def regression_plots():
from src.regression_compare import plot_compare_r2, load_results
from src.gp import plot_res_distribution, plot_res_distribution_time
from src.gp import GP
gp_dir = "%s/gp" % OUTPUT_DIR
mkdirs_safe([gp_dir])
# plot comparison
plot_compare_r2(gp_dir)
plt.savefig('%s/compare_gp_r2.pdf' % gp_dir, transparent=True)
plot_compare_r2(gp_dir, show_legend=True)
plt.savefig('%s/compare_gp_r2_legend.pdf' % gp_dir, transparent=True)
from src.gp import plot_res_distribution_time, plot_res_distribution, GP
results = load_results(gp_dir)
for name in ['Full']:
cur = GP(name, results_path='%s/%s_results.csv' % (gp_dir, name))
plot_res_distribution(cur, selected_genes=selected_genes)
plt.savefig('%s/%s_predictions.pdf' % (gp_dir, name), transparent=True)
for time in [7.5, 30, 120]:
plot_res_distribution_time(cur,
time,
selected_genes=selected_genes)
plt.savefig('%s/%s_%s.pdf' % (gp_dir, name, time),
transparent=True,
dpi=100)
def summary_plots():
orfs = paper_orfs
orf_cc = pd.read_hdf(cross_corr_sense_path, 'cross_correlation')
sum_plotter = SummaryPlotter(datastore, orfs, orf_cc)
show_saved_plot = False
custom_lims = {'TAD2': [(-3, 3), (-3, 3)], 'MET31': [(-2.5, 2.5), (-8, 8)]}
cc_dir = '%s/cc' % OUTPUT_DIR
lines_dir = '%s/lines' % OUTPUT_DIR
mkdirs_safe([cc_dir, lines_dir])
sum_plotter.write_gene_plots(genes,
cc_dir=cc_dir,
lines_dir=lines_dir,
show_plot=show_saved_plot,
custom_lims=custom_lims)
sum_plotter.write_gene_plots(['HSP26'],
cc_dir=cc_dir,
lines_dir=lines_dir,
show_plot=show_saved_plot,
custom_lims=custom_lims,
suffix='_figure',
large_font=True)
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 plot_heatmaps():
from config import OUTPUT_DIR
from src.chromatin_metrics_data import pivot_metric
from src.chromatin_heatmaps import ChromatinHeatmaps
heatmaps = ChromatinHeatmaps(datastore)
write_dir = '%s/heatmaps' % OUTPUT_DIR
mkdirs_safe([write_dir])
heatmaps.show_xlabels = True
heatmaps.show_saved_plot = False
heatmaps.plot_heatmap(write_path=("%s/all.png" % write_dir),
aspect_scale=25.,
fig_height=20.,
lines=[200, -200])
heatmaps.show_xlabels = False
small_heatmap_scale = 15.
