatedPrimers:
print 'Primer', DuplicatedPrimer, 'was specified twice with the same',\
'option.'
print 'Quitting.'
exit(1)
# Read in the sequences from the alignment file (into a dictionary)
SeqDict, AlignmentLength = ReadSequencesFromFile(AlignmentFile)
# Check the chosen reference is in the alignment
if not ChosenRef in SeqDict:
print 'Could not find', ChosenRef, 'in', AlignmentFile+'.\nQuitting.'
exit(1)
ChosenRefSeq = SeqDict[ChosenRef]
# Define the set of unique primers, i.e. StartPrimers+EndPrimers but not
# double counting those that appear in both. Record their lengths in a dict.
AllUniquePrimers = StartPrimers + \
[primer for primer in EndPrimers if not primer in StartPrimers]
NumUniquePrimers = len(AllUniquePrimers)
PrimerLengths = {primer : len(primer) for primer in AllUniquePrimers}
# Finds the position in the alignment, for each primer, after
