def compute_cross_correlations(strand='sense'):
from src.cross_correlation_kernel import MNaseSeqDensityKernel
from src.cross_correlation import calculate_cross_correlation_all_chromosomes
cc_orfs = paper_orfs
cc_dir = cc_sense_chrom_dir
cross_corr_path = cross_corr_sense_path
if strand == 'antisense':
cc_orfs = antisense_orfs
cc_dir = cc_antisense_chrom_dir
cross_corr_path = cross_corr_antisense_path
mkdirs_safe([cc_dir])
nuc_kernel = MNaseSeqDensityKernel(filepath=nuc_kernel_path)
sm_kernel = MNaseSeqDensityKernel(filepath=sm_kernel_path)
triple_kernel = compute_triple_kernel(nuc_kernel)
print_fl("Cross correlating %d ORFs..." % len(cc_orfs))
cross, summary_cross = calculate_cross_correlation_all_chromosomes(
all_mnase_data, cc_orfs, nuc_kernel, sm_kernel, triple_kernel,
save_chrom_dir=cc_dir, timer=timer, log=True,
find_antisense=(strand == 'antisense'))
cross.to_hdf(cross_corr_path,
'cross_correlation', mode='w', complevel=9, complib='zlib')
summary_cross.to_csv('%s/cross_correlation_summary_%s.csv' %
(mnase_dir, strand))
print_fl("Done.")
timer.print_time()
print_fl()
def danpos():
from src.dpos_bed import create_bed_for_dpos
import os
from src.utils import run_cmd
working_dir = os.getcwd()
danpos_output = '%s/danpos/' % (OUTPUT_DIR)
mkdirs_safe([danpos_output])
danpos_path = "%s/danpos-2.2.2/danpos.py" % working_dir
# create DANPOS Bed file
mnase = pd.read_hdf(mnase_seq_path, 'mnase_data')
mnase = mnase[mnase.time == 0]
save_file = 'mnase_0.bed'
save_path = '%s/%s' % (danpos_output, save_file)
create_bed_for_dpos(mnase, save_path)
print_fl("Wrote %s" % save_path)
bash_command = "scripts/6_reviewer_mats/run_danpos.sh %s %s %s" % \
(save_file, OUTPUT_DIR, danpos_path)
output, error = run_cmd(bash_command, stdout_file=None)
danpos_calls_path = '%s/result/pooled/mnase_0.smooth.positions.xls' % \
(danpos_output)
danpos_positions = pd.read_csv(danpos_calls_path, sep='\t')
plt.hist(danpos_positions[danpos_positions.smt_value < 10000].smt_value,
bins=100)
plt.savefig("%s/danpos_smt_pos.png" % danpos_output)
danpos_positions = danpos_positions.sort_values('smt_value',
ascending=False)
top_danpos = danpos_positions.head(2500)
top_danpos = top_danpos.rename(columns={
'chr': 'chromosome',
'smt_pos': 'position'
})
from src.chromatin import collect_mnase
from src.kernel_fitter import compute_nuc_kernel
nuc_kernel = compute_nuc_kernel(mnase, top_danpos)
nuc_kernel.save_kernel("%s/danpos_kernel.json" % danpos_output)
from src.kernel_fitter import compute_triple_kernel
nuc_kernel.plot_kernel(kernel_type='nucleosome')
plt.savefig('%s/danpos_nuc_kernel.pdf' % (save_dir), transparent=True)
triple_kernel = compute_triple_kernel(nuc_kernel)
triple_kernel.plot_kernel(kernel_type='triple')
plt.savefig('%s/danpos_triple_kernel.pdf' % (save_dir), transparent=True)
def __init__(self):
park_TSS_PAS = read_park_TSS_PAS()
orfs = paper_orfs#.join(park_TSS_PAS[['PAS']])
self.typhoon_plotter = TyphoonPlotter(mnase_path=mnase_seq_path,
rna_seq_pileup_path=pileup_path,
orfs=orfs)
self.sm_kernel = MNaseSeqDensityKernel(filepath=sm_kernel_path)
self.nuc_kernel = MNaseSeqDensityKernel(filepath=nuc_kernel_path)
self.triple_kernel = compute_triple_kernel(self.nuc_kernel)
self.kernel_type = 'nucleosomal'
def main():
from src.kernel_fitter import compute_triple_kernel
(_, chrom, antisense) = \
tuple(sys.argv)
antisense = antisense.lower() == 'true'
chrom = int(chrom)
print_fl("Running cross correlation on chromosome %d, antisense: %s" %
(chrom, str(antisense)))
name = task_name(antisense)
timer = Timer()
nuc_kernel = MNaseSeqDensityKernel(filepath=nuc_kernel_path)
sm_kernel = MNaseSeqDensityKernel(filepath=sm_kernel_path)
triple_kernel = compute_triple_kernel(nuc_kernel)
print_fl("Reading MNase-seq...", end='')
all_mnase_data = pd.read_hdf(mnase_seq_path, 'mnase_data')
print_fl("Done.")