heatmaps.plot_heatmap(head=200,
write_path=("%s/t100.png" % write_dir),
aspect_scale=small_heatmap_scale,
lines=[-20])
heatmaps.show_xlabels = True
heatmaps.plot_heatmap(tail=200,
write_path=("%s/b100.png" % write_dir),
aspect_scale=small_heatmap_scale,
lines=[20])
heatmaps.show_xlabels = False
heatmaps.plot_gene_names = True
heatmaps.plot_heatmap(head=20,
write_path=("%s/t20.png" % write_dir),
aspect_scale=small_heatmap_scale)
heatmaps.show_xlabels = True
heatmaps.plot_heatmap(tail=20,
write_path=("%s/b20.png" % write_dir),
aspect_scale=small_heatmap_scale)
heatmaps.plot_gene_names = False
from src import plot_utils
heatmaps.plot_colorbars(write_path='%s/cbar.png' % write_dir)
from src import met4
heatmaps.show_saved_plot = True
heatmaps.plot_gene_names = True
heatmaps.plot_heatmap(orf_groups=met4.orf_groups(),
group_names=met4.groups(),
group_colors=met4.group_colors(),
write_path=("%s/sulfur.pdf" % write_dir),
fig_height=11,
aspect_scale=5000.,
highlight_max=[],
y_padding=1)
heatmaps.plot_gene_names = False
def main():
print_fl("*******************************")
print_fl("* 6 Reviewer Materials *")
print_fl("*******************************")
print_preamble()
mkdirs_safe([save_dir])
plot_utils.apply_global_settings()
# plots for shift edge analysis
shift_edge_analysis.main()
# additional scatter plots
scatters()
xrate_vs_TPM()
# danpos
danpos()
# OD curve
plot_OD_curve()
def tf_plots():
global plotter
from src.small_peak_calling import SmallPeakCalling
from src.utils import mkdir_safe
from src.small_peak_calling import plot_tf_scatter, plot_tf_heatmap, \
plot_tf_summary
from src.small_peak_calling import plot_colorbars
small_peaks = SmallPeakCalling()
small_peaks.load_data()
save_dir = '%s/tf_analysis' % OUTPUT_DIR
mkdir_safe(save_dir)
plot_tf_scatter(small_peaks, t1=60)
plt.savefig('%s/small_peaks_0_60.pdf' % save_dir, transparent=True)
plot_tf_summary(small_peaks, tail=small_peaks.view_low)
plt.savefig('%s/tf_means_bottom.pdf' % save_dir, transparent=True)
plot_tf_summary(small_peaks, head=small_peaks.view_high)
plt.savefig('%s/tf_means_top.pdf' % save_dir, transparent=True)
plot_tf_summary(small_peaks)
plt.savefig('%s/tf_means.pdf' % save_dir, transparent=True)
# plot Aft1/Aft2 peaks
labeled_peaks = small_peaks.all_motifs.copy()
labeled_peaks = labeled_peaks[labeled_peaks.tf.isin(
['AFT1', 'AFT2'])][['orf', 'peak']].drop_duplicates()
labeled_peaks = labeled_peaks.merge(paper_orfs[['name']],
left_on='orf',
right_on='orf_name')
labeled_peaks = labeled_peaks.set_index('peak')
selected_labeled_peaks = labeled_peaks[labeled_peaks['name'].isin(
['LEE1', 'SER33', 'ENB1'])]
fig, ax = plot_tf_scatter(small_peaks,
tf_names=['AFT1', 'AFT2'],
labeled_peaks=selected_labeled_peaks,
t1=60.0)
plt.savefig("%s/aft1_aft2_scatter.pdf" % save_dir, transparent=True)
# typhoon dir
save_typhoon_dir = '%s/tf_analysis/typhoon/' % OUTPUT_DIR
save_dir_all_motifs = '%s/tf_analysis/typhoon_all_motifs/' % OUTPUT_DIR
mkdirs_safe([save_typhoon_dir, save_dir_all_motifs])
if plotter is None:
plotter = get_plotter()
aft_genes = ['SER33', 'LEE1', 'ENB1']
plotter.plot_genes(aft_genes,
save_typhoon_dir,
save_dir_all_motifs,
times=[0.0, 30.0, 60.0],
titlesize=34)
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 save_data(self):
