def plot_squiggle(args, filename, start_times, mean_signals):
"""
Use rpy2 to create a squiggle plot of the read
"""
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
# set t_0 as the first measured time for the read.
t_0 = start_times[0]
total_time = start_times[-1] - start_times[0]
# adjust times to be relative to t_0
r_start_times = robjects.FloatVector([t - t_0 for t in start_times])
r_mean_signals = robjects.FloatVector(mean_signals)
# infer the appropriate number of events given the number of facets
num_events = len(r_mean_signals)
events_per_facet = (num_events / args.num_facets) + 1
# dummy variable to control faceting
facet_category = robjects.FloatVector([(i / events_per_facet) + 1 for i in range(len(start_times))])
# make a data frame of the start times and mean signals
d = {'start': r_start_times, 'mean': r_mean_signals, 'cat': facet_category}
df = robjects.DataFrame(d)
gp = ggplot2.ggplot(df)
if not args.theme_bw:
pp = gp + ggplot2.aes_string(x='start', y='mean') \
+ ggplot2.geom_step(size=0.25) \
+ ggplot2.facet_wrap(robjects.Formula('~cat'), ncol=1, scales="free_x") \
+ ggplot2.scale_x_continuous('Time (seconds)') \
+ ggplot2.scale_y_continuous('Mean signal (picoamps)') \
+ ggplot2.ggtitle('Squiggle plot for read: ' + filename + "\nTotal time (sec): " + str(total_time)) \
+ ggplot2.theme(**{'plot.title': ggplot2.element_text(size=11)})
else:
pp = gp + ggplot2.aes_string(x='start', y='mean') \
+ ggplot2.geom_step(size=0.25) \
+ ggplot2.facet_wrap(robjects.Formula('~cat'), ncol=1, scales="free_x") \
+ ggplot2.scale_x_continuous('Time (seconds)') \
+ ggplot2.scale_y_continuous('Mean signal (picoamps)') \
+ ggplot2.ggtitle('Squiggle plot for read: ' + filename + "\nTotal time (sec): " + str(total_time)) \
+ ggplot2.theme(**{'plot.title': ggplot2.element_text(size=11)}) \
+ ggplot2.theme_bw()
if args.saveas is not None:
plot_file = os.path.basename(filename) + "." + args.saveas
if os.path.isfile(plot_file):
raise Exception('Cannot create plot for %s: plot file %s already exists' % (filename, plot_file))
if args.saveas == "pdf":
grdevices.pdf(plot_file, width = 8.5, height = 11)
elif args.saveas == "png":
grdevices.png(plot_file, width = 8.5, height = 11,
units = "in", res = 300)
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
def make_output(tss_cov, out_prefix, upstream, downstream):
# dump raw counts to file
raw_out = open('%s_raw.txt' % out_prefix,'w')
for i in range(-upstream,downstream+1):
print >> raw_out, '%d\t%e' % (i, tss_cov[upstream+i])
raw_out.close()
# make plot data structures
tss_i = ro.IntVector(range(-upstream,downstream+1))
cov = ro.FloatVector(tss_cov)
df = ro.DataFrame({'tss_i':tss_i, 'cov':cov})
# construct full plot
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='tss_i', y='cov') + \
ggplot2.geom_point() + \
ggplot2.scale_x_continuous('TSS index') + \
ggplot2.scale_y_continuous('Coverage')
# plot to file
grdevices.pdf(file='%s_full.pdf' % out_prefix)
gp.plot()
grdevices.dev_off()
# construct zoomed plot
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='tss_i', y='cov') + \
ggplot2.geom_point() + \
ggplot2.scale_x_continuous('TSS index',limits=ro.IntVector([-1000,1000])) + \
ggplot2.scale_y_continuous('Coverage')
# plot to file
grdevices.pdf(file='%s_zoom.pdf' % out_prefix)
gp.plot()
grdevices.dev_off()
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 main():
usage = 'usage: %prog [options] <raw file>'
parser = OptionParser(usage)
parser.add_option('-d', dest='downstream', default=2000, type='int', help='TSS downstream [Default: %default]')
parser.add_option('-o', dest='out_prefix', default='tss', help='Output prefix [Default: %default]')
parser.add_option('-u', dest='upstream', default=5000, type='int', help='TSS upstream [Default: %default]')
parser.add_option('--ymax', dest='ymax', default=None, type='float', help='Y-coordinate limit [Default: %default]')
(options,args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide raw file')
else:
raw_file = args[0]
# collect data
coords = []
main_cov = []
control_cov = []
for line in open(raw_file):
a = line.split()
coords.append(int(a[0]))
main_cov.append(float(a[1]))
control_cov.append(float(a[2]))
# data structures
tss_i = ro.IntVector(range(-options.upstream,options.downstream+1))
labels = ro.StrVector(['Main']*(options.upstream+options.downstream+1)+['Control']*(options.upstream+options.downstream+1))
cov = ro.FloatVector(main_cov + control_cov)
df = ro.DataFrame({'tss_i':tss_i, 'cov':cov, 'label':labels})
# plot
'''
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='tss_i', y='cov', colour='label') + \
ggplot2.geom_point() + \
ggplot2.scale_x_continuous('TSS index') + \
ggplot2.scale_colour_discrete('')
'''
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='tss_i', y='cov', colour='label') + \
ggplot2.geom_smooth(method='loess', size=1, span=0.2, se=False) + \
ggplot2.scale_x_continuous('TSS Position') + \
ggplot2.scale_colour_discrete('') + \
ggplot2.theme_bw()
if options.ymax == None:
gp += ggplot2.scale_y_continuous('Coverage')
else:
gp += ggplot2.scale_y_continuous('Coverage', limits=ro.FloatVector([0,options.ymax]))
# save to file
grdevices.pdf(file='%s_and.pdf' % options.out_prefix)
gp.plot()
grdevices.dev_off()
def make_output_and(cov, control_cov, out_prefix, window):
# dump raw counts to file
raw_out = open("%s_raw.txt" % out_prefix, "w")
for i in range(-window / 2, window / 2 + 1):
print >> raw_out, "%d\t%e\t%e" % (i, cov[window / 2 + i], control_cov[window / 2 + i])
raw_out.close()
# make plot data structures
splice_i = ro.IntVector(2 * range(-window / 2, window / 2 + 1))
cov_r = ro.FloatVector(cov + control_cov)
labels = ro.StrVector(["Main"] * len(cov) + ["Control"] * len(control_cov))
df = ro.DataFrame({"splice_i": splice_i, "cov": cov_r, "label": labels})
# construct plot
gp = (
ggplot2.ggplot(df)