timer.print_time()
print_fl()
if not antisense:
cc_dir = cc_sense_chrom_dir
cc_orfs = read_orfs_data("%s/orfs_cd_paper_dataset.csv" % OUTPUT_DIR)
else:
cc_dir = cc_antisense_chrom_dir
cc_orfs = antisense_orfs
calculate_cross_correlation_chr(all_mnase_data,
cc_orfs,
chrom,
antisense,
nuc_kernel,
sm_kernel,
triple_kernel,
cc_dir,
log=True,
timer=timer)
child_done(name, WATCH_TMP_DIR, chrom)
def plot_entropy_example(plotter, orf, plot_span, title):
from src.chromatin import filter_mnase
from src.utils import get_orf
from src.reference_data import all_orfs_TSS_PAS
import matplotlib.pyplot as plt
span = (orf.TSS - 1000, orf.TSS + 1000)
data = filter_mnase(plotter.all_mnase_data,
span[0],
span[1],
chrom=orf.chr,
time=120)
data['orf_name'] = orf.name
data.mid = data.mid - orf.TSS
from src.kernel_fitter import compute_triple_kernel
from src.cross_correlation_kernel import MNaseSeqDensityKernel
nuc_kernel = MNaseSeqDensityKernel(filepath=nuc_kernel_path)
sm_kernel = MNaseSeqDensityKernel(filepath=sm_kernel_path)
triple_kernel = compute_triple_kernel(nuc_kernel)
from src.transformations import exhaustive_counts
from src.cross_correlation import compute_cross_correlation_metrics
win_2 = 1000
cur_wide_counts_df = exhaustive_counts((-win_2, win_2), (0, 250),
'mid',
'length',
parent_keys=['orf_name', 'time'],
data=data,
returns='wide',
log=False)
cur_cc = compute_cross_correlation_metrics(cur_wide_counts_df,
nuc_kernel,
sm_kernel,
triple_kernel,
times=[120.0])
triple_cc = cur_cc.loc['triple'].loc[orf.name].loc[120]
from src.entropy import calc_entropy
from src.plot_utils import apply_global_settings
apply_global_settings()
triple_cc_values = triple_cc[np.arange(plot_span[0],
plot_span[0] + 150)].values
value = calc_entropy(triple_cc_values)
fig, ax = plt.subplots(1, 1, figsize=(1.5, 2.5))
fig.tight_layout(rect=[0.0, 0.0, 1, 0.8])
plt.subplots_adjust(hspace=0.0, wspace=0.5)
plotter.set_span_chrom(plot_span, orf.chr)
plotter.plot_typhoon_time(ax, data, 120, scale_z=True)
ax.set_xlim(*plot_span)
ax.set_xticks([])
ax.set_yticks([])
ax.set_xticks([], minor=True)
ax.set_yticks([], minor=True)
ax.tick_params(axis='x', length=0, pad=0)
ax.tick_params(axis='y', length=0, pad=0)
x = triple_cc.index.values.astype(int)
y = triple_cc.values.astype(float)
ax.fill_between(x, y, color='#28a098')
ax.set_title("%s\n%.1f bits" % (title, value))
def misc_plots():
scatter_dpi = 200
from src.met4 import plot_timecourse
from src.chromatin_summary_plots import (
plot_combined_vs_xrate, plot_sul_prom_disorg, plot_occ_vs_xrate,
plot_disorg_vs_xrate, plot_diosorg_vs_occ, plot_frag_len_dist)