save_dir = '%s/tf_analysis' % OUTPUT_DIR
mkdirs_safe([save_dir])
print_fl("Saving %s" % save_dir)
self.all_peaks.to_csv('%s/all_peaks.csv' % save_dir)
self.linked_peaks_normalized.to_csv('%s/linked_peaks_norm.csv' % save_dir)
self.linked_peaks.to_csv('%s/linked_peaks.csv' % save_dir)
self.prom_peaks.to_csv('%s/prom_peaks.csv' % save_dir)
self.all_motifs.to_csv('%s/all_motifs.csv' % save_dir)
def locus_plots():
"""Merge typhoon, cc, and line plots into a single pdf"""
from src.pdf_utils import merge_locus_pdf
save_dir = '%s/locus_plots' % OUTPUT_DIR
mkdirs_safe([save_dir])
for gene_name in genes:
write_path = '%s/locus_%s.pdf' % (save_dir, gene_name)
merge_locus_pdf(OUTPUT_DIR, gene_name, write_path)
def __init__(self, name, parent_watch_dir, num_wait, sleep_time=600,
timer=None):
self.name = name
self.watch_dir = parent_watch_dir + '/' + name
self.num_wait = num_wait
self.sleep_time = sleep_time
self.timer = timer
# create directory to watch for slurm jobs to finish
mkdirs_safe([self.watch_dir])
def main():
"""
Initial BAM data download and conversion to dataframes
1. Download RNA-seq and MNase-seq BAM files to disk
2. Read RNA-seq BAM convert to dataframe and save
3. Compute RNA-seq pileup and save
4. Read MNase-seq BAM duplicates
5. Merged, sample, and save
Inputs:
- output directory path
- RNA-seq BAM files path
- MNase-seq BAM files path
Output:
- RNA-seq data frame of reads
- RNA-seq pileup data frame
- MNase-seq merged data frame
"""
print_fl("*******************************")
print_fl("* 1 Initialization *")
print_fl("*******************************")
# ------ Setup -------------
print_preamble()
# Make directories
mkdirs_safe([
rna_bam_rep1_dir, mnase_bam_rep2_dir, mnase_bam_rep1_dir,
rna_dir, mnase_dir
])
# ------- Download BAM files to disk ------------
print_fl("\n------- Downloading dataset ----------\n")
download_bam()
print_fl("\n------- RNA-seq ----------\n")
init_rna_seq()
print_fl("\n------- MNase-seq ----------\n")
init_mnase_seq()
print_fl("Data initialization done. Time elapsed: %s" % timer.get_time())
def call_p123_nucleosomes(strand='sense'):
from src.nucleosome_linkages import call_all_nucleosome_p123
# relevant cross correlation directory
p123_orfs = paper_orfs
save_chrom_dir = sense_nuc_chrom_dir
cc_dir = cc_sense_chrom_dir
p1_path, p2_path, p3_path = (
p1_sense_path,
p2_sense_path,
p3_sense_path
)
if strand == 'antisense':
p123_orfs = antisense_orfs
save_chrom_dir = anti_nuc_chrom_dir
cc_dir = cc_antisense_chrom_dir
p1_path, p2_path, p3_path = (
p1_antisense_path,
p2_antisense_path,
p3_antisense_path
)
mkdirs_safe([save_chrom_dir])
print_fl("Calling +1, +2, and +3 nucleosomes...", end='\n')
linkages, p123_orfs = call_all_nucleosome_p123(p123_orfs,
(strand=='antisense'), cc_dir, save_chrom_dir, timer)
linkages.to_csv('%s/called_orf_nucleosomes_%s.csv' % (mnase_dir, strand))
p123_orfs.to_csv('%s/called_orf_p123_nucleosomes_%s.csv' % (mnase_dir, strand))
p1 = nucleosome_linkages.convert_to_pos_time_df(p123_orfs, linkages, '+1')
p2 = nucleosome_linkages.convert_to_pos_time_df(p123_orfs, linkages, '+2')
p3 = nucleosome_linkages.convert_to_pos_time_df(p123_orfs, linkages, '+3')
p1.to_csv(p1_path)
p2.to_csv(p2_path)
p3.to_csv(p3_path)
print_fl('Done.')
