def main():
usage = 'usage: %prog [options] <mut1 file> <mut2 file>'
parser = OptionParser(usage)
parser.add_option('-m', dest='mut_norm', action='store_true', default=False, help='Normalize by # mutations (as opposed to sequenced bp) [Default: %default]')
parser.add_option('-o', dest='output_pdf', default='mut_cmp.pdf', help='Output pdf file for heatmap [Default: %default]')
parser.add_option('-r', dest='raw', action='store_true', default=False, help='Use raw mutation counts (as opposed to normalized for ACGT content) [Default: %default]')
(options,args) = parser.parse_args()
if len(args) != 2:
parser.error(usage)
else:
mut1_file = args[0]
mut2_file = args[1]
mutation_profile1, seq_bp1 = parse_mutations(mut1_file, options.raw)
mutation_profile2, seq_bp2 = parse_mutations(mut2_file, options.raw)
relative_mutation_profile = compute_relative_profile(mutation_profile1, seq_bp1, mutation_profile2, seq_bp2)
print_table(relative_mutation_profile)
# make plotting data structures
nts = ['_','A','C','G','T']
nts1 = []
nts2 = []
rel = []
for nt1 in nts:
for nt2 in nts:
nts1.append(nt1)
nts2.append(nt2)
rel.append(relative_mutation_profile[(nt1,nt2)])
nts1_r = ro.StrVector(nts1)
nts2_r = ro.StrVector(nts2)
rel_r = ro.FloatVector(rel)
df = ro.DataFrame({'nt1':nts1_r, 'nt2':nts2_r, 'rel':rel_r})
# plot
'''
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='nt2', y='nt1', fill='rel') + \
ggplot2.geom_tile() + \
ggplot2.scale_x_discrete(mut2_file, limits=nts) + \
ggplot2.scale_y_discrete(mut1_file, limits=nts) + \
ggplot2.scale_fill_gradient('Enrichment 1/2')
'''
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='nt2', y='nt1', fill='rel') + \
ggplot2.geom_tile() + \
ggplot2.scale_x_discrete('Read') + \
ggplot2.scale_y_discrete('Reference') + \
ggplot2.scale_fill_gradient2('log2 enrichment', low='darkblue', mid='white', high='darkred')
# save to file
grdevices.pdf(file=options.output_pdf)
gp.plot()
grdevices.dev_off()
def gray_plot(data, min=0, max=1, name=""):
reshape = importr('reshape')
gg = ggplot2.ggplot(reshape.melt(data,id_var=['x','y']))
pg = gg + ggplot2.aes_string(x='L1',y='L2')+ \
ggplot2.geom_tile(ggplot2.aes_string(fill='value'))+ \
ggplot2.scale_fill_gradient(low="black", high="white",limits=FloatVector((min,max)))+ \
ggplot2.coord_equal() + ggplot2.scale_x_continuous(name)
return pg
def gray_plot(data, min=0, max=1, name=""):
reshape = importr('reshape')
gg = ggplot2.ggplot(reshape.melt(data, id_var=['x', 'y']))
pg = gg + ggplot2.aes_string(x='L1',y='L2')+ \
ggplot2.geom_tile(ggplot2.aes_string(fill='value'))+ \
ggplot2.scale_fill_gradient(low="black", high="white",limits=FloatVector((min,max)))+ \
ggplot2.coord_equal() + ggplot2.scale_x_continuous(name)
return pg
def plot_similarity_matrix(self, item_type, image_file, title):
'''Plot similarities of crawls (overlap of unique items)
as heat map matrix'''
data = defaultdict(dict)
n = 1
for crawl1 in self.similarity[item_type]:
for crawl2 in self.similarity[item_type][crawl1]:
similarity = self.similarity[item_type][crawl1][crawl2]
data['crawl1'][n] = MonthlyCrawl.short_name(crawl1)
data['crawl2'][n] = MonthlyCrawl.short_name(crawl2)
data['similarity'][n] = similarity
data['sim_rounded'][n] = similarity # to be rounded
n += 1
data = pandas.DataFrame(data)
print(data)