+ ggplot2.aes_string(x="splice_i", y="cov", colour="label")
+ ggplot2.geom_point()
+ ggplot2.scale_x_continuous("Position relative to splice site")
+ ggplot2.scale_y_continuous("Coverage")
+ ggplot2.scale_colour_discrete("")
)
# plot to file
grdevices.pdf(file="%s.pdf" % out_prefix)
gp.plot()
grdevices.dev_off()
def make_output_and(cov, control_cov, out_prefix, window):
# dump raw counts to file
raw_out = open('%s_raw.txt' % out_prefix,'w')
for i in range(-window/2,window/2+1):
print >> raw_out, '%d\t%e\t%e' % (i, cov[window/2+i], control_cov[window/2+i])
raw_out.close()
# make plot data structures
splice_i = ro.IntVector(2*range(-window/2,window/2+1))
cov_r = ro.FloatVector(cov+control_cov)
labels = ro.StrVector(['Main']*len(cov)+['Control']*len(control_cov))
df = ro.DataFrame({'splice_i':splice_i, 'cov':cov_r, 'label':labels})
# construct plot
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='splice_i', y='cov', colour='label') + \
ggplot2.geom_point() + \
ggplot2.scale_x_continuous('Position relative to splice site') + \
ggplot2.scale_y_continuous('Coverage') + \
ggplot2.scale_colour_discrete('')
# plot to file
grdevices.pdf(file='%s.pdf' % out_prefix)
gp.plot()
grdevices.dev_off()
def main():
usage = 'usage: %prog [options] arg'
parser = OptionParser(usage)
#parser.add_option()
(options,args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide BAM file')
else:
bam_file = args[0]
align_lengths = {}
for aligned_read in pysam.Samfile(bam_file, 'rb'):
align_lengths[aligned_read.qlen] = align_lengths.get(aligned_read.qlen,0) + 1
min_len = min(align_lengths.keys())
max_len = max(align_lengths.keys())
# construct data frame
len_r = ro.IntVector(range(min_len,max_len+1))
counts_r = ro.IntVector([align_lengths.get(l,0) for l in range(min_len,max_len+1)])
df = ro.DataFrame({'length':len_r, 'counts':counts_r})
# construct full plot
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='length', y='counts') + \
ggplot2.geom_bar(stat='identity') + \
ggplot2.scale_x_continuous('Alignment length') + \
ggplot2.scale_y_continuous('')
# plot to file
grdevices.pdf(file='align_lengths.pdf')
gp.plot()
grdevices.dev_off()
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 make_output(cov, out_prefix, window):
# dump raw counts to file
raw_out = open("%s_raw.txt" % out_prefix, "w")
for i in range(-window / 2, window / 2 + 1):
print >> raw_out, "%d\t%e" % (i, cov[window / 2 + i])
raw_out.close()
# make plot data structures
splice_i = ro.IntVector(range(-window / 2, window / 2 + 1))
cov = ro.FloatVector(cov)
df = ro.DataFrame({"splice_i": splice_i, "cov": cov})
# construct plot
gp = (
ggplot2.ggplot(df)
+ ggplot2.aes_string(x="splice_i", y="cov")
+ ggplot2.geom_point()
+ ggplot2.scale_x_continuous("Position relative to splice site")
+ ggplot2.scale_y_continuous("Coverage")
)
# plot to file
grdevices.pdf(file="%s.pdf" % out_prefix)
gp.plot()
grdevices.dev_off()
def make_output_and(te_tss_cov, control_te_tss_cov, out_prefix, upstream,
downstream):
# clean raw counts dir
if os.path.isdir('%s_raw' % out_prefix):
shutil.rmtree('%s_raw' % out_prefix)
os.mkdir('%s_raw' % out_prefix)
# dump raw counts to file
for te in te_tss_cov:
if te[0] in [
'n', '*', 'HERVH-int', 'L2a', 'AluSx', 'AluJb', 'MIRb', 'LTR7'
] and te[1] in [
'n', '*', 'LINE/L1', 'SINE/Alu', 'LTR/ERV1', 'LTR/ERVL-MaLR',
'LINE/L2', 'LTR/ERVL', 'SINE/MIR', 'DNA/hAT-Charlie',
'LTR/ERVK', 'DNA/TcMar-Tigger'
]:
raw_out = open(
'%s_raw/%s_%s.txt' %
(out_prefix, te[0].replace('/', '_'), te[1].replace('/', '_')),
'w')
for i in range(-upstream, downstream + 1):
print >> raw_out, '%d\t%e\t%e' % (i, te_tss_cov[te][
upstream + i], control_te_tss_cov[te][upstream + i])
raw_out.close()
# clean plot dirs
if os.path.isdir('%s_plot' % out_prefix):
shutil.rmtree('%s_plot' % out_prefix)
os.mkdir('%s_plot' % out_prefix)
# make data structures
tss_i = ro.IntVector(2 * range(-upstream, downstream + 1))
labels = ro.StrVector(['Main'] * (upstream + downstream + 1) +
['Control'] * (upstream + downstream + 1))
for te in te_tss_cov:
if te[0] in [
'n', '*', 'HERVH-int', 'L2a', 'AluSx', 'AluJb', 'MIRb', 'LTR7'
] and te[1] in [
'n', '*', 'LINE/L1', 'SINE/Alu', 'LTR/ERV1', 'LTR/ERVL-MaLR',
'LINE/L2', 'LTR/ERVL', 'SINE/MIR', 'DNA/hAT-Charlie',
'LTR/ERVK', 'DNA/TcMar-Tigger'
]:
cov = ro.FloatVector(te_tss_cov[te] + control_te_tss_cov[te])
df = ro.DataFrame({'tss_i': tss_i, 'cov': cov, 'label': labels})
# construct full plot
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='tss_i', y='cov', colour='label') + \
ggplot2.geom_point() + \
ggplot2.scale_x_continuous('TSS index') + \
ggplot2.scale_y_continuous('Coverage') + \
ggplot2.scale_colour_discrete('')
# plot to file
grdevices.pdf(
file='%s_plot/%s_%s.pdf' %
(out_prefix, te[0].replace('/', '_'), te[1].replace('/', '_')))
gp.plot()
grdevices.dev_off()
def plot(data, x, y, ylabel, color, filename):
gp = ggplot2.ggplot(data=data)
gp = gp + \
ggplot2.geom_line(ggplot2.aes_string(x=x, y=y), color=color) + \
ggplot2.theme(**{'axis.text.x' : ggplot2.element_text(angle = 90, hjust = 1),
'strip.text.y' : ggplot2.element_text(size = 6, angle=90)}) + \
ggplot2.scale_y_continuous(ylabel)
ggplot2.ggplot2.ggsave(filename, gp)
def _plot_with_rpy2(self, regions, filename):
from rpy2 import robjects
import rpy2.robjects.lib.ggplot2 as ggplot2
from rpy2.robjects.lib import grid
from rpy2.robjects.packages import importr
grdevices = importr('grDevices')
base = importr('base')
grdevices.pdf(file=filename + '.pdf')
t = [x for x in range(-self.num_bins, self.num_bins + 1)]
for region in regions[:self.num_regs]:
if not np.any(region.weighted):
logger.warning(
"Warning: No data for region located on bin " + str(region.bin) + ". Not plotting this one.")
continue
middle = (len(region.weighted[0]) - 1) / 2
if middle < self.num_bins:
logger.error("Warning: There are less bins calculated for regions than you want to plot.")
