def interval(locus_table, interval_table, intervals, loci, boxplot = True):
qry = get_interval_query(intervals, loci, locus_table, interval_table)
frame = robjects.r('''data <- dbGetQuery(con, {})'''.format(qry))
# because we're sorting by interval, which is a factor, we need to
# explicitly re-sort the data by the first integer value
# of the interval. This is a bit cumbersome, because sorting
# in R is less than pleasant.
sort_string = '''data$interval <- factor(data$interval, {})'''.format(order_intervals(frame[1]))
robjects.r(sort_string)
gg_frame = ggplot2.ggplot(robjects.r('''data'''))
if boxplot:
plot = gg_frame + ggplot2.aes_string(x = 'interval', y = 'pi') + \
ggplot2.geom_boxplot(**{
'outlier.size':0,
'alpha':0.3
}
) + \
ggplot2.geom_jitter(ggplot2.aes_string(color = 'locus'), size = 3, \
alpha = 0.6, position=ggplot2.position_jitter(width=0.25)) + \
ggplot2.scale_y_continuous('phylogenetic informativeness') + \
ggplot2.scale_x_discrete('interval (years ago)')
else:
plot = gg_frame + ggplot2.aes_string(x = 'interval', y = 'pi',
fill='locus') + ggplot2.geom_bar() + \
ggplot2.facet_wrap(robjects.Formula('~ locus')) + \
ggplot2.opts(**{
'axis.text.x':ggplot2.theme_text(angle = -90, hjust = 0),
'legend.position':'none'
}) + \
ggplot2.scale_y_continuous('phylogenetic informativeness') + \
ggplot2.scale_x_discrete('interval (years ago)')
return plot
def compare_sum_barplot(locus_table, interval_table, intervals, loci, names,
rows):
frame = get_r_data_by_top(locus_table, interval_table, intervals, names,
rows)
#pdb.set_trace()
frame2 = robjects.r('''agg_data <- aggregate(pi ~ interval + db, data = data, sum)''')
if len(intervals) > 1:
sort_string = '''agg_data$interval <- factor(agg_data$interval,{})'''.format(order_intervals(frame2[0]))
robjects.r(sort_string)
gg_frame = ggplot2.ggplot(robjects.r('''agg_data'''))
plot = gg_frame + \
ggplot2.aes_string(
x = 'interval',
y = 'pi',
fill='factor(db)'
) + \
ggplot2.geom_bar(**{
'position':'dodge',
'colour':'#767676',
'alpha':0.6
}
) + \
ggplot2.scale_y_continuous('net phylogenetic informativeness') + \
ggplot2.scale_x_discrete('interval (years ago)') + \
ggplot2.scale_fill_brewer("database", palette="Blues")
return plot
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 plot_coef(feat_mat_dir,
model_dir,
expt_names,
pref,
outfile=None,
height=120,
fsize=12):
for expt_idx, ex in enumerate(expt_names):
feat_mat_file = os.path.join(feat_mat_dir, ex + '_feat_mat.npz')
model_file = os.path.join(model_dir, pref + ex + '_model.pkl')
model = read_model(model_file)
(tmp_feat, tmp_y, tmp_feat_names,
tmp_gene_names) = read_feat_mat(feat_mat_file)
if expt_idx == 0:
feat_names = tmp_feat_names
clf_coef = model.clf_coef()
reg_coef = model.reg_coef()
else:
assert (all(f[0] == f[1] for f in zip(feat_names, tmp_feat_names)))
clf_coef = np.concatenate((clf_coef, model.clf_coef()), axis=1)
reg_coef = np.concatenate((reg_coef, model.reg_coef()), axis=1)
nexpt = expt_idx + 1
# Now clf_coef has one row per coefficient and one column per experiment.
# The reshape below will read the data row-first.
df = pd.DataFrame({
'feature': np.repeat(feat_names, nexpt),
'Classification': np.reshape(clf_coef, (clf_coef.size, )),
'Regression': np.reshape(reg_coef, (reg_coef.size, ))
})
df2 = pd.melt(df, id_vars='feature', var_name='fun')
r_df = com.convert_to_r_dataframe(df2)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(feature)', y = 'value') + \
ggplot2.facet_wrap('fun', scales = 'free_y') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Importance') + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize, angle = 65, vjust = 1, hjust = 1),
'axis.text.y':ggplot2.element_text(size = fsize),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
w = max(22 * nexpt, 80)
if outfile is None:
gp.plot()
else:
ro.r.ggsave(filename=outfile,
plot=gp,
width=w,
height=height,
unit='mm')
return df
def plot_cv_r2(pandas_df, outfile, fsize = 10, height = 120, max_width = 50, xlab = 'Parameters'):
"""Makes boxplots of cross-validation results for different parameter settings"""
ncv = len(set(list(pandas_df['title'])))
r_df = com.convert_to_r_dataframe(pandas_df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(title)', y = 'r2') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('R-squared') + \
ggplot2.scale_x_discrete(xlab) + ggplot2.theme_bw() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize, angle = 65, vjust = 1, hjust = 1),
'axis.text.y':ggplot2.element_text(size = fsize)})
w = max(5 * ncv, max_width)
ro.r.ggsave(filename = outfile, plot = gp, width = w, height = height, unit = 'mm')
def plot_cv_r2(pandas_df,
outfile,
fsize=10,
height=120,
max_width=50,
xlab='Parameters'):
"""Makes boxplots of cross-validation results for different parameter settings"""
ncv = len(set(list(pandas_df['title'])))
r_df = com.convert_to_r_dataframe(pandas_df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(title)', y = 'r2') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('R-squared') + \
ggplot2.scale_x_discrete(xlab) + ggplot2.theme_bw() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize, angle = 65, vjust = 1, hjust = 1),
'axis.text.y':ggplot2.element_text(size = fsize)})
w = max(5 * ncv, max_width)
ro.r.ggsave(filename=outfile, plot=gp, width=w, height=height, unit='mm')
def plot_thresh_distr(motif_names, thresh, out_dir, width = 350):
"""Creates boxplots of the thresholds used with each feature."""
