def geno2geno(args):
""" perform pair-wise FST by population """
genoparser = tabparser.GenotypeLineParser(args)
sample_header = genoparser.get_sample_header()
filename = args.outfile
with open(filename + '.geno.txt',
'wt') as outfile, open(filename + '.pos.txt', 'wt') as outpos:
outfile.write(sample_header)
outfile.write('\n')
outpos.write(genoparser.get_position_header())
outpos.write('\n')
c = 0
for posline, genoline in genoparser.parse_raw_lines():
# split posline
tokens = posline.split()
if (tokens[0], tokens[1]) in genoparser.include_positions:
outfile.write(genoline)
outpos.write(posline)
c += 1
cerr('I: writing %d positions' % c)
def prepare_stratified_samples(haplotypes,
group_keys,
k_fold,
haplotype_func=None):
""" check the suitability of sample sets and modify haplotypes and group_keys properly """
groups = []
for group_key, count in zip(*np.unique(group_keys, return_counts=True)):
# we make sure that every group has at least 2 * k_fold member
if count < k_fold * 2:
groups.append((group_key, math.ceil(k_fold * 2 / count)))
if len(groups) == 0:
# nothing to modify
return (haplotypes, group_keys)
cerr('[I - prepare_stratified_sample() replicated group: %s]' %
' '.join(x[0] for x in groups))
#import IPython; IPython.embed()
new_haplotypes = [haplotypes]
new_group_keys = [group_keys]
for group_key, m_factor in groups:
indexes = np.where(group_keys == group_key)
for i in range(m_factor):
new_haplotypes.append(haplotypes[indexes])
new_group_keys.append(group_keys[indexes])
haplotypes = np.concatenate(new_haplotypes, axis=0)
group_keys = np.concatenate(new_group_keys, axis=0)
return (haplotypes, group_keys)
def parse_snps(self):
""" this is generator that yield (legends, genotype) """
with open(self.genofile) as genofile, open(self.legendfile) as legendfile:
# sanity check for sample number in genotype file
header = next(genofile).strip()
samples = header.split()
if len(samples) != self.no_of_samples:
cerr('ERR: no of sample in infile does not match the sample file')
next(legendfile)
gene = next(gene_iter)
genotype = []
# generate genotype_line
for (idx, line) in enumerate(zip(genofile, legendfile)):
geno_line, legend_line = line
tokens = geno_line.strip().split()
legends = legend_line.replace('"', '').strip().split()
seqid = legends[0]
pos = int(legends[1])
if len(tokens) != self.no_of_samples:
cerr('ERR: line %d - no of sample in infile does not match the sample file' % (idx + 1))
g = self.translate(tokens)
yield( (legends, g))
def dist2clonalqc(args):
# read distance matrix
df = pd.read_csv(args.infile, sep='\t')
samples = df.columns
D = df.values
# read quality file or pickled ralt/nalt file
if args.datafile:
nalt_args = SimpleNamespace(infile=args.datafile, fmt=args.fmt, n=-1)
nalt_parser = naltparser.NAltLineParser(nalt_args,
with_group=False,
with_position=False)
region = nalt_parser.parse_whole()
qual = np.count_nonzero(region.M == -1, axis=0)
else:
cexit('ERR: other input file has not been defined')
clonal_samples = clonal_index(D,
qual.max() - qual, samples, args.threshold)
cerr('[I - removing %d clonal samples]' % len(clonal_samples))
if args.outfile:
np.savetxt(args.outfile, samples[clonal_samples], fmt='%s')
def prune_2(genotypes, positions, threshold=0.5, score=None):
""" prune by r^2 except on CDS, only CDS within the same segment/region will be pruned
"""
if score == None:
# we use MAC as default score
score = np.min( genotypes.count_alleles(), axis=1)
N = len(genotypes)
if N != len(score) or N != len(positions):
cexit('E: length of genotypes != length of score nor positions!')