timer.print_time()
print_fl()
def compute_organization_measures(strand='sense'):
from src.entropy import calculate_cc_summary_measure
orfs = paper_orfs
if strand == 'antisense':
orfs = antisense_orfs
mkdirs_safe([sense_entropy_dir, anti_entropy_dir])
print_fl("Loading cross correlation")
cross = pd.read_hdf('%s/cross_correlation_%s.h5.z' %
(mnase_dir, strand), 'cross_correlation')
print_fl("Calculating entropy %d ORFS..." % len(orfs))
entropies = calculate_cc_summary_measure(orfs, cross, strand,
timer)
entropies = entropies.round(3)
entropies.to_csv('%s/orf_%s_entropies.csv' % (mnase_dir, strand))
timer.print_time()
print_fl()
def typhoon_plots():
global plotter
plotter = get_plotter()
save_dir = '%s/typhoon' % OUTPUT_DIR
save_dir_all_motifs = '%s/typhoon_all_motifs' % OUTPUT_DIR
mkdirs_safe([save_dir, save_dir_all_motifs, misc_figures_dir])
figwidths = {'MCD4': 12, 'APJ1': 12}
paddings = {'MCD4': (1000, 2000), 'APJ1': (1000, 2000)}
print_fl("Plotting typhoons...", end='')
plotter.plot_genes(genes,
save_dir,
save_dir_all_motifs,
figwidths=figwidths,
paddings=paddings)
print_fl("Done.")
timer.print_time()
# example plots
print_fl("Plotting examples...", end='')
draw_example_mnase_seq(plotter, misc_figures_dir)
draw_example_rna_seq(plotter, misc_figures_dir)
# plot_example_cross(plotter, misc_figures_dir)
print_fl("Done.")
timer.print_time()
# Hsp26 plot for figure 1
plotter.plot_genes(['HSP26'],
save_dir,
None,
times=[0.0, 30.0, 60.0, 120.0],
prefix='fig_')
def shift_plots():
from src.nucleosome_calling import plot_p123
from src.reference_data import read_sgd_orf_introns, read_sgd_orfs
from src.reference_data import read_park_TSS_PAS
from src.summary_plotter import SummaryPlotter
global plotter
orf_cc = pd.read_hdf(cross_corr_sense_path, 'cross_correlation')
all_orfs = all_orfs_TSS_PAS()
sum_plotter = SummaryPlotter(datastore, all_orfs, orf_cc)
if plotter is None:
plotter = get_plotter()
save_dir = '%s/shift' % OUTPUT_DIR
mkdirs_safe([save_dir])
shift_genes = ['RPS7A']
for gene_name in shift_genes:
fig = plot_p123(gene_name, orf_cc, plotter, sum_plotter, save_dir)
p1 = datastore.p1_shift[[120.0]]
p2 = datastore.p2_shift[[120.0]]
p3 = datastore.p3_shift[[120.0]]
p12 = p1.join(p2, lsuffix='_+1', rsuffix='_+2')
p23 = p2.join(p3, lsuffix='_+2', rsuffix='_+3')
from src.chromatin_summary_plots import plot_distribution
x = datastore.p1_shift[120]
y = datastore.transcript_rate_logfold.loc[x.index][120.0]
model = plot_distribution(x,
y,
'$\\Delta$ +1 nucleosome shift',
'$\log_2$ fold-change transcription rate',
title='+1 shift vs transcription, 0-120 min',
xlim=(-40, 40),
ylim=(-8, 8),
xstep=10,
ystep=2,
pearson=True,
s=10)
plt.savefig('%s/shift_+1_xrate.pdf' % save_dir, transparent=True)
x = datastore.p1_shift[120]
y = datastore.p2_shift[120]
model = plot_distribution(x,
y,
'$\\Delta$ +1 nucleosome shift',
'$\\Delta$ +2 nucleosome shift',
title='+1, +2 nucleosome shift\n0-120 min',
xlim=(-40, 40),
ylim=(-40, 40),
xstep=10,
ystep=10,
pearson=False,
s=10)
plt.savefig('%s/shift_p12.pdf' % save_dir, transparent=True)
def determine_transcript_boundaries():
print_fl("Reading RNA-seq pileup...", end='')
rna_seq_pileup = pd.read_hdf(pileup_path, 'pileup')
print_fl("Done.")