from src.cross_correlation_kernel import MNaseSeqDensityKernel
met4_dir = "%s/met4" % OUTPUT_DIR
scatters_dir = "%s/scatters" % OUTPUT_DIR
kernels_dir = "%s/kernels" % OUTPUT_DIR
mkdirs_safe([met4_dir, scatters_dir, kernels_dir])
nuc_kernel = MNaseSeqDensityKernel(filepath=nuc_kernel_path)
nuc_kernel.plot_kernel(kernel_type='nucleosome')
plt.savefig('%s/nuc_kernel.pdf' % (kernels_dir), transparent=True)
sm_kernel = MNaseSeqDensityKernel(filepath=sm_kernel_path)
sm_kernel.plot_kernel(kernel_type='small')
plt.savefig('%s/sm_kernel.pdf' % (kernels_dir), transparent=True)
from src.kernel_fitter import compute_triple_kernel
triple_kernel = compute_triple_kernel(nuc_kernel)
triple_kernel.plot_kernel(kernel_type='triple')
plt.savefig('%s/triple_kernel.pdf' % (kernels_dir), transparent=True)
from src.nucleosome_calling import plot_nuc_calls_cc
plot_nuc_calls_cc()
plt.savefig('%s/nuc_cross_cor_0_min.pdf' % (misc_figures_dir),
transparent=True)
# met4 plots
plot_timecourse(datastore)
plt.savefig('%s/met4_timecourse.pdf' % (met4_dir), transparent=True)
plot_sul_prom_disorg(datastore)
plt.savefig('%s/met4_scatter.pdf' % (met4_dir),
transparent=True,
dpi=scatter_dpi)
# scatter plots
plot_combined_vs_xrate(datastore, selected_genes)
plt.savefig('%s/combined_vs_xrate.pdf' % (scatters_dir),
transparent=True,
dpi=scatter_dpi)
plot_occ_vs_xrate(datastore, selected_genes)
plt.savefig('%s/small_vs_xrate.pdf' % (scatters_dir),
transparent=True,
dpi=scatter_dpi)
plot_disorg_vs_xrate(datastore, selected_genes)
plt.savefig('%s/disorg_vs_xrate.pdf' % (scatters_dir),
transparent=True,
dpi=scatter_dpi)
plot_diosorg_vs_occ(datastore, selected_genes)
plt.savefig('%s/disorg_vs_small.pdf' % (scatters_dir),
transparent=True,
dpi=scatter_dpi)
plot_ORFs_len(misc_figures_dir)
plot_coverage(misc_figures_dir)
global plotter
if plotter is None:
plotter = get_plotter()
# plot sampled mnase data
plot_frag_len_dist(plotter.all_mnase_data)
plt.savefig("%s/frag_length_distribution.pdf" % misc_figures_dir,
transparent=True)
print_fl("Load all MNase-seq data for fragment length distributions")
all_mnase_data = pd.read_hdf('%s/mnase_seq_merged_all.h5.z' % mnase_dir,
'mnase_data')
repl1_mnase = all_mnase_data[all_mnase_data['source'] == 'dm498_503']
repl2_mnase = all_mnase_data[all_mnase_data['source'] == 'dm504_509']
print_fl("Done.")
plot_frag_len_dist(repl1_mnase, "Replicate 1", normalize=True)
plt.savefig('%s/frag_length_distribution_repl1.pdf' % misc_figures_dir,
transparent=True)
plot_frag_len_dist(repl2_mnase, "Replicate 2", normalize=True)
plt.savefig('%s/frag_length_distribution_repl2.pdf' % misc_figures_dir,
transparent=True)