index = arrange_index( score )
compress_index = np.ones( len(index), dtype=np.int8 )
# calculate r^2
r_2 = calculate_r_2( genotypes )
# walk through index
cerr('I: scanning r^2 matrix')
for i in range(N):
if not compress_index[i]:
continue
for _, j in scoring_index[i+1:]:
if r_2[i,j] > threshold:
# check if this is a CDS region
if positions[j][4] and positions[j][4] != positions[i][4]:
continue
compress_index[j] = 0
return compress_index
def prune_1(genotypes, threshold=0.5, score=None):
""" prune by r^2 with score as priority,
returning indexing array
"""
N = len(genotypes)
if score == None:
# we use MAC as default score
score = np.min( count_allele(genotypes), axis=1)
if N != len(score):
cexit('E: length of genotypes !+ length of score! ({} vs {})'.format(N, len(score)))
index = arrange_index( score )
compress_index = np.ones( len(index), dtype=np.int8 )
# calculate r^2
r_2 = calculate_r_2( genotypes )
count = 0
# walk through index
cerr('[I - pruning for {} SNPs]'.format(N))
for i in range(N):
if not compress_index[i]:
continue
for j in index[i+1:]:
if r_2[i,j] > threshold:
compress_index[j] = 0
count += 1
pruned_index = np.nonzero(compress_index)[0]
return pruned_index
def calculate_required_aspect(data):
total_width = 1.37 * len(data['REG'].unique())
total_height = total_width / 1.42 / 2 # bad approximation of square root of 2
cerr('[I - Using figure size: {:.2f} x {:.2f} inches]'.format(
total_height, total_width))
return total_width, total_height
def align( seqs, method=None, matrix='DNA', degap=True):
""" aligned a list of sequences in seqs, returning a list of aligned sequences """
if len(seqs) == 2:
# perform pairwise alignment
from seqpy.core.pwaligner import calign
if degap:
s_0 = degapped( seqs[0] )
s_1 = degapped( seqs[1] )
else:
s_0 = seqs[0]
s_1 = seqs[1]
if not method:
method = 'global_cfe'
a_0, a_1, score = calign.aligner(s_0.upper(), s_1.upper(), method=method,
matrix=matrix)
cerr('pairwise aligned with score: %f' % score)
return (preserve_case(s_0, a_0), preserve_case(s_1, a_1), score)
elif len(seqs) > 2:
# perform multiple sequence alignment
if method is None or method.startswith('muscle'):
pass
else:
raise RuntimerError('Alignment must involve 2 or more sequences')
def save(self,
fmt,
prefixname=None,
autofilename=False,
with_position=False):
# we make assumption on the type of data
if self.M.dtype == np.int8:
datatype = 'nalt'
else:
datatype = 'ralt'
if autofilename:
prefixname = '%s-%d-%d' % ('r' if datatype == 'ralt' else 'n',
len(self.df_M.columns), len(self.M))
outmatrix = prefixname + ('.ralt' if datatype == 'ralt' else '.nalt')
if fmt == 'pickle':
outmatrix = outmatrix + '.pickle.gz'
self.df_M.to_pickle(outmatrix)
elif fmt == 'npy':
outmatrix = outmatrix + '.npy.gz'
with gzopen(outmatrix, 'wb') as f:
a = np.array([np.array(self.df_M.columns), self.df_M.values])
np.save(f, a)
else:
outmatrix = outmatrix + '.txt.gz'
self.df_M.to_csv(outmatrix, sep='\t', index=False)
cerr('[I - writing genotype data to %s]' % outmatrix)
if with_position:
outpos = prefixname + '.pos.txt.gz'
self.df_P.to_csv(outpos, sep='\t', index=False)
cerr('[I - writing position data to %s]' % (outpos))
def geno2filtindv(args):
cerr('I: reading genotype file')
genoparser = tabparser.GenotypeLineParser(args)
cerr('I: generating haplotypes')
haplotypes = genoparser.parse_haplotypes()
cerr('I: scanning haplotypes')
flags = [True] * len(haplotypes)
for idx, haplo in enumerate(haplotypes):
missingness = haplo.count(b'-') / len(haplo)
if missingness > args.cutoff:
flags[idx] = False
#cerr('I: %4d : %f' % (idx, haplo.count(b'-')/len(haplo))
cerr('I: filtering samples')
outfile = open(args.outfile, 'w')
genoparser2 = tabparser.GenotypeLineParser(args)
samples = itertools.compress(genoparser2.samples, flags)
outfile.write('\t'.join(samples))
outfile.write('\n')
for posline, genoline in genoparser2.parse_raw_lines():
new_genotypes = itertools.compress(genoline.strip().split(), flags)