# select median of similarity values as midpoint of similarity scale
midpoint = data['similarity'].median()
decimals = 3
textsize = 2
minshown = .0005
if (data['similarity'].max()-data['similarity'].min()) > .2:
decimals = 2
textsize = 2.8
minshown = .005
data['sim_rounded'] = data['sim_rounded'].apply(
lambda x: ('{0:.'+str(decimals)+'f}').format(x).lstrip('0')
if x >= minshown else '0')
print('Median of similarities for', item_type, '=', midpoint)
matrix_size = len(self.similarity[item_type])
if matrix_size > self.MAX_MATRIX_SIZE:
n = 0
for crawl1 in sorted(self.similarity[item_type], reverse=True):
short_name = MonthlyCrawl.short_name(crawl1)
if n > self.MAX_MATRIX_SIZE:
data = data[data['crawl1'] != short_name]
data = data[data['crawl2'] != short_name]
n += 1
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl2', y='crawl1',
fill='similarity', label='sim_rounded') \
+ ggplot2.geom_tile(color="white") \
+ ggplot2.scale_fill_gradient2(low="red", high="blue", mid="white",
midpoint=midpoint, space="Lab") \
+ GGPLOT2_THEME \
+ ggplot2.coord_fixed() \
+ ggplot2.theme(**{'axis.text.x':
ggplot2.element_text(angle=45,
vjust=1, hjust=1)}) \
+ ggplot2.labs(title=title, x='', y='') \
+ ggplot2.geom_text(color='black', size=textsize)
img_path = os.path.join(PLOTDIR, image_file)
p.save(img_path)
return p
def main():
usage = 'usage: %prog [options] <mut1 file> <mut2 file>'
parser = OptionParser(usage)
parser.add_option(
'-m',
dest='mut_norm',
action='store_true',
default=False,
help=
'Normalize by # mutations (as opposed to sequenced bp) [Default: %default]'
)
parser.add_option('-o',
dest='output_pdf',
default='mut_cmp.pdf',
help='Output pdf file for heatmap [Default: %default]')
parser.add_option(
'-r',
dest='raw',
action='store_true',
default=False,
help=
'Use raw mutation counts (as opposed to normalized for ACGT content) [Default: %default]'
)
(options, args) = parser.parse_args()
if len(args) != 2:
parser.error(usage)
else:
mut1_file = args[0]
mut2_file = args[1]
mutation_profile1, seq_bp1 = parse_mutations(mut1_file, options.raw)
mutation_profile2, seq_bp2 = parse_mutations(mut2_file, options.raw)
relative_mutation_profile = compute_relative_profile(
mutation_profile1, seq_bp1, mutation_profile2, seq_bp2)
print_table(relative_mutation_profile)
# make plotting data structures
nts = ['_', 'A', 'C', 'G', 'T']
nts1 = []
nts2 = []
rel = []
for nt1 in nts:
for nt2 in nts:
nts1.append(nt1)
nts2.append(nt2)
rel.append(relative_mutation_profile[(nt1, nt2)])
nts1_r = ro.StrVector(nts1)
nts2_r = ro.StrVector(nts2)
rel_r = ro.FloatVector(rel)
df = ro.DataFrame({'nt1': nts1_r, 'nt2': nts2_r, 'rel': rel_r})
# plot
'''
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='nt2', y='nt1', fill='rel') + \
ggplot2.geom_tile() + \
ggplot2.scale_x_discrete(mut2_file, limits=nts) + \
ggplot2.scale_y_discrete(mut1_file, limits=nts) + \
ggplot2.scale_fill_gradient('Enrichment 1/2')
'''
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='nt2', y='nt1', fill='rel') + \
ggplot2.geom_tile() + \
ggplot2.scale_x_discrete('Read') + \
ggplot2.scale_y_discrete('Reference') + \
ggplot2.scale_fill_gradient2('log2 enrichment', low='darkblue', mid='white', high='darkred')
# save to file
grdevices.pdf(file=options.output_pdf)
gp.plot()
grdevices.dev_off()