sys.exit(1)
d = {'map': robjects.StrVector(
[str(m) for sublist in [[x] * len(t) for x in range(len(region.weighted))] for m in sublist]),
't': robjects.FloatVector(t * len(region.weighted)),
'e': robjects.FloatVector([i for sublist in region.weighted for i in
sublist[middle - self.num_bins:middle + self.num_bins + 1]]),
'p': robjects.FloatVector([-np.log10(x) for sublist in region.pvalues for x in
sublist[middle - self.num_bins:middle + self.num_bins + 1]]),
'c': robjects.FloatVector([-np.log10(x) for sublist in region.corrected_pvalues for x in
sublist[middle - self.num_bins:middle + self.num_bins + 1]])}
dataf = robjects.DataFrame(d)
gp = ggplot2.ggplot(dataf) # first yellow second red
p1 = gp + ggplot2.geom_line(mapping=ggplot2.aes_string(x='t', y='e', group='map', colour='map'),
alpha=0.8) + ggplot2.scale_y_continuous(trans='log2') + ggplot2.ggtitle(
"\n".join(wrap("Bin " + str(region.bin) + " : " + str(region.positions)))) + ggplot2.labs(
y="log Intensity") + ggplot2.theme_classic() + ggplot2.theme(
**{'axis.title.x': ggplot2.element_blank(), 'axis.text.y': ggplot2.element_text(angle=45),
'axis.text.x': ggplot2.element_blank(),
'legend.position': 'none'}) + ggplot2.scale_colour_brewer(palette="Set1")
p2 = gp + ggplot2.geom_line(mapping=ggplot2.aes_string(x='t', y='p', group='map', colour='map'),
alpha=0.8) + ggplot2.labs(
y="-log10(p-value)") + ggplot2.theme_classic() + ggplot2.theme(
**{'axis.title.x': ggplot2.element_blank(), 'axis.text.x': ggplot2.element_blank(),
'legend.position': 'none'}) + ggplot2.scale_colour_brewer(palette="Set1")
p3 = gp + ggplot2.geom_line(mapping=ggplot2.aes_string(x='t', y='c', group='map', colour='map'),
alpha=0.8) + ggplot2.labs(y="-log10(q-value)",
x='bins (' + str(self.bin_res) + ' bp each)') + \
ggplot2.geom_hline(mapping=ggplot2.aes_string(yintercept=str(-np.log10(self.threshold))),
colour='black', alpha=0.8, linetype='dashed') + ggplot2.theme_classic() + \
ggplot2.theme(**{'legend.position': 'none'}) + ggplot2.scale_colour_brewer(palette="Set1")
g1 = ggplot2.ggplot2.ggplotGrob(p1)
g2 = ggplot2.ggplot2.ggplotGrob(p2)
g3 = ggplot2.ggplot2.ggplotGrob(p3)
robjects.globalenv["g"] = base.rbind(g1, g2, g3, size='first')
robjects.r("grid::grid.draw(g)")
grid.newpage()
logger.debug('Plotted region ' + str(region.bin))
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 single_locus_net_informativeness(locus_table, net_pi_table, locus):
qry = '''"SELECT {0}.locus, time, pi FROM {0}, {1}
WHERE {0}.id = {1}.id AND locus = '{2}'"'''.format(locus_table,
net_pi_table, locus)
frame = robjects.r('''dbGetQuery(con, {})'''.format(qry))
gg_frame = ggplot2.ggplot(frame)
plot = gg_frame + ggplot2.aes_string(x = 'time', y='pi') + \
ggplot2.geom_point(size = 3, alpha = 0.4) + \
ggplot2.scale_x_reverse('years ago') + \
ggplot2.scale_y_continuous('phylogenetic informativeness') + \
ggplot2.opts(title = locus)
return plot
def plot_summary(barcodes_obs, barcode_table, directory, expt_id):
barcodes, counts, matches = get_vectors(barcodes_obs, barcode_table)
df = DataFrame({'barcode': barcodes, 'count': counts, 'matched': matches})
p = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='factor(matched)', y='count / 1000000') + \
ggplot2.geom_boxplot(outlier_size = 0) + \
ggplot2.geom_jitter() + \
ggplot2.ggtitle(label = expt_id) + \
ggplot2.ggplot2.xlab(label = "") + \
ggplot2.scale_y_continuous(name = "Count\n(million reads)")
filename = "{0}/{1}.png".format(directory, expt_id)
grdevices.png(filename=filename, width=4, height=5, unit='in', res=300)
p.plot()
grdevices.dev_off()
def plot_cels(expr, expt_names, expt_name_idx, cel_names, outdir = None):
"""Makes correlation plots between CEL files for the same cell type"""
fsize = 10
names_1 = []
names_2 = []
cors = []
titles = []
for ex_idx, ex in enumerate(expt_names):
# Indices of CEL files (columns of expr) corresponding to that cell type
tmp_idx = expt_name_idx[ex]
plot_idx = 0
for i in range(len(tmp_idx)):
name1 = re.sub('_', '.', cel_names[tmp_idx[i]])
for j in range(i + 1, len(tmp_idx)):
name2 = re.sub('_', '.', cel_names[tmp_idx[j]])
plot_idx += 1
cor = np.corrcoef(expr[:, tmp_idx[i]], expr[:, tmp_idx[j]])[0, 1]
names_1.append(name1)
names_2.append(name2)
cors.append(cor)
titles.append(ex + '-' + str(plot_idx))
df = ro.DataFrame({'x':ro.FloatVector(expr[:, tmp_idx[i]]),
'y':ro.FloatVector(expr[:, tmp_idx[j]])})
gp = ggplot2.ggplot(df) + ggplot2.aes_string(x = 'x', y = 'y') + \
ggplot2.geom_point(size = 1) + \
ggplot2.scale_x_continuous(name1) + ggplot2.scale_y_continuous(name2) + \
ggplot2.theme_bw() + ggplot2.ggtitle('{:s}-{:d} ({:.4f})'.format(ex, plot_idx, cor)) + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.title.x':ggplot2.element_text(size = 8),
'axis.text.y':ggplot2.element_text(size = fsize),
'axis.title.y':ggplot2.element_text(size = 8, angle = 90),
'plot.title':ggplot2.element_text(size = fsize)})
if outdir is None:
gp.plot()
else:
if not os.path.isdir(outdir):
os.makedirs(outdir)
outfile = os.path.join(outdir, ex + '-' + str(plot_idx) + '.png')
ro.r.ggsave(filename = outfile, plot = gp, width = 85, height = 85, unit = 'mm')
df = pd.DataFrame({'name1':names_1, 'name2':names_2, 'cor':cors}, index = titles)
if not outdir is None:
df.to_csv(os.path.join(outdir, 'cor_summary.txt'), sep = '\t')
return df
def generate_histogram(subgroups_to_sses_to_n_count, tname, file_name):
columns_to_data = {'subgroup': [], tname: [], 'count': []}
max_count = 0
for subgroup, sses_to_n_count in subgroups_to_sses_to_n_count.items():
for ss, n_count in sses_to_n_count.items():
columns_to_data['subgroup'].append(subgroup)
columns_to_data[tname].append(ss)
columns_to_data['count'].append(n_count)
if n_count > max_count:
max_count = n_count
r_columns_to_data = {
'subgroup':
ro.FactorVector(columns_to_data['subgroup'],
levels=ro.StrVector(
_sort_subgroup(set(columns_to_data['subgroup'])))),
tname:
ro.StrVector(columns_to_data[tname]),
'count':
ro.IntVector(columns_to_data['count'])
}
df = ro.DataFrame(r_columns_to_data)
max_count = int(max_count / 1000 * 1000 + 1000)
histogram_file_path = os.path.join(OUTPUT_PATH, file_name)
logging.debug(
str.format("The Data Frame for file {}: \n{}", histogram_file_path,
df))
grdevices.png(file=histogram_file_path, width=1200, height=800)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string(x='subgroup', y='count', fill=tname) + \
ggplot2.geom_bar(position="dodge",width=0.8, stat="identity") + \
ggplot2.theme_bw() + \
ggplot2.theme_classic() + \
ggplot2.theme(**{'legend.title': ggplot2.element_blank()}) + \
ggplot2.theme(**{'legend.text': ggplot2.element_text(size=40)}) + \
ggplot2.theme(**{'axis.text.x': ggplot2.element_text(size=40,angle=45)}) + \
ggplot2.theme(**{'axis.text.y': ggplot2.element_text(size=40)}) + \
ggplot2.scale_y_continuous(expand=ro.IntVector([0, 0]),
limits=ro.IntVector([0, max_count])) + \
ggplot2.geom_text(ggplot2.aes_string(label='count'), size=6, angle=35, hjust=-0.1,
position=ggplot2.position_dodge(width=0.8),