timer.print_time()
print_fl()
from src.transcript_boundaries import compute_boundaries, load_park_boundaries
park_boundaries = load_park_boundaries()
mkdirs_safe([anti_chrom_dir, sense_chrom_dir])
# ------------- Antisense transcript boundaries ------------------
print_fl("Determining antisense boundaries...", end='')
antisense_boundaries = compute_boundaries(park_boundaries,
rna_seq_pileup,
save_dir=anti_chrom_dir,
pileup_path=pileup_path,
find_antisense=True,
log=True,
timer=timer)
# all to compare with Park
path = '%s/antisense_boundaries_computed_all.csv' % rna_dir
antisense_boundaries.to_csv(path)
# antisense paper data set
path = '%s/antisense_boundaries_computed.csv' % rna_dir
antisense_boundaries = antisense_boundaries[[
'TSS', 'strand', 'start', 'stop'
]].join(paper_orfs[['name', 'chr', 'orf_class']], how='inner')
antisense_boundaries.to_csv(antisense_orfs_path)
print_fl("Done.")
print_fl("Wrote to %s" % path)
timer.print_time()
print_fl()
# ------------- Sense transcript boundaries ------------------
# compute sense boundaries
# TODO: currently unused, only for check against Park boundaries
print_fl("Determining sense boundaries...", end='')
sense_boundaries = compute_boundaries(park_boundaries,
rna_seq_pileup,
save_dir=sense_chrom_dir,
pileup_path=pileup_path,
find_antisense=False,
log=True,
timer=timer)
# all to compare with Park
path = '%s/sense_boundaries_computed_all.csv' % rna_dir
sense_boundaries.to_csv(path)
# paper data set
path = '%s/sense_boundaries_computed.csv' % rna_dir
sense_boundaries.join(paper_orfs[[]], how='inner').to_csv(path)
print_fl("Done.")
print_fl("Wrote to %s" % path)
timer.print_time()
print_fl()
def main():
"""
Computation of chromatin metrics against sense and antisense strand
for analysis.
1. * For the sense strand for each ORF
2. Compute occupancies
3. Compute cross correlation and save these per chromosome to disk
4. Compute cross correlation summaries
5. Call nucleosomes in cross correlation window
6. Call +1, +2, and +3 nucleosomes relative to TSS
7. * Repeat 2-6 for identified for antisense TSSs
Inputs:
- MNase-seq data
- RNA-seq data
- Antisense transcript boundaries
Output:
- MNase-seq occupancy summaries for each ORF
- Per bp cross correlation scores for each ORF
- Cross correlation summary scores for each ORF
- Called nucleosomes local to each ORF
- Called +1, +2, +3 nucleosomes to each ORF
* for Sense and Antisense strands
"""
print_fl("***********************")
print_fl("* 3 Metrics *")
print_fl("***********************")
print_preamble()
# paths to save cross correlations per chromosome
mkdirs_safe([cc_sense_chrom_dir, cc_antisense_chrom_dir])
if USE_SLURM: mkdirs_safe([WATCH_TMP_DIR])
print_fl("\n------- Read inputs ----------\n")
read_input_data()
print_fl("\n------- Calculate occupancies (Sense) ----------\n")
compute_occupancies()
print_fl("\n------- Calculate cross correlation (Sense) ----------\n")
compute_cross_correlations()
print_fl("\n------- Calculate nucleosome shift (Sense) ----------\n")
call_p123_nucleosomes()
print_fl("\n------- Calculate entropy (Sense) ----------\n")
compute_organization_measures(strand='sense')
print_fl("\n------- Calculate occupancies (Antisense) ----------\n")
compute_occupancies(strand='antisense')
print_fl("\n------- Calculate cross correlation (Antisense) ----------\n")
