def __init__(self, glfo, args):
self.glfo = glfo
self.args = args
self.mfreqer = MuteFreqer(self.glfo,
exclusions=args.region_end_exclusions)
self.reco_total = 0 # total number of recombination events
self.mute_total = 0 # total number of sequences
self.counts = {}
self.counts['all'] = {}
for column in utils.column_dependencies:
self.counts[column] = {}
self.string_columns = set([r + '_gene' for r in utils.regions])
for bound in utils.boundaries:
self.counts[bound + '_insertion_content'] = {
n: 0
for n in utils.nukes
} # base content of each insertion
self.string_columns.add(bound + '_insertion_content')
self.counts['cdr3_length'] = {}
self.counts['seq_content'] = {
n: 0
for n in utils.nukes
} # now I'm adding the aa content, I wish this had nucleotide in the name, but I don't want to change it since it corresponds to a million existing file paths
self.init_aa_stuff()
self.counts['seq_aa_content'] = {a: 0 for a in self.all_aa}
self.string_columns.add('seq_content')
self.string_columns.add('seq_aa_content')
self.no_write_columns = [
'cdr3_length', 'seq_aa_content'
] # don't write these to the parameter dir, since a) cdr3_length is better viewed as an output of more fundamental parameters (gene choice, insertion + deletion lengths) and b) I"m adding them waaay long after the others, and I don't want to add a new file to the established parameter directory structure. (I'm adding these because I want them plotted)
self.columns_to_subset_by_gene = [
e + '_del' for e in utils.all_erosions
] + [b + '_insertion' for b in utils.boundaries]
def __init__(self, germline_seqs): #, base_outdir='', plotdir='', write_parameters=True, plot_parameters=True):
self.reco_total = 0 # total number of recombination events
self.mute_total = 0 # total number of sequences
self.counts = {}
self.counts['all'] = {}
for column in utils.column_dependencies:
self.counts[column] = {}
for bound in utils.boundaries:
self.counts[bound + '_insertion_content'] = {n : 0 for n in utils.nukes} # base content of each insertion
self.counts['seq_content'] = {n : 0 for n in utils.nukes}
self.mutefreqer = MuteFreqer(germline_seqs) #, self.base_outdir, self.plotdir, write_parameters=self.write_parameters, plot_parameters=self.plot_parameters)
def __init__(self, glfo, args):
self.glfo = glfo
self.args = args
self.mfreqer = MuteFreqer(self.glfo)
self.reco_total = 0 # total number of recombination events
self.mute_total = 0 # total number of sequences
self.counts = {}
self.counts['all'] = {}
for column in utils.column_dependencies:
self.counts[column] = {}
self.string_columns = set([r + '_gene' for r in utils.regions])
for bound in utils.boundaries:
self.counts[bound + '_insertion_content'] = {n : 0 for n in utils.nukes} # base content of each insertion
self.string_columns.add(bound + '_insertion_content')
self.counts['seq_content'] = {n : 0 for n in utils.nukes}
self.string_columns.add('seq_content')
self.columns_to_subset_by_gene = [e + '_del' for e in utils.all_erosions] + [b + '_insertion' for b in utils.boundaries]
def __init__(
self, germline_seqs
): #, base_outdir='', plotdir='', write_parameters=True, plot_parameters=True):
self.total = 0
self.counts = {}
self.counts['all'] = {}
for column in utils.column_dependencies:
self.counts[column] = {}
for bound in utils.boundaries:
self.counts[bound + '_insertion_content'] = {
'A': 0,
'C': 0,
'G': 0,
'T': 0
} # base content of each insertion
self.counts['seq_content'] = {'A': 0, 'C': 0, 'G': 0, 'T': 0}
self.mutefreqer = MuteFreqer(
germline_seqs
) #, self.base_outdir, self.plotdir, write_parameters=self.write_parameters, plot_parameters=self.plot_parameters)