outfile.write('\t'.join(new_genotypes))
outfile.write('\n')
cerr('I: writing for %d samples' % flags.count(True))
def __init__(self, vcffile, chroms=None, filters='', **kwargs):
self.vcffile = vcffile
self._hdl = open(self.vcffile)
# parse filter
cerr('Filters: %s' % filters)
self.filters = {}
for filter_item in filters.split(','):
if not filter_item: continue
if '=' in filter_item:
k, v = filter_item.split('=', 1)
k = k.strip()
self._check_keyword(k)
self.filters[k.strip()] = float(v.strip())
else:
filter_item = filter_item.strip()
self._check_keyword(filter_item)
self.filters[filter_item] = True
self.sample_labels = None
if ',' in chroms:
chroms = [c.strip() for c in chroms.split(',')]
self.chroms = chroms
self.installed_filters = [
self._filter_MissingThreshold,
self._filter_HetThreshold,
self._filter_MAF,
self._filter_MAC,
]
self.dp = 0 if 'DP' not in kwargs else int(kwargs['DP'])
self.ad = 0 if 'AD' not in kwargs else int(kwargs['AD'])
self.init_params(**kwargs)
def D( level, text ):
cf = getouterframes( currentframe() )[ 1 ]
#print cf
#infos = getframeinfo( cf )
if level >= debug_level:
cerr("[%s] %s [%s:%s]:: %s " % (time.strftime('%H:%M:%S'),
cf[3], cf[1], cf[2], text))
def do_export_ralt(M, sample_idx, site_idx, indv_idx, args):
cerr('[I - exporting sample and position indexes for %d samples' % args.s)
collected_samples = indv_idx[:args.s]
filt_site_idx, inf_site_idx = filter_site_idx(M, collected_samples, site_idx, mac=args.mac)
np.savetxt('exhqc.indv.txt', collected_samples, fmt='%d')
np.savetxt('exhqc.pos.txt', inf_site_idx, fmt='%d')
def main():
greet()
if len(sys.argv) == 1:
usage()
if sys.argv[1].endswith('.py'):
# will execute a script file
seqpy.cerr('Attempting to run script: %s' % sys.argv[1])
with open(sys.argv[1]) as fh:
code = compile(fh.read(), sys.argv[1], 'exec')
sys.argv = sys.argv[1:]
_l = {}
module = exec(code, None, _l)
if 'main' in _l:
globals().update(_l)
main = _l['main']
if 'init_argparser' in _l:
init_argparser = _l['init_argparser']
p = init_argparser()
args = p.parse_args(sys.argv[1:])
main(args)
else:
main()
elif sys.argv[1] == '-i':
# interactive
pass
else:
from seqpy import cmds
cmds.execute(sys.argv[1:])
def barplot( args ):
cerr('I: reading data...')
df = pandas.read_table( args.infile )
column = df.columns[args.column - 1]
cerr('I: selecting column %s' % column)
if args.asc:
cerr('I: sorting ascending...')
df = df.sort_values( column )
elif args.desc:
cerr('I: sorting descending...')
df = df.sort_values( column, ascending=False)
heights = df[column]
cerr('I: plotting...')
#plt.bar( np.arange(0, len(heights)), heights, 1.0)
#plt.plot( heights )
plt.scatter( np.arange(0, len(heights)), heights, 0.25 )
if args.xlabel:
plt.xlabel(args.xlabel)
if args.ylabel:
plt.ylabel(args.ylabel)
if args.title:
plt.title(args.title)
plt.savefig(args.outfile, dpi = args.dpi)
def parse_haplotypes(self, maxline=-1):
""" this return a list like the following:
[ '0000022020',
'0002020000' ]
"""
if not self.posfile:
self.parse_position_header()
M = []
for (idx, paired_line) in enumerate(zip(self.posfile, self.infile)):
if maxline > 0 and idx >= maxline:
break
posline, genoline = paired_line
if self.include_positions:
posinfo = posline.strip('\n').split('\t')
if (posinfo[0], posinfo[1]) not in self.include_positions:
continue
tokens = genoline.strip().split('\t')
M.append(x[0] for x in tokens)
cerr('I: haplotyping for %d SNP positions' % len(M))
# do transpose
M_t = [*zip(*M)]
H = [''.join(x).encode('UTF-8') for x in M_t]
return H
def txt2select(args):
df = pandas.read_table(args.infile, delimiter='\t', na_values=' nan')
filtered_positions = {}
for i in args.column.split(','):
i = int(i) - 1
column = df.columns[i]
cerr('I: selecting with column %s' % column)
if args.minthreshold is not None:
df_filtered = df[df[column] > args.minthreshold]
else:
df_filtered = df.nlargest(args.topmax, column)
for r in df_filtered.itertuples():