vjust=-0.2)
pp.plot()
logging.info(str.format("Output step3 file {}", histogram_file_path))
grdevices.dev_off()
def multiple_locus_net_informativeness_scatterplot(locus_table, net_pi_table,
loci):
if loci[0].lower() != 'all':
qry = '''"SELECT {0}.locus, time, pi FROM {0}, {1}
WHERE {0}.id = {1}.id and locus in {2}"'''.format(locus_table,
net_pi_table, tuple(loci))
else:
qry = '''"SELECT {0}.locus, time, pi FROM {0}, {1}
WHERE {0}.id = {1}.id"'''.format(locus_table,
net_pi_table)
frame = robjects.r('''dbGetQuery(con, {})'''.format(qry))
gg_frame = ggplot2.ggplot(frame)
plot = gg_frame + ggplot2.aes_string(x = 'time', y = 'pi') + \
ggplot2.geom_point(ggplot2.aes_string(colour = 'locus'), \
size = 3, alpha = 0.4) + ggplot2.scale_x_reverse('years ago') + \
ggplot2.scale_y_continuous('phylogenetic informativeness')
return plot
def plot_summary(barcodes_obs, barcode_table, directory, expt_id):
barcodes, counts, matches = get_vectors(barcodes_obs, barcode_table)
df = DataFrame({'barcode': barcodes,
'count': counts,
'matched': matches})
p = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='factor(matched)', y='count / 1000000') + \
ggplot2.geom_boxplot(outlier_size = 0) + \
ggplot2.geom_jitter() + \
ggplot2.ggtitle(label = expt_id) + \
ggplot2.ggplot2.xlab(label = "") + \
ggplot2.scale_y_continuous(name = "Count\n(million reads)")
filename = "{0}/{1}.png".format(directory, expt_id)
grdevices.png(filename=filename, width=4, height=5, unit='in', res=300)
p.plot()
grdevices.dev_off()
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_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 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 generate_step3_9_n_count_histogram(place_type_pos_type_to_count,
file_name):
columns_to_data = {'place': [], 'pos': [], 'count': []}
max_count = 0
for place_pos_type, n_count in place_type_pos_type_to_count.items():
place_type, pos_type = place_pos_type.split('_')
columns_to_data['place'].append(place_type)
columns_to_data['pos'].append(pos_type)
columns_to_data['count'].append(n_count)
if n_count > max_count:
max_count = n_count
r_columns_to_data = {
'place': ro.StrVector(columns_to_data['place']),
'pos': ro.StrVector(columns_to_data['pos']),
'count': ro.IntVector(columns_to_data['count'])
}
df = ro.DataFrame(r_columns_to_data)
if max_count > 1000:
max_count = int(max_count / 1000 * 1000 + 1000)
else:
max_count = int(max_count / 100 * 100 + 100)
histogram_file_path = os.path.join(OUTPUT_PATH, file_name)
logging.debug(
str.format("The Data Frame for file {}: \n{}", histogram_file_path,
df))
grdevices.png(file=histogram_file_path, width=1024, height=512)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string(x='pos', y='count', fill='place') + \
ggplot2.geom_bar(position="dodge", stat="identity") + \
ggplot2.theme_bw() + \
ggplot2.theme_classic() + \
ggplot2.theme(**{'axis.text.x': ggplot2.element_text(size=35)}) + \
ggplot2.theme(**{'axis.text.y': ggplot2.element_text(size=35)}) + \
ggplot2.scale_y_continuous(expand=ro.IntVector([0, 0]),
limits=ro.IntVector([0, max_count])) + \
ggplot2.geom_text(ggplot2.aes_string(label='count'),
position=ggplot2.position_dodge(width=0.8), size=10, angle=35, hjust=-0.2,
vjust=-0.5)
pp.plot()
logging.info(str.format("Output step3 file {}", histogram_file_path))
grdevices.dev_off()
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 make_output_and(te_tss_cov, control_te_tss_cov, out_prefix, upstream, downstream):
# clean raw counts dir
if os.path.isdir('%s_raw' % out_prefix):
shutil.rmtree('%s_raw' % out_prefix)
os.mkdir('%s_raw' % out_prefix)
# dump raw counts to file
for te in te_tss_cov:
if te[0] in ['n','*','HERVH-int','L2a','AluSx','AluJb','MIRb','LTR7'] and te[1] in ['n','*','LINE/L1','SINE/Alu','LTR/ERV1','LTR/ERVL-MaLR','LINE/L2','LTR/ERVL','SINE/MIR','DNA/hAT-Charlie','LTR/ERVK','DNA/TcMar-Tigger']:
raw_out = open('%s_raw/%s_%s.txt' % (out_prefix,te[0].replace('/','_'),te[1].replace('/','_')),'w')
for i in range(-upstream,downstream+1):
print >> raw_out, '%d\t%e\t%e' % (i, te_tss_cov[te][upstream+i], control_te_tss_cov[te][upstream+i])
raw_out.close()
# clean plot dirs
if os.path.isdir('%s_plot' % out_prefix):
shutil.rmtree('%s_plot' % out_prefix)
os.mkdir('%s_plot' % out_prefix)
# make data structures
tss_i = ro.IntVector(2*range(-upstream,downstream+1))
labels = ro.StrVector(['Main']*(upstream+downstream+1)+['Control']*(upstream+downstream+1))
for te in te_tss_cov:
if te[0] in ['n','*','HERVH-int','L2a','AluSx','AluJb','MIRb','LTR7'] and te[1] in ['n','*','LINE/L1','SINE/Alu','LTR/ERV1','LTR/ERVL-MaLR','LINE/L2','LTR/ERVL','SINE/MIR','DNA/hAT-Charlie','LTR/ERVK','DNA/TcMar-Tigger']:
cov = ro.FloatVector(te_tss_cov[te] + control_te_tss_cov[te])
df = ro.DataFrame({'tss_i':tss_i, 'cov':cov, 'label':labels})
# construct full plot
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='tss_i', y='cov', colour='label') + \
ggplot2.geom_point() + \
ggplot2.scale_x_continuous('TSS index') + \
ggplot2.scale_y_continuous('Coverage') + \
ggplot2.scale_colour_discrete('')
# plot to file
grdevices.pdf(file='%s_plot/%s_%s.pdf' % (out_prefix,te[0].replace('/','_'),te[1].replace('/','_')))
gp.plot()
grdevices.dev_off()
def make_output(cov, out_prefix, window):
# dump raw counts to file
raw_out = open('%s_raw.txt' % out_prefix,'w')
for i in range(-window/2,window/2+1):
print >> raw_out, '%d\t%e' % (i, cov[window/2+i])
raw_out.close()
# make plot data structures
splice_i = ro.IntVector(range(-window/2,window/2+1))
cov = ro.FloatVector(cov)
df = ro.DataFrame({'splice_i':splice_i, 'cov':cov})
# construct plot
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='splice_i', y='cov') + \
ggplot2.geom_point() + \
ggplot2.scale_x_continuous('Position relative to splice site') + \
ggplot2.scale_y_continuous('Coverage')
# plot to file
grdevices.pdf(file='%s.pdf' % out_prefix)
gp.plot()
grdevices.dev_off()
def main():
usage = 'usage: %prog [options] arg'
parser = OptionParser(usage)
#parser.add_option()
(options, args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide BAM file')
else:
bam_file = args[0]
align_lengths = {}
for aligned_read in pysam.Samfile(bam_file, 'rb'):
align_lengths[aligned_read.qlen] = align_lengths.get(
aligned_read.qlen, 0) + 1
min_len = min(align_lengths.keys())
max_len = max(align_lengths.keys())
# construct data frame
len_r = ro.IntVector(range(min_len, max_len + 1))
counts_r = ro.IntVector(
[align_lengths.get(l, 0) for l in range(min_len, max_len + 1)])
df = ro.DataFrame({'length': len_r, 'counts': counts_r})
# construct full plot
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='length', y='counts') + \
ggplot2.geom_bar(stat='identity') + \
ggplot2.scale_x_continuous('Alignment length') + \
ggplot2.scale_y_continuous('')
# plot to file
grdevices.pdf(file='align_lengths.pdf')
gp.plot()
grdevices.dev_off()
def plot_collectors_curve(args, start_times, read_lengths):
"""
Use rpy2 to create a collectors curve of the run
"""
