class CounterCompositionNucleotides(Counter):
headers = SequenceProperties.SequencePropertiesNA().getHeaders()
def __init__(self, *args, **kwargs):
Counter.__init__(self, *args, **kwargs)
self.result_class = SequenceProperties.SequencePropertiesNA
assert self.fasta, "Counter requires a genomic sequence"
def count(self, bed):
s = self.fasta.getSequence(bed.contig, "+", bed.start, bed.end)
self.result = self.result_class()
self.result.loadSequence(s)
def __str__(self):
return str(self.result)
class CounterCompositionCpG(CounterCompositionNucleotides):
'''compute CpG frequencies as well as nucleotide frequencies.
Note that CpG density is calculated across the merged exons of a
transcript. Thus, there might be difference between the CpG on a
genomic level and on the transrcipt level depending on how many
genomic CpG are lost across an intron-exon boundary or how many
transcript CpG are created by exon fusion.
'''
headers = SequenceProperties.SequencePropertiesCpg().getHeaders()
def __init__(self, *args, **kwargs):
CounterCompositionNucleotides.__init__(self, *args, **kwargs)
self.result_class = SequenceProperties.SequencePropertiesCpg
def count(self, bed):
s = self.fasta.getSequence(bed.contig, "+", bed.start, bed.end)
self.result = self.result_class()
self.result.loadSequence(s)
def getCounter(section):
if options.seqtype == "na":
if section == "length":
s = SequenceProperties.SequencePropertiesLength()
elif section == "sequence":
s = SequenceProperties.SequencePropertiesSequence()
elif section == "hid":
s = SequenceProperties.SequencePropertiesHid()
elif section == "na":
s = SequenceProperties.SequencePropertiesNA()
elif section == "gaps":
s = SequenceProperties.SequencePropertiesGaps(
options.gap_chars)
elif section == "cpg":
s = SequenceProperties.SequencePropertiesCpg()
elif section == "dn":
s = SequenceProperties.SequencePropertiesDN()
# these sections requires sequence length to be a multiple of 3
elif section == "aa":
s = SequenceProperties.SequencePropertiesAA()
elif section == "degeneracy":
s = SequenceProperties.SequencePropertiesDegeneracy()
elif section == "codon-bias":
s = SequenceProperties.SequencePropertiesBias(reference_codons)
elif section == "codons":
s = SequenceProperties.SequencePropertiesCodons()
elif section == "codon-usage":
s = SequenceProperties.SequencePropertiesCodonUsage()
elif section == "codon-translator":
s = SequenceProperties.SequencePropertiesCodonTranslator()
else:
raise ValueError("unknown section %s" % section)
elif options.seqtype == "aa":
if section == "length":
s = SequenceProperties.SequencePropertiesLength()
elif section == "sequence":
s = SequenceProperties.SequencePropertiesSequence()
elif section == "hid":
s = SequenceProperties.SequencePropertiesHid()
elif section == "aa":
s = SequenceProperties.SequencePropertiesAminoAcids()
else:
raise ValueError("unknown section %s" % section)
return s