filtered_positions[(r[1], int(r[2]))] = True
sorted_positions = sorted(filtered_positions.keys())
with open(args.outfile, 'w') as outfile:
outfile.write('CHROM\tPOS\n')
for k in sorted_positions:
outfile.write('%s\t%d\n' % (k))
cerr('I: writing %d positions' % len(sorted_positions))
def cross_validate(models,
haplotypes,
group_keys,
repeats,
fold,
outfile,
outsnp=None,
logfile=None,
outpred=None,
procs=1):
""" distribute the repeats over multi process
"""
start_time = time.monotonic()
cerr('[I - cross_validate() for %d model(s)]' % (len(models)))
seed = np.random.randint(1e8)
group_keys = np.array(
group_keys) if type(group_keys) != np.ndarray else group_keys
arguments = [(group_keys, fold, seed + n) for n in range(repeats)]
worker_func = cross_validate_worker
run_worker(models, haplotypes, arguments, worker_func, procs, outfile,
outsnp, logfile, outpred)
cerr('[I - cross_validate() finished in %6.2f minute(s) at %s]' %
((time.monotonic() - start_time) / 60, datetime.datetime.now()))
def get_position_indexes(self, poslines):
# create dictionary of [chr][pos] = index
d = {}
for i, line in enumerate(self.P):
try:
d[line[0]][line[1]] = i
except KeyError:
d[line[0]] = {line[1]: i}
indexes = []
counter = 0
for line in poslines:
if not line: continue
try:
counter += 1
indexes.append(d[line[0]][int(line[1])])
except KeyError:
cerr('[I - warning: position not found: %s %s]' %
(line[0], line[1]))
cerr('[I - warning: only found %d out of %d positions]' %
(len(indexes), counter))
return indexes
def pos2bed_microhaps(args, positions):
if args.namecol < 0:
cexit('ERR: microhaps mode needs --namecol option!')
with open(args.outfile, 'w') as fout:
mh_name = ''
mh_seq = ''
mh_1pos = -1
mh_2pos = -1
for entry in positions:
seq = entry[0]
pos = int(entry[1])
name = entry[args.namecol]
if name == mh_name and mh_seq == seq:
mh_2pos = pos
continue
if mh_name:
fout.write('%s\t%d\t%d\t%s\n' %
(mh_seq, mh_1pos, mh_2pos, mh_name))
mh_name = name
mh_seq = seq
mh_1pos = pos - 1
fout.write('%s\t%d\t%d\t%s\n' % (mh_seq, mh_1pos, mh_2pos, mh_name))
cerr('[I - writing microhap-based BED to %s]' % args.outfile)
def filter_mac(self, mac=1, inplace=True):
# get posindex whose MAC >= mac
snpindex = self.get_snpindex(mac=mac)
cerr('[I - filtering MAC = %d from %d SNPs to %d SNPs]' %
(mac, len(allele_mac), len(snpindex)))
return self.filter_positions(snpindex, inplace)
def seq2fst(args):
# open and read sequence file
cerr('[I - reading sequence file %s]' % args.infile)
seqs = load(args.infile)
# open and read group/meta file using groupfile/metafile if available
if args.groupfile or args.metafile:
cerr('[I - reading group information file]')
group_parser = grpparser.GroupParser(args)
group_parser.parse()
group_seqs = {}
for seq in seqs:
try:
grp = group_parser.group_info[seq.label.decode('ASCII')]
except KeyError:
cerr('[W - sample %s is not assign to any group]' %
seq.label.decode('ASCII'))
continue
if grp in group_seqs:
group_seqs[grp].append(seq)
else:
ms = multisequence()
ms.append(seq)
group_seqs[grp] = ms
else:
cexit('[ERR - seq2fst.py requires group information!]')
for grp_seq in group_seqs:
cerr('[I - group %s has %d sample(s)]' %
(grp_seq, len(group_seqs[grp_seq])))
if args.sitefile:
# perform FST site-wise
FST_sites = calc_site_fst(group_seqs, args.nantozero)
with open(args.sitefile, 'w') as fout:
for (label, mat) in FST_sites:
fout.write(label)
fout.write('\t')
np.savetxt(fout,
mat,
fmt='%5.4f',
delimiter='\t',
newline='\t')
fout.write('\n')
cerr('[I - site FST written to %s]' % (args.sitefile))
return
FST_mat, groups = calc_fst(group_seqs)
with open(args.outfile, 'w') as fout:
fout.write('\t'.join(groups))
fout.write('\n')
np.savetxt(fout, FST_mat, fmt='%5.4f', delimiter='\t')
def vcf2ped( args ):
""" create a ped and map file based on vcf and metafile, suitable for isoRelate """
# open group file
group_parser = grpparser.GroupParser( args )
# open VCF file
cerr('[I: reading VCF...]')