compute_cross_correlations(strand='antisense')
print_fl("\n------- Calculate nucleosome shift (Antisense) ----------\n")
call_p123_nucleosomes(strand='antisense')
print_fl("\n------- Calculate entropy (Antisense) ----------\n")
compute_organization_measures(strand='antisense')
print_fl("\n--------- Generate data for supplemental ------------\n")
create_suppl_data()
def init_rna_seq():
rna_seq_rep1_filenames = [
"DM538_RNA_rep1_0_min.bam",
"DM539_RNA_rep1_7.5_min.bam",
"DM540_RNA_rep1_15_min.bam",
"DM541_RNA_rep1_30_min.bam",
"DM542_RNA_rep1_60_min.bam",
"DM543_RNA_rep1_120_min.bam"
]
rna_seq_rep2_filenames = [
"DM1450_RNA_rep2_0_min.bam",
"DM1451_RNA_rep2_7.5_min.bam",
"DM1452_RNA_rep2_15_min.bam",
"DM1453_RNA_rep2_30_min.bam",
"DM1454_RNA_rep2_60_min.bam",
"DM1455_RNA_rep2_120_min.bam"
]
from src.read_bam import read_rna_seq_set
from src.transcription import sample_rna
# Read replicate 1
print_fl("Reading Replicate 1 RNA-seq BAM...", end='')
rna_seq_rep1 = read_rna_seq_set(rna_bam_rep1_dir, rna_seq_rep1_filenames,
source='dm538_dm543',
debug=DEBUG)
print_fl("Done.")
timer.print_time()
print_fl()
# Read replicate 2
print_fl("Reading Replicate 2 RNA-seq BAM...", end='')
rna_seq_rep2 = read_rna_seq_set(rna_bam_rep2_dir, rna_seq_rep2_filenames,
source='dm1450_dm1455',
debug=DEBUG)
print_fl("Done.")
timer.print_time()
print_fl()
# depth of each dataset
rep1_depth = rna_seq_rep1[['chr', 'time']].groupby('time').count()\
.rename(columns={'chr':'count'})
rep2_depth = rna_seq_rep2[['chr', 'time']].groupby('time').count()\
.rename(columns={'chr':'count'})
print_fl("Rep1 read depth:\n" + str(rep1_depth), end='\n\n')
print_fl("Rep2 read depth:\n" + str(rep2_depth), end='\n\n')
sample_rep1_depth = rep1_depth['count'].min()
sample_rep2_depth = rep2_depth['count'].min()
print_fl("Sampling Rep1 to %d for each time point..." %
sample_rep1_depth, end='')
rep1_sampled = sample_rna(rna_seq_rep1, sample_rep1_depth)
print_fl("Done.")
timer.print_time()
print_fl()
print_fl("Sampling Rep2 to %d for each time point..." %
sample_rep2_depth, end='')
rep2_sampled = sample_rna(rna_seq_rep2, sample_rep2_depth)
print_fl("Done.")
timer.print_time()
print_fl()
# Merge replicates
print_fl("Merging RNA-seq files...", end='')
merged_rna = rna_seq_rep1.append(rna_seq_rep2)
merged_rna = merged_rna[['chr', 'start',
'stop', 'length', 'strand', 'time', 'source']].sort_values(
['source', 'time', 'chr', 'start'])
print_fl("Done.")
timer.print_time()
print_fl()
# Merge sampled replicates
print_fl("Merging RNA-seq files...", end='')
merged_rna_sampled = rep1_sampled.append(rep2_sampled)
merged_rna_sampled = merged_rna_sampled[['chr', 'start',
'stop', 'length', 'strand', 'time', 'source']].sort_values(
['source', 'time', 'chr', 'start'])
print_fl("Done.")
timer.print_time()
print_fl()
# Save to all RNA-seq data to disk
save_path = '%s/rnase_seq_all.h5.z' % rna_dir
print_fl("Saving merged RNase-seq to %s..." % save_path, end='')
merged_rna.to_hdf(save_path, 'rna_seq_data', mode='w', complevel=9,
complib='zlib')
# Save merged data to disk
save_path = '%s/rnase_seq_merged_sampled.h5.z' % rna_dir
print_fl("Saving merged RNase-seq to %s..." % save_path, end='')
merged_rna_sampled.to_hdf(save_path, 'rna_seq_data', mode='w', complevel=9,
complib='zlib')
print_fl("Done.")
