def plot_example_cross(plotter, save_dir):
from src.chromatin import filter_mnase
from src.plot_utils import apply_global_settings
from config import cross_corr_sense_path
from src.utils import get_orf
orf_cc = pd.read_hdf(cross_corr_sense_path, 'cross_correlation')
orfs = plotter.orfs
gene = get_orf('APJ1', orfs)
span = (gene.TSS - 500, gene.TSS + 500)
plotter.set_span_chrom(span, gene.chr)
cc_nuc = orf_cc.loc['nucleosomal'].loc[gene.name].loc[0.0]
cc_small = orf_cc.loc['small'].loc[gene.name].loc[0.0]
data = filter_mnase(plotter.all_mnase_data,
span[0],
span[1],
chrom=gene.chr,
time=0)
fig, (ax, leg_ax) = plt.subplots(2, 1, figsize=(5, 6))
fig.tight_layout(rect=[0.1, 0.1, 0.92, 0.945])
plt.subplots_adjust(hspace=0.0, wspace=0.5)
plotter.plot_typhoon_time(ax, data, 0, scale_z=True)
ax.set_xlim(*span)
ax.set_xticks(np.arange(span[0], span[1], 500))
ax.set_xticks(np.arange(span[0], span[1], 100), minor=True)
ax.set_xlabel("Position (bp)", fontsize=16)
ax.set_ylabel("Fragment length (bp)", fontsize=16, labelpad=10)
ax.set_ylim(-100, 250)
draw_legend(leg_ax, span, 500)
cc_ax = ax.twinx()
cc_ax.set_ylabel("Cross correlation $\\times$0.1",
rotation=270,
fontsize=16,
labelpad=10,
va='bottom')
scale_cc = 1
y_origin = 0
x = cc_nuc.index + gene.TSS
y = cc_nuc.values * scale_cc + y_origin
cc_ax.fill_between(x, y, y_origin, color='#28a098')
y = -cc_small.values * scale_cc + y_origin
cc_ax.fill_between(x, y_origin, y, color='#f28500')
cc_ax.set_ylim(-0.1, 0.4)
cc_ax.set_yticklabels(np.arange(-1, 5))
write_path = '%s/%s.pdf' % (save_dir, 'example_cross_correlation')
plt.savefig(write_path, transparent=True)
print_fl("Wrote %s" % write_path)
def get_linkages_cc(orf_cc, gene_name, orfs):
orf = get_orf(gene_name, orfs)
cur_cc = orf_cc.loc['diff'].loc[orf.name]
nucs = call_orf_nucleosomes(orf_cc.loc['diff'], orf)
linkages = find_linkages(nucs)
return cur_cc, linkages, nucs
def entropy_examples():
all_orfs = all_orfs_TSS_PAS()
global plotter
if plotter is None:
plotter = get_plotter()
from src.entropy import plot_entropy_example
orf = get_orf('CLF1', all_orfs)
plot_entropy_example(plotter, orf, (-460, 40), "Low entropy")
plt.savefig('%s/low_entropy.pdf' % (misc_figures_dir), dpi=100)
from src.entropy import plot_entropy_example
orf = get_orf('HSP26', all_orfs)
plot_entropy_example(plotter, orf, (200, 700), "High entropy")
plt.savefig('%s/high_entropy.pdf' % (misc_figures_dir), dpi=100)
def plot_p123(gene_name, orf_cc, plotter, sum_plotter, save_dir):
from src.nucleosome_linkages import plot_linkages_cc, get_linkages_cc, find_p123_gene
from src.utils import get_orf
plot_linkages_lines = False
orf = get_orf(gene_name)
cur_cc, linkages, _ = get_linkages_cc(orf_cc, gene_name, plotter.orfs)
p1, p2, p3 = find_p123_gene(orf, linkages)
if plot_linkages_lines:
plot_linkages = linkages[linkages.link.isin([p1, p2, p3])]
plot_linkages_cc(cur_cc, plot_linkages)
plotter.disable_mnase_seq = False
min_cc_plotting = -1
plot_linkages = linkages[linkages.link.isin([p1, p2, p3])]
plot_linkages = plot_linkages[
plot_linkages.cross_correlation > min_cc_plotting]
# typhoon plot of linkages
plotter.linkages = plot_linkages
fig, time_ax, twen_axs = plotter.plot_gene(gene_name,
figwidth=12,
padding=(500, 1000),
highlight=False,
dpi=100,
save_dir=save_dir,
prefix='typhoon_shift_')
plt.close(fig)
# get nucleosome positions by time and linkage
# TODO: use this data structure for typhoon plot
time_mids = pd.DataFrame()
for p_nuc in [p1, p2, p3]:
p_pos = linkages[linkages.link == p_nuc]
cur_mids = linkages[linkages.link == p_nuc][['time', 'mid']]
cur_mids['link'] = p_nuc
time_mids = time_mids.append(cur_mids)
# plot cross correlation
sum_plotter.set_gene(gene_name)
write_path = "%s/cc_%s.pdf" % (save_dir, gene_name)
fig = sum_plotter.plot_cross_correlation_heatmap(
show_colorbar=True,
title='$\it{' + gene_name + '}$ cross correlation',
nucs=time_mids)
plt.savefig(write_path, transparent=False)
plt.close(fig)
def plot_small_peaks(gene, all_peaks, plotter):
all_orfs = all_orfs_TSS_PAS()
orf_name = get_orf_name(gene)