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
# set t_0 as the first measured time for the read.
t_0 = start_times[0]
# adjust times to be relative to t_0
r_start_times = robjects.FloatVector([float(t - t_0) / float(3600) \
for t in start_times])
r_read_lengths = robjects.IntVector(read_lengths)
# compute the cumulative based on reads or total base pairs
if args.plot_type == 'reads':
y_label = "Total reads"
cumulative = \
r.cumsum(robjects.IntVector([1] * len(start_times)))
elif args.plot_type == 'basepairs':
y_label = "Total base pairs"
cumulative = r.cumsum(r_read_lengths)
# make a data frame of the lists
d = {'start': r_start_times,
'lengths': r_read_lengths,
'cumul': cumulative}
df = robjects.DataFrame(d)
# title
total_reads = len(read_lengths)
total_bp = sum(read_lengths)
plot_title = "Yield: " \
+ str(total_reads) + " reads and " \
+ str(total_bp) + " base pairs."
# plot
gp = ggplot2.ggplot(df)
pp = gp + ggplot2.aes_string(x='start', y='cumul') \
+ ggplot2.geom_point() \
+ ggplot2.geom_line() \
+ ggplot2.scale_x_continuous('Time (hours)') \
+ ggplot2.scale_y_continuous(y_label) \
+ ggplot2.ggtitle(plot_title)
if args.saveas is not None:
plot_file = args.saveas
if plot_file.endswith(".pdf"):
grdevices.pdf(plot_file, width = 8.5, height = 8.5)
elif plot_file.endswith(".png"):
grdevices.png(plot_file, width = 8.5, height = 8.5,
units = "in", res = 300)
else:
print >>sys.stderr, "Unrecognized extension for %s!" % (plot_file)
sys.exit()
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
d['n_loop'] = IntVector([x[-1] for x in combos]) + IntVector([x[3] for x in combos_r])
d['group'] = StrVector([d['code'][x] + ':' + d['sequence'][x] for x in range(len(d['n_loop']))])
dataf = DataFrame(d)
from rpy2.robjects.lib import ggplot2
p = ggplot2.ggplot(dataf) + \
ggplot2.geom_line(ggplot2.aes_string(x="n_loop",
y="time",
colour="code")) + \
ggplot2.geom_point(ggplot2.aes_string(x="n_loop",
y="time",
colour="code")) + \
ggplot2.facet_wrap(Formula('~sequence')) + \
ggplot2.scale_y_continuous('running time') + \
ggplot2.scale_x_continuous('repeated n times', ) + \
ggplot2.xlim(0, max(n_loops)) + \
ggplot2.labs(title = "Benchmark (running time)")
from rpy2.robjects.packages import importr
grdevices = importr('grDevices')
grdevices.png('../../_static/benchmark_sum.png',
width = 712, height = 512)
p.plot()
grdevices.dev_off()
#base = importr("base")
stats = importr('stats')
nlme = importr("nlme")
def plot_squiggle(args, filename, start_times, mean_signals):
"""
Use rpy2 to create a squiggle plot of the read
"""
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
# set t_0 as the first measured time for the read.
t_0 = start_times[0]
total_time = start_times[-1] - start_times[0]
# adjust times to be relative to t_0
r_start_times = robjects.FloatVector([t - t_0 for t in start_times])
r_mean_signals = robjects.FloatVector(mean_signals)
# infer the appropriate number of events given the number of facets
num_events = len(r_mean_signals)
events_per_facet = (num_events / args.num_facets) + 1
# dummy variable to control faceting
facet_category = robjects.FloatVector([(i / events_per_facet) + 1
for i in range(len(start_times))])
# make a data frame of the start times and mean signals
d = {'start': r_start_times, 'mean': r_mean_signals, 'cat': facet_category}
df = robjects.DataFrame(d)
gp = ggplot2.ggplot(df)
if not args.theme_bw:
pp = gp + ggplot2.aes_string(x='start', y='mean') \
+ ggplot2.geom_step(size=0.25) \
+ ggplot2.facet_wrap(robjects.Formula('~cat'), ncol=1, scales="free_x") \
+ ggplot2.scale_x_continuous('Time (seconds)') \
+ ggplot2.scale_y_continuous('Mean signal (picoamps)') \
+ ggplot2.ggtitle('Squiggle plot for read: ' + filename + "\nTotal time (sec): " + str(total_time)) \
+ ggplot2.theme(**{'plot.title': ggplot2.element_text(size=11)})
else:
pp = gp + ggplot2.aes_string(x='start', y='mean') \
+ ggplot2.geom_step(size=0.25) \
+ ggplot2.facet_wrap(robjects.Formula('~cat'), ncol=1, scales="free_x") \
+ ggplot2.scale_x_continuous('Time (seconds)') \
+ ggplot2.scale_y_continuous('Mean signal (picoamps)') \
+ ggplot2.ggtitle('Squiggle plot for read: ' + filename + "\nTotal time (sec): " + str(total_time)) \
+ ggplot2.theme(**{'plot.title': ggplot2.element_text(size=11)}) \
+ ggplot2.theme_bw()
if args.saveas is not None:
plot_file = os.path.basename(filename) + "." + args.saveas
if os.path.isfile(plot_file):
raise Exception(
'Cannot create plot for %s: plot file %s already exists' %
(filename, plot_file))
if args.saveas == "pdf":
grdevices.pdf(plot_file, width=8.5, height=11)
elif args.saveas == "png":
grdevices.png(plot_file, width=8.5, height=11, units="in", res=300)
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
ggplot2.scale_fill_gradient(high = 'blue', low = 'red') + \
ggplot2.scale_fill_continuous(name = "Obama Vote Share") + \
ggplot2.scale_colour_continuous(name = "Obama Vote Share") + \
ggplot2.opts(**{'legend.position': 'left', 'legend.key.size': robjects.r.unit(2, 'lines'), 'legend.title' : ggplot2.theme_text(size = 14, hjust=0), \
'legend.text': ggplot2.theme_text(size = 12), 'title' : "Obama Vote Share and Distance to Railroads in IL", \
'plot.title': ggplot2.theme_text(size = 24), 'plot.margin': robjects.r.unit(robjects.r.rep(0,4),'lines'), \
'panel.background': ggplot2.theme_blank(), 'panel.grid.minor': ggplot2.theme_blank(), 'panel.grid.major': ggplot2.theme_blank(), \
'axis.ticks': ggplot2.theme_blank(), 'axis.title.x': ggplot2.theme_blank(), 'axis.title.y': ggplot2.theme_blank(), \
'axis.title.x': ggplot2.theme_blank(), 'axis.title.x': ggplot2.theme_blank(), 'axis.text.x': ggplot2.theme_blank(), \
'axis.text.y': ggplot2.theme_blank()} ) + \
ggplot2.geom_line(ggplot2.aes(x='long', y='lat', group='group'), data=IL_railroads, color='grey', size=0.2) + \
ggplot2.coord_equal()
p_map.plot()
## add the scatterplot
## define layout of subplot with viewports
vp_sub = grid.viewport(x = 0.19, y = 0.2, width = 0.32, height = 0.4)
p_sub = ggplot2.ggplot(RR_distance) + \
ggplot2.aes_string(x = 'OBAMA_SHAR', y= 'NEAR_DIST') + \
ggplot2.geom_point(ggplot2.aes(color='OBAMA_SHAR')) + \
ggplot2.stat_smooth(color="black") + \
ggplot2.opts(**{'legend.position': 'none'}) + \
ggplot2.scale_x_continuous("Obama Vote Share") + \
ggplot2.scale_y_continuous("Distance to nearest Railroad")
p_sub.plot(vp=vp_sub)
grdevices.dev_off()
def plot_qc_reads(qc_df):
"""
Plot number of reads part of a pipeline QC file.