start_time = time.monotonic()
vcfset = allel.read_vcf(args.infile,
fields = ['samples', 'variants/CHROM', 'variants/POS', 'calldata/GT'])
cerr('[I: read %s site, %s samples in %d secs]' % (len(vcfset['variants/CHROM']),
len(vcfset['samples']), time.monotonic() - start_time))
# assign groups
samples = vcfset['samples']
group_parser.assign_groups(samples)
groups = group_parser.group_keys
#import IPython; IPython.embed()
# write to PED
with open(args.outprefix + '.ped', 'w') as outf:
for i in range(len(samples)):
outf.write('%s\t%s\t0\t0\t1\t0\t' % (groups[i], samples[i]))
alleles = []
for gt in vcfset['calldata/GT'][:,i]:
allele_1, allele_2 = gt
#print(allele_1, allele_2)
if allele_1 == allele_2:
if allele_1 == -1:
alleles += [0, 0]
elif allele_1 == 0:
alleles += [1, 1]
elif allele_1 == 1:
alleles += [2, 2]
else:
alleles += [1, 1]
else:
alleles += [1, 2]
outf.write('\t'.join( str(i) for i in alleles))
outf.write('\n')
#import IPython; IPython.embed()
# write to MAP
with open(args.outprefix + '.map', 'w') as outf:
last_pos = 0
curr_chr = None
for (chrom, pos) in zip( vcfset['variants/CHROM'], vcfset['variants/POS'] ):
if curr_chr != chrom:
curr_chr = chrom
last_pos = 0
dist = (pos - last_pos) * 1e-6
last_pos = pos
outf.write('%s\t%s:%d\t%8.6f\t%d\n' % (chrom, chrom, pos, dist, pos))
def filter_imiss(M, site_idx, sample_idx, imiss):
cerr('[I - filtering for sample missingness < %4.3f]' % imiss)
check_sanity(M, site_idx, sample_idx)
indv_missingness = np.count_nonzero(M < 0, axis=0) / len(site_idx)
indexes = np.where( indv_missingness <= (1.0 - imiss) * indv_missingness.max() )
M2 = M[:, indexes[0]]
sample_idx2 = sample_idx[ indexes[0] ]
cerr('[I - keeping %d from %d samples]' % (len(sample_idx2), len(sample_idx)))
return M2, site_idx, sample_idx2
def fas2table(args):
msa = load(args.infile)
ref = load(args.reffile)
table = generate_table(msa, ref)
with open(args.outfile, 'w') as fout:
for (label, muts) in table:
fout.write('%s/\t%s\n' % (label, ' '.join(muts)))
cerr('[Writing table to %s]' % args.outfile)
def geno2fst( args ):
lineparser = tabparser.GenotypeLineParser( args )
lineparser.set_translator(lineparser.diploid_translator)
cout('Grouping:')
groups = lineparser.parse_grouping()
for k in groups:
cout(' %12s %3d' % (k, len(groups[k])))
FST = [] # FST indexed by group_keys
group_keys = sorted(groups.keys())
cout(group_keys)
# output to file
cout('Writing outfile...')