orf = get_orf(orf_name, all_orfs)
span = orf.TSS - 1000, orf.TSS + 1000
plotter.set_span_chrom(span, orf.chr)
plotter.dpi = 100
fig, axs, tween_axs = plotter.plot()
for i in range(len(times)):
time = times[i]
ax = axs[i]
data = all_peaks[(all_peaks.cross_correlation > 0.05) &
(all_peaks.orf == orf.name) &
(all_peaks.time == time)]
ax.scatter(data.original_mid, data.cross_correlation+10.0)
def set_gene(self, gene_name):
orf = get_orf(gene_name, paper_orfs)
self.orf = orf
self.gene_name = gene_name
mnase = self.typhoon_plotter.all_mnase_data
# default cross correlation
cur_wide_counts_df, cur_cc = calculate_cross_correlation_orf(self.orf,
mnase, 3000, self.nuc_kernel, self.sm_kernel, self.triple_kernel)
self.cur_cc = cur_cc
self.cur_wide_counts_df = cur_wide_counts_df
times = self.typhoon_plotter.times
orf_entropies = []
for i in range(len(times)):
time = times[i]
orf_cc = cur_cc.loc[self.kernel_type].loc[orf.name].loc[time]
cur_e = calc_entropy(orf_cc[np.arange(self.e_range[0], self.e_range[1]+1)])
orf_entropies.append(cur_e)
self.orf_entropies = orf_entropies
def set_gene(self, gene_name):
gene = get_orf(gene_name)
self.gene = gene
self.get_cc()
def plot_antisense_calling(gene_name, rna_seq_pileup):
from src.rna_seq_plotter import get_smoothing_kernel
from src.plot_utils import apply_global_settings
from src.utils import get_orf
from src.transcription import filter_rna_seq
from src.transcription import filter_rna_seq_pileup
from src.transcript_boundaries import load_park_boundaries
from src.plot_orf_annotations import ORFAnnotationPlotter
from config import paper_orfs
from src.reference_data import read_sgd_orfs, read_park_TSS_PAS
from src.datasets import read_orfs_data
all_orfs = read_sgd_orfs()
all_orfs = all_orfs.join(read_park_TSS_PAS()[['TSS', 'PAS']])
orfs_plotter = ORFAnnotationPlotter(orfs=all_orfs)
antisense_boundaries = read_orfs_data('%s/antisense_boundaries_computed.csv' % rna_dir)
park_boundaries = load_park_boundaries()
park_boundaries = park_boundaries.join(paper_orfs[['name']])
orf = get_orf(gene_name, park_boundaries)
search_2 = 1000
span = orf.transcript_start-search_2, orf.transcript_stop+search_2
gene_pileup = filter_rna_seq_pileup(rna_seq_pileup,
span[0], span[1], orf.chr)
plot_span = span
gene = orf
gene_rna_seq = gene_pileup
apply_global_settings(30)
fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(6, 5.))
fig.tight_layout(rect=[0.1, 0, 1, 0.85])
orfs_plotter.set_span_chrom(plot_span, gene.chr)
orfs_plotter.plot_orf_annotations(ax1)
sense_data = gene_rna_seq[gene_rna_seq.strand == '+']
antisense_data = gene_rna_seq[gene_rna_seq.strand == '-']
sense_data = np.log2(sense_data.groupby('position').sum()+1).pileup
antisense_data = np.log2(antisense_data.groupby('position').sum()+1).pileup
smooth_kernel = get_smoothing_kernel(100, 20)
sense_strand = '+' if gene.strand == '+' else '-'
antisense_strand = '+' if sense_strand == '-' else '-'
x = sense_data.index
sense_data = np.convolve(sense_data, smooth_kernel, mode='same')
antisense_data = np.convolve(antisense_data, smooth_kernel, mode='same')
ax2.plot(x, sense_data, color=plt.get_cmap('Blues')(0.5))
ax2.plot(x, -antisense_data, color=plt.get_cmap('Reds')(0.5))
ax2.set_xlim(*plot_span)
ax2.set_ylim(-15, 15)
ax2.axhline(0, color='black')
if gene.name in antisense_boundaries.index:
anti_gene = antisense_boundaries.loc[gene.name]
y_plot = 0, 20 if gene.strand == '-' else -20, 0
ax2.plot([anti_gene.start, anti_gene.start],
[y_plot[0], y_plot[1]], color='red', linewidth=2.5, solid_capstyle='butt')
ax2.plot([anti_gene.stop, anti_gene.stop],
[y_plot[0], y_plot[1]], color='red', linewidth=2.5, solid_capstyle='butt')
ax2.set_xticks(np.arange(plot_span[0], plot_span[1], 500))
ax2.set_xticklabels([])
_ = ax2.set_xticks(np.arange(plot_span[0], plot_span[1], 100), minor=True)
ax2.tick_params(labelsize=14)
ax2.set_ylabel("Sum log$_2$ (pileup+1)", fontsize=15)
ax2.set_xlabel("Position (bp)", fontsize=15)
ax1.set_title("Calling antisense transcripts", fontsize=26)
ax2.axvline(383344)
ax2.axvline(384114)