"""
# Record NA values as 0
qc_df = qc_df.fillna(0)#.set_index("sample")
cols = ["sample",
"num_reads",
"num_mapped",
"num_unique_mapped",
"num_junctions"]
qc_df = qc_df[cols]
melted_qc = pandas.melt(qc_df, id_vars=["sample"])
qc_r = conversion_pydataframe(melted_qc)
labels = tuple(["num_reads",
"num_mapped",
"num_unique_mapped",
"num_junctions"])
labels = robj.StrVector(labels)
variable_i = qc_r.names.index('variable')
qc_r[variable_i] = robj.FactorVector(qc_r[variable_i],
levels = labels)
ggplot2.theme_set(ggplot2.theme_bw(12))
scales = importr("scales")
r_opts = r.options(scipen=4)
p = ggplot2.ggplot(qc_r) + \
ggplot2.geom_point(aes_string(x="sample", y="value")) + \
ggplot2.scale_y_continuous(trans=scales.log10_trans(),
breaks=scales.trans_breaks("log10",
robj.r('function(x) 10^x')),
labels=scales.trans_format("log10",
robj.r('math_format(10^.x)'))) + \
r.xlab("CLIP-Seq samples") + \
r.ylab("No. reads") + \
ggplot2.coord_flip() + \
ggplot2.facet_wrap(Formula("~ variable"), ncol=1) + \
theme(**{"panel.grid.major.x": element_blank(),
"panel.grid.minor.x": element_blank(),
"panel.grid.major.y": theme_line(size=0.5,colour="grey66",linetype=3)})
p.plot()
return
r.par(mfrow=np.array([1,2]))
num_samples = len(qc_df.num_reads)
r.par(bty="n", lwd=1.7, lty=2)
r_opts = r.options(scipen=4)
r.options(r_opts)
r.dotchart(convert_to_r_matrix(qc_df[["num_reads",
"num_mapped",
"num_unique_mapped"]]),
xlab="No. reads",
lcolor="black",
pch=19,
gcolor="darkblue",
cex=0.8)
r.par(bty="n")
r.dotchart(convert_to_r_matrix(qc_df[["num_ribosub_mapped",
"num_ribo",
"num_junctions"]]),
xlab="No. reads",
lcolor="black",
pch=19,
gcolor="darkblue",
cex=0.8)
def plot_cels(expr, expt_names, expt_name_idx, cel_names, outdir=None):
"""Makes correlation plots between CEL files for the same cell type"""
fsize = 10
names_1 = []
names_2 = []
cors = []
titles = []
for ex_idx, ex in enumerate(expt_names):
# Indices of CEL files (columns of expr) corresponding to that cell type
tmp_idx = expt_name_idx[ex]
plot_idx = 0
for i in range(len(tmp_idx)):
name1 = re.sub('_', '.', cel_names[tmp_idx[i]])
for j in range(i + 1, len(tmp_idx)):
name2 = re.sub('_', '.', cel_names[tmp_idx[j]])
plot_idx += 1
cor = np.corrcoef(expr[:, tmp_idx[i]], expr[:, tmp_idx[j]])[0,
1]
names_1.append(name1)
names_2.append(name2)
cors.append(cor)
titles.append(ex + '-' + str(plot_idx))
df = ro.DataFrame({
'x': ro.FloatVector(expr[:, tmp_idx[i]]),
'y': ro.FloatVector(expr[:, tmp_idx[j]])
})
gp = ggplot2.ggplot(df) + ggplot2.aes_string(x = 'x', y = 'y') + \
ggplot2.geom_point(size = 1) + \
ggplot2.scale_x_continuous(name1) + ggplot2.scale_y_continuous(name2) + \
ggplot2.theme_bw() + ggplot2.ggtitle('{:s}-{:d} ({:.4f})'.format(ex, plot_idx, cor)) + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.title.x':ggplot2.element_text(size = 8),
'axis.text.y':ggplot2.element_text(size = fsize),
'axis.title.y':ggplot2.element_text(size = 8, angle = 90),
'plot.title':ggplot2.element_text(size = fsize)})
if outdir is None:
gp.plot()
else:
if not os.path.isdir(outdir):
os.makedirs(outdir)
outfile = os.path.join(outdir,
ex + '-' + str(plot_idx) + '.png')
ro.r.ggsave(filename=outfile,
plot=gp,
width=85,
height=85,
unit='mm')
df = pd.DataFrame({
'name1': names_1,
'name2': names_2,
'cor': cors
},
index=titles)
if not outdir is None:
df.to_csv(os.path.join(outdir, 'cor_summary.txt'), sep='\t')
return df
ggplot2.scale_fill_gradient(high = 'blue', low = 'red') + \
ggplot2.scale_fill_continuous(name = "Obama Vote Share") + \
ggplot2.scale_colour_continuous(name = "Obama Vote Share") + \
ggplot2.opts(**{'legend.position': 'left', 'legend.key.size': robjects.r.unit(2, 'lines'), 'legend.title' : ggplot2.theme_text(size = 14, hjust=0), \
'legend.text': ggplot2.theme_text(size = 12), 'title' : "Obama Vote Share and Distance to Railroads in IL", \
'plot.title': ggplot2.theme_text(size = 24), 'plot.margin': robjects.r.unit(robjects.r.rep(0,4),'lines'), \
'panel.background': ggplot2.theme_blank(), 'panel.grid.minor': ggplot2.theme_blank(), 'panel.grid.major': ggplot2.theme_blank(), \
'axis.ticks': ggplot2.theme_blank(), 'axis.title.x': ggplot2.theme_blank(), 'axis.title.y': ggplot2.theme_blank(), \
'axis.title.x': ggplot2.theme_blank(), 'axis.title.x': ggplot2.theme_blank(), 'axis.text.x': ggplot2.theme_blank(), \
'axis.text.y': ggplot2.theme_blank()} ) + \
ggplot2.geom_line(ggplot2.aes(x='long', y='lat', group='group'), data=IL_railroads, color='grey', size=0.2) + \
ggplot2.coord_equal()
p_map.plot()
## add the scatterplot
## define layout of subplot with viewports
vp_sub = grid.viewport(x=0.19, y=0.2, width=0.32, height=0.4)
p_sub = ggplot2.ggplot(RR_distance) + \
ggplot2.aes_string(x = 'OBAMA_SHAR', y= 'NEAR_DIST') + \
ggplot2.geom_point(ggplot2.aes(color='OBAMA_SHAR')) + \
ggplot2.stat_smooth(color="black") + \
ggplot2.opts(**{'legend.position': 'none'}) + \
ggplot2.scale_x_continuous("Obama Vote Share") + \
ggplot2.scale_y_continuous("Distance to nearest Railroad")
p_sub.plot(vp=vp_sub)
grdevices.dev_off()
number_of_peaks = len(dataf[0])
cvI = []
newRow = []
for i in range(1,number_of_peaks+1):
row = dataf.rx(i,True)
rowA = np.array(row)
newRow.append(rowA[2:])
cvI.append(cv(rowA[2:]))
#cv.append(rowA[2:].std()/rowA[2:].mean())
cv_r=robjects.conversion.py2ri(cvI)
df_cv = {'CV' : cv_r}
dataf_cv = robjects.DataFrame(df_cv)
dtf_cv = robjects.r.melt(dataf_cv)
d=dataf.cbind(dtf_cv.rx(2))
d.names[tuple(d.colnames).index('value')] = 'CV'
#d = base.merge_data_frame(dataf,dtf_cv.rx(2))
utilis.write_csv(d, options.csv_output)