df = pd.DataFrame({'motif':motif_names, 'thresh':thresh})
df = df[df['thresh'] > 1]
df.to_csv(os.path.join(out_dir, 'count_thresh.txt'), sep = '\t', index = False)
fsize = 10
r_df = com.convert_to_r_dataframe(df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(motif)', y = 'thresh') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Threshold counts', limits = ro.IntVector([0, 70])) + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + ggplot2.coord_flip() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.text.y':ggplot2.element_text(size = fsize, hjust = 1),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
for ext in ['.pdf', '.png']:
ro.r.ggsave(filename = os.path.join(out_dir, 'count_thresh_bar' + ext),
plot = gp, width = width, height = 300, unit = 'mm')
def compare_mean_boxplot(locus_table, interval_table, intervals, loci, names, rows):
frame = get_r_data_by_top(locus_table, interval_table, intervals, names,
rows)
if len(intervals) > 1:
sort_string = '''data$interval <- factor(data$interval, {})'''.format(order_intervals(frame[1]))
robjects.r(sort_string)
gg_frame = ggplot2.ggplot(robjects.r('''data'''))
plot = gg_frame + ggplot2.aes_string(x = 'interval', y = 'pi') + \
ggplot2.geom_boxplot(ggplot2.aes_string(fill = 'factor(db)'), **{
'outlier.size':3,
'outlier.colour':'#767676',
'outlier.alpha':0.3,
'alpha':0.6
}
) + \
ggplot2.scale_y_continuous('mean phylogenetic informativeness') + \
ggplot2.scale_x_discrete('interval (years ago)') + \
ggplot2.scale_fill_brewer("database", palette='Blues')
return plot
def plot_thresh_distr(motif_names, thresh, out_dir, width=350):
"""Creates boxplots of the thresholds used with each feature."""
df = pd.DataFrame({'motif': motif_names, 'thresh': thresh})
df = df[df['thresh'] > 1]
df.to_csv(os.path.join(out_dir, 'count_thresh.txt'), sep='\t', index=False)
fsize = 10
r_df = com.convert_to_r_dataframe(df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(motif)', y = 'thresh') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Threshold counts', limits = ro.IntVector([0, 70])) + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + ggplot2.coord_flip() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.text.y':ggplot2.element_text(size = fsize, hjust = 1),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
for ext in ['.pdf', '.png']:
ro.r.ggsave(filename=os.path.join(out_dir, 'count_thresh_bar' + ext),
plot=gp,
width=width,
height=300,
unit='mm')
def plot_coef(feat_mat_dir, model_dir, expt_names, pref, outfile = None, height = 120, fsize = 12):
for expt_idx, ex in enumerate(expt_names):
feat_mat_file = os.path.join(feat_mat_dir, ex + '_feat_mat.npz')
model_file = os.path.join(model_dir, pref + ex + '_model.pkl')
model = read_model(model_file)
(tmp_feat, tmp_y, tmp_feat_names, tmp_gene_names) = read_feat_mat(feat_mat_file)
if expt_idx == 0:
feat_names = tmp_feat_names
clf_coef = model.clf_coef()
reg_coef = model.reg_coef()
else:
assert(all(f[0] == f[1] for f in zip(feat_names, tmp_feat_names)))
clf_coef = np.concatenate((clf_coef, model.clf_coef()), axis = 1)
reg_coef = np.concatenate((reg_coef, model.reg_coef()), axis = 1)
nexpt = expt_idx + 1
# Now clf_coef has one row per coefficient and one column per experiment.
# The reshape below will read the data row-first.
df = pd.DataFrame({'feature':np.repeat(feat_names, nexpt),
'Classification':np.reshape(clf_coef, (clf_coef.size,)),
'Regression':np.reshape(reg_coef, (reg_coef.size,))})
df2 = pd.melt(df, id_vars = 'feature', var_name = 'fun')
r_df = com.convert_to_r_dataframe(df2)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(feature)', y = 'value') + \
ggplot2.facet_wrap('fun', scales = 'free_y') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Importance') + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize, angle = 65, vjust = 1, hjust = 1),
'axis.text.y':ggplot2.element_text(size = fsize),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
w = max(22 * nexpt, 80)
if outfile is None:
gp.plot()
else:
ro.r.ggsave(filename = outfile, plot = gp, width = w, height = height, unit = 'mm')
return df
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()