timer.print_time()
print_fl()
# convert to pileup dataframe
mkdirs_safe([pileup_chrom_dir])
print_fl("Calculating RNA-seq pileup...", end='')
from src.rna_seq_pileup import calculate_rna_seq_pileup
pileup = calculate_rna_seq_pileup(merged_rna_sampled, timer)
print_fl("Done.")
timer.print_time()
print_fl()
save_path = pileup_path
print_fl("Saving RNA-seq pileup to %s..." % save_path, end='')
pileup.to_hdf(save_path, 'pileup', mode='w', complevel=9, complib='zlib')
print_fl("Done.")
timer.print_time()
print_fl()
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)
def antisense_plots():
from src.antisense_analysis import plot_antisense_vs_sense
from src.antisense_analysis import plot_bar_counts, plot_antisense_dist
save_dir = '%s/antisense' % OUTPUT_DIR
mkdirs_safe([save_dir])
antisense_TPM = read_orfs_data('%s/antisense_TPM.csv' % rna_dir)
antisense_TPM_logfold = read_orfs_data('%s/antisense_TPM_log2fold.csv' %
rna_dir)
plot_antisense_vs_sense(
antisense_TPM_logfold,
datastore.transcript_rate_logfold,
120.0,
highlight=['MET31', 'CKB1', 'RPS7A', 'YBR241C', 'UTR2'])
plt.savefig('%s/sense_antisense_distr.pdf' % save_dir,
transparent=True,
dpi=100)
plot_bar_counts(antisense_TPM_logfold, datastore.transcript_rate_logfold)
plt.savefig('%s/sense_antisense_counts.pdf' % save_dir)
plot_antisense_dist(antisense_TPM_logfold)
plt.savefig('%s/antisense_logfc_dist.pdf' % save_dir)
from src.antisense_analysis import plot_antisense_lengths, plot_antisense_calling
rna_seq_pileup = pd.read_hdf('%s/rna_seq_pileup.h5.z' % rna_dir, 'pileup')
antisense_boundaries = read_orfs_data(
'%s/antisense_boundaries_computed.csv' % rna_dir)
plot_antisense_lengths()
plt.savefig('%s/antisense_lengths_dist.pdf' % save_dir)
plot_antisense_calling('MET31', rna_seq_pileup)
plt.savefig('%s/antisense_met31_calling.pdf' % save_dir)
from src.chromatin_summary_plots import plot_distribution
anti_datastore = ChromatinDataStore(is_antisense=True)
x = anti_datastore.promoter_sm_occupancy_delta.mean(axis=1)
y = anti_datastore.antisense_TPM_logfold.mean(axis=1).loc[x.index]
model = plot_distribution(
x,
y,
'$\\Delta$ Antisense promoter occupancy',
'Log$_2$ fold-change antisense transcript',
highlight=[],
title='Promoter occupancy vs transcription (Antisense)',
xlim=(-1.5, 1.5),
ylim=(-4, 4),
xstep=0.5,
ystep=1)
plt.savefig('%s/antisense_chrom_dist_prom_vs_xrate.pdf' % save_dir)
x = anti_datastore.gene_body_disorganization_delta.mean(axis=1).dropna()
y = anti_datastore.antisense_TPM_logfold.loc[x.index].mean(
axis=1).loc[x.index]
model = plot_distribution(
x,
y,
'$\\Delta$ antisense nucleosome disorganization',
'Log$_2$ fold-change antisense transcripts',
highlight=[],
title='Nuc. disorganization vs transcription (Antisense)',
xlim=(-1.5, 1.5),
ylim=(-4, 4),
xstep=0.5,
ystep=1)
plt.savefig('%s/antisense_chrom_dist_disorg_vs_xrate.pdf' % save_dir)