dc = dtf_cv.cbind(n_peak = robjects.IntVector(range(1,number_of_peaks+1)))
#n_peak = robjects.IntVector(1,number_of_peaks)
gp = ggplot2.ggplot(dc)
pp=gp+ggplot2.aes_string(x='n_peak',y='value') + ggplot2.geom_point()+ggplot2.theme_bw()+ ggplot2.ggtitle('Coefficient of Variation')+ \
ggplot2.scale_x_continuous("Number of Peaks")+ ggplot2.scale_y_continuous("CV")
r.X11()
pp.plot()
def plot_collectors_curve(args, start_times, read_lengths):
"""
Use rpy2 to create a collectors curve of the run
"""
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
# set t_0 as the first measured time for the read.
t_0 = start_times[0]
# adjust times to be relative to t_0
r_start_times = robjects.FloatVector([float(t - t_0) / float(3600) + 0.00000001 \
for t in start_times])
r_read_lengths = robjects.IntVector(read_lengths)
# compute the cumulative based on reads or total base pairs
if args.plot_type == 'reads':
y_label = "Total reads"
cumulative = \
r.cumsum(robjects.IntVector([1] * len(start_times)))
elif args.plot_type == 'basepairs':
y_label = "Total base pairs"
cumulative = r.cumsum(r_read_lengths)
# make a data frame of the lists
d = {'start': r_start_times,
'lengths': r_read_lengths,
'cumul': cumulative}
df = robjects.DataFrame(d)
if args.savedf:
robjects.r("write.table")(df, file=args.savedf, sep="\t")
# title
total_reads = len(read_lengths)
total_bp = sum(read_lengths)
plot_title = "Yield: " \
+ str(total_reads) + " reads and " \
+ str(total_bp) + " base pairs."
# plot
gp = ggplot2.ggplot(df)
pp = gp + ggplot2.aes_string(x='start', y='cumul') \
+ ggplot2.geom_step(size=2) \
+ ggplot2.scale_x_continuous('Time (hours)') \
+ ggplot2.scale_y_continuous(y_label) \
+ ggplot2.ggtitle(plot_title)
# extrapolation
if args.extrapolate:
start = robjects.ListVector({'a': 1, 'b': 1})
pp = pp + ggplot2.stat_smooth(fullrange='TRUE', method='nls',
formula='y~a*I((x*3600)^b)',
se='FALSE', start=start) \
+ ggplot2.xlim(0, float(args.extrapolate))
if args.theme_bw:
pp = pp + ggplot2.theme_bw()
if args.saveas is not None:
plot_file = args.saveas
if plot_file.endswith(".pdf"):
grdevices.pdf(plot_file, width = 8.5, height = 8.5)
elif plot_file.endswith(".png"):
grdevices.png(plot_file, width = 8.5, height = 8.5,
units = "in", res = 300)
else:
logger.error("Unrecognized extension for %s!" % (plot_file))
sys.exit()
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
def main():
usage = 'usage: %prog [options] <raw file>'
parser = OptionParser(usage)
parser.add_option('-d',
dest='downstream',
default=2000,
type='int',
help='TSS downstream [Default: %default]')
parser.add_option('-o',
dest='out_prefix',
default='tss',
help='Output prefix [Default: %default]')
parser.add_option('-u',
dest='upstream',
default=5000,
type='int',
help='TSS upstream [Default: %default]')
parser.add_option('--ymax',
dest='ymax',
default=None,
type='float',
help='Y-coordinate limit [Default: %default]')
(options, args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide raw file')
else:
raw_file = args[0]
# collect data
coords = []
main_cov = []
control_cov = []
for line in open(raw_file):
a = line.split()
coords.append(int(a[0]))
main_cov.append(float(a[1]))
control_cov.append(float(a[2]))
# data structures
tss_i = ro.IntVector(range(-options.upstream, options.downstream + 1))
labels = ro.StrVector(['Main'] *
(options.upstream + options.downstream + 1) +
['Control'] *
(options.upstream + options.downstream + 1))
cov = ro.FloatVector(main_cov + control_cov)
df = ro.DataFrame({'tss_i': tss_i, 'cov': cov, 'label': labels})
# plot
'''
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='tss_i', y='cov', colour='label') + \
ggplot2.geom_point() + \
ggplot2.scale_x_continuous('TSS index') + \
ggplot2.scale_colour_discrete('')
'''
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='tss_i', y='cov', colour='label') + \
ggplot2.geom_smooth(method='loess', size=1, span=0.2, se=False) + \
ggplot2.scale_x_continuous('TSS Position') + \
ggplot2.scale_colour_discrete('') + \
ggplot2.theme_bw()
if options.ymax == None:
gp += ggplot2.scale_y_continuous('Coverage')
else:
gp += ggplot2.scale_y_continuous('Coverage',
limits=ro.FloatVector(
[0, options.ymax]))
# save to file
grdevices.pdf(file='%s_and.pdf' % options.out_prefix)
gp.plot()
grdevices.dev_off()
def plot_collectors_curve(args, start_times, read_lengths):
"""
Use rpy2 to create a collectors curve of the run
"""
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
# set t_0 as the first measured time for the read.
t_0 = start_times[0]
# adjust times to be relative to t_0
r_start_times = robjects.FloatVector([float(t - t_0) / float(3600) + 0.00000001 \
for t in start_times])
r_read_lengths = robjects.IntVector(read_lengths)
# compute the cumulative based on reads or total base pairs
if args.plot_type == 'reads':
y_label = "Total reads"
cumulative = \
r.cumsum(robjects.IntVector([1] * len(start_times)))
elif args.plot_type == 'basepairs':
y_label = "Total base pairs"
cumulative = r.cumsum(r_read_lengths)
step = args.skip
# make a data frame of the lists
d = {
'start':
robjects.FloatVector(
[r_start_times[n] for n in xrange(0, len(r_start_times), step)]),
'lengths':
robjects.IntVector(
[r_read_lengths[n] for n in xrange(0, len(r_read_lengths), step)]),
'cumul':
robjects.IntVector(
[cumulative[n] for n in xrange(0, len(cumulative), step)])
}
df = robjects.DataFrame(d)
if args.savedf:
robjects.r("write.table")(df, file=args.savedf, sep="\t")
# title
total_reads = len(read_lengths)
total_bp = sum(read_lengths)
plot_title = "Yield: " \
+ str(total_reads) + " reads and " \
+ str(total_bp) + " base pairs."