outfile = open(args.outfile, 'w')
outfile.write('CHROM\tPOS\tREGION\tMAX\tMEAN\tMEDIAN\tMAF\t%s\n' % '\t'.join(group_keys) )
idx = 0
for (posinfo, genolist) in lineparser.parse():
idx += 1
genoarray = allel.GenotypeArray( [genolist] )
# calculate MAF
ac = genoarray.count_alleles()
num = np.min(ac)
denom = np.sum(ac)
if num == denom:
maf = 0
else:
maf = np.min(ac)/np.sum(ac)
# calculate FST per group against other samples
fst_sites = []
for g in group_keys:
ac_g = genoarray.count_alleles(subpop = groups[g])
ac_ng = genoarray.count_alleles(subpop = list( lineparser.sample_idx - set(groups[g])))
num, den = allel.stats.hudson_fst(ac_g, ac_ng)
fst = num[0]/den[0]
if not (0.0 <= fst <= 1.0):
fst = 0
fst_sites.append( fst )
if idx % 100 == 0:
cerr('I: writing position no %d' % idx)
outfile.write('%s\t%s\t%s\t%5.4f\t%5.4f\t%5.4f\t%5.4f\t%s\n' %
(posinfo[0], posinfo[1], posinfo[4], np.max(fst_sites), np.mean(fst_sites), np.median(fst_sites), maf,
'\t'.join( '%5.4f' % x for x in fst_sites)))
def filter_lmiss(M, site_idx, sample_idx, lmiss):
cerr('[I - filtering for SNP missingness < %4.3f]' % lmiss)
check_sanity(M, site_idx, sample_idx)
site_missingness = np.count_nonzero(M < 0, axis=1) / len(sample_idx)
indexes = np.where( site_missingness <= (1.0 - lmiss) * site_missingness.max())
M2 = M[ indexes[0], : ]
site_idx2 = site_idx[ indexes[0] ]
cerr('[I - keeping %d from %d sites]' % (len(site_idx2), len(site_idx)))
#import IPython; IPython.embed()
return M2, site_idx2, sample_idx
def ralt2nalt(args):
ralt_parser = naltparser.NAltLineParser(args,
datatype='ralt',
with_group=False,
with_position=False)
region = ralt_parser.parse_whole()
# convert to n_alt
cerr('[I - converting to nalt format]')
cerr('[ M dtype: {}]'.format(region.M.dtype))
region.ralt_to_nalt(hetratio=args.hetratio if not args.major else -1)
cerr('[ M dtype: {}]'.format(region.M.dtype))
region.save(args.outfmt,
prefixname=args.outfile,
autofilename=args.autofilename,
with_position=False)
return
# write to outfile
with open(args.outfile, 'w') as outfile:
# write header
outfile.write(ralt_parser.get_sample_header())
outfile.write('\n')
np.savetxt(outfile, region.M, fmt='%d', delimiter='\t')
cerr('[I: finish writing to %s' % args.outfile)
def ralt2iterqc( args ):
cerr('[I - reading input files]')
start_time = time.monotonic()
df = pd.read_csv(args.infile, sep='\t', dtype=float,
nrows=args.n if args.n > 0 else None)
samples = df.columns
sample_idx = np.arange(len(samples))
M = df.values
site_idx = np.arange(len(M))
cerr('[I - reading %d sites for %d samples in %d secs]'
% (len(site_idx), len(sample_idx), time.monotonic() - start_time))
for i in range(args.iter):
cerr('[I - ITER -> %d]' % (i+1))
site_N = len(site_idx)
sample_N = len(sample_idx)
if args.lmiss > 0:
M, site_idx, sample_idx = filter_lmiss(M, site_idx, sample_idx, args.lmiss)
if args.imiss > 0:
M, site_idx, sample_idx = filter_imiss(M, site_idx, sample_idx, args.imiss)
if args.mac > 0:
M, site_idx, sample_idx = filter_mac(M, site_idx, sample_idx, args.mac)
if site_N == len(site_idx) and sample_N == len(sample_idx):
cerr('[I - filtering has converged]')
break
def assign_groups(self, samples):
if not self.group_info:
self.parse()
groups = {}
sample_idx = []
group_keys = []
for idx, code in enumerate(samples):
grp_key = self.group_info[code]
if grp_key in groups:
groups[grp_key].append(idx)
else:
groups[grp_key] = [idx]
sample_idx.append(idx)
group_keys.append(grp_key)
self.samples = samples
self.sample_idx = set(sample_idx)
self.groups = groups
self.group_keys = group_keys
if self.colourfile:
# parse colour file
self.colourfile.seek(0)
next(self.colourfile)
for line in self.colourfile:
tokens = line.strip().split('\t')
self.group_colours[tokens[0]] = tokens[1]
# checking whether all groups has been assigned with colours
for k in self.groups:
if k not in self.group_colours:
cexit('E: group %s is not assigned' % k)
cerr('[I: assigning manual colours to %d groups]' %
(len(self.group_colours)))
else:
colour_wheel = cycle(colour_list)
for k in sorted(self.groups.keys()):
self.group_colours[k] = next(colour_wheel)
if len(self.groups.keys()) > len(colour_list):
cerr(
"W: warning, no of groups (%d) exceeds available colour list!"
% len(self.groups.keys()))
return self.groups