# plot
gp = ggplot2.ggplot(df)
pp = gp + ggplot2.aes_string(x='start', y='cumul') \
+ ggplot2.geom_step(size=2) \
+ ggplot2.scale_x_continuous('Time (hours)') \
+ ggplot2.scale_y_continuous(y_label) \
+ ggplot2.ggtitle(plot_title)
# extrapolation
if args.extrapolate:
start = robjects.ListVector({'a': 1, 'b': 1})
pp = pp + ggplot2.stat_smooth(fullrange='TRUE', method='nls',
formula='y~a*I((x*3600)^b)',
se='FALSE', start=start) \
+ ggplot2.xlim(0, float(args.extrapolate))
if args.theme_bw:
pp = pp + ggplot2.theme_bw()
if args.saveas is not None:
plot_file = args.saveas
if plot_file.endswith(".pdf"):
grdevices.pdf(plot_file, width=8.5, height=8.5)
elif plot_file.endswith(".png"):
grdevices.png(plot_file,
width=8.5,
height=8.5,
units="in",
res=300)
else:
logger.error("Unrecognized extension for %s!" % (plot_file))
sys.exit()
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
d['n_loop'] = IntVector([x[-1] for x in combos]) + IntVector(
[x[1] for x in combos_r])
d['group'] = StrVector(
[d['code'][x] + ':' + d['sequence'][x] for x in xrange(len(d['n_loop']))])
dataf = DataFrame(d)
from rpy2.robjects.lib import ggplot2
p = ggplot2.ggplot(dataf) + \
ggplot2.geom_line(ggplot2.aes_string(x="n_loop",
y="time",
colour="code")) + \
ggplot2.geom_point(ggplot2.aes_string(x="n_loop",
y="time",
colour="code")) + \
ggplot2.facet_wrap(Formula('~sequence')) + \
ggplot2.scale_y_continuous('running time') + \
ggplot2.scale_x_continuous('repeated n times', ) + \
ggplot2.xlim(0, max(n_loops)) + \
ggplot2.opts(title = "Benchmark (running time)")
from rpy2.robjects.packages import importr
grdevices = importr('grDevices')
grdevices.png('../../_static/benchmark_sum.png', width=712, height=512)
p.plot()
grdevices.dev_off()
#base = importr("base")
stats = importr('stats')
nlme = importr("nlme")
fit = nlme.lmList(Formula('time ~ n_loop | group'),
data=dataf,
def plot_volcano_with_r(
data,
xlabel='Estimated effect (change in H/L ratio)',
title='',
max_labels=20,
color_background='#737373',
color_significant='#252525',
color_significant_muted='#252525',
label_only_large_fc=False,
special_labels=None,
special_palette=None,
base_size=12,
label_size=3,
x='logFC',
y='neg_log10_p_adjust',
special_labels_mode='all',
xlim=None,
skip_labels=None,
nudges=None,
):
r_data, r_like_data = transform_data_for_ggplot(
data,
label_only_large_fc=label_only_large_fc,
special_labels=special_labels,
max_labels=max_labels,
special_labels_mode=special_labels_mode,
skip_labels=skip_labels,
nudges=nudges)
plot = r_ggplot2.ggplot(r_data)
plot += r_ggplot2.theme_minimal(base_size=base_size)
plot += r_ggplot2.theme(
**{
'panel.grid.major':
r_ggplot2.element_blank(),
'panel.grid.minor':
r_ggplot2.element_blank(),
'panel.border':
r_ggplot2.element_rect(fill=robjects.rinterface.NA, color="black")
})
plot += r_ggplot2.theme(
text=r_ggplot2.element_text(family='Helvetica', face='plain'))
plot += r_ggplot2.theme(
**{
'plot.title': r_ggplot2.element_text(hjust=0.5),
# 'axis.title.y': r_ggplot2.element_text((t = 0, r = 20, b = 0, l = 0)),
})
aes_points = r_ggplot2.aes_string(x=x, y=y, color='group')
scale_points = r_ggplot2.scale_colour_manual(
aes_points,
values=r_label_palette(
r_like_data,
special_palette,
color_background=color_background,
color_significant=color_significant,
color_significant_muted=color_significant_muted))
plot += aes_points
plot += scale_points
if xlim is not None:
plot += r_ggplot2.scale_x_continuous(
labels=r_custom.formatterFunTwoDigits, limits=robjects.r.c(*xlim))
else:
plot += r_ggplot2.scale_x_continuous(
labels=r_custom.formatterFunTwoDigits)
plot += r_ggplot2.scale_y_continuous(labels=r_custom.formatterFunOneDigit)
plot += r_ggplot2.geom_hline(
yintercept=float(-np.log10(FDR_THRESHOLD_RESPONSE)),
color='#BDBDBD',
alpha=.3)
plot += r_ggplot2.geom_vline(xintercept=float(FC_THRESHOLD_RESPONSE),
color='#BDBDBD',
alpha=.3)
plot += r_ggplot2.geom_vline(xintercept=-float(FC_THRESHOLD_RESPONSE),
color='#BDBDBD',
alpha=.3)
plot += r_ggplot2.geom_point(**{'show.legend': False})
aes_text = r_ggplot2.aes_string(label='label')
plot += aes_text
plot += r_ggrepel.geom_text_repel(
aes_text,
nudge_x=r_dollar(r_data, 'nudgex'),
nudge_y=r_dollar(r_data, 'nudgey'),
size=label_size,
family='Helvetica',
**{
'show.legend': False,
'point.padding': 0.25,
'min.segment.length': 0,
#'max.iter':0,
'segment.color': '#BDBDBD'
},
)
plot += r_ggplot2.labs(x=xlabel,
y='Adjusted p value (-log10)',
title=title)
plot.plot()
##text_log+="average: "+str(rmean(test23)[0])+end
##text_log+="sum: "+str(rsum(test23)[0])+end
#
#roughbin= round(ma[0]/100)
#bins=round(roughbin/100)*100
#ma2=rmax(ed)
#dataf_subset = dataf.rx(dataf.rx2("contig").ro >= 18, true)
scales = importr('scales')
gp = ggplot2.ggplot(dataf)
#geom_histogram(aes(y = ..density..))
# ggplot2.geom_density()+\
# pp = gp + ggplot2.aes_string(x='%s(contrrr)') + ggplot2.geom_histogram()+ggplot2.scale_y_sqrt()
bins=10
teest3=robjects.r('theme(axis.text.x=element_text(angle=90))')
pp = gp + \
ggplot2.aes_string(x='Length') + \
ggplot2.geom_histogram()+\
ggplot2.ggtitle("Found IS fragment lengths")+ \
ggplot2.scale_x_continuous(name="fragment lengths, bin="+str(bins),breaks=scales.pretty_breaks(20)) +\
ggplot2.scale_y_continuous(labels=scales.comma,name="Count",breaks=scales.pretty_breaks(10))+ \
teest3
pp.plot()
robjects.r.ggsave("/Users/security/science/dna_subj_hist.pdf")
