def modisco_export_seqlets(modisco_dir, output_dir, trim_frac=0.08):
from pybedtools import Interval
from bpnet.modisco.files import ModiscoFile
add_file_logging(output_dir, logger, 'modisco_export_seqlets')
ranges = load_ranges(modisco_dir)
example_intervals = [
Interval(row.chrom, row.start, row.end)
for i, row in ranges.iterrows()
]
r = ModiscoFile(os.path.join(modisco_dir, "modisco.h5"))
r.export_seqlets_bed(output_dir,
example_intervals=example_intervals,
position='absolute',
trim_frac=trim_frac)
r.close()
def chip_nexus_analysis(modisco_dir,
trim_frac=0.08,
num_workers=20,
run_cwm_scan=False,
force=False,
footprint_width=200):
"""Compute all the results for modisco specific for ChIP-nexus/exo data. Runs:
- modisco_plot
- modisco_report
- modisco_table
- modisco_export_patterns
- cwm_scan
- modisco_export_seqlets
Note:
All the sub-commands are only executed if they have not been ran before. Use --force override this.
Whether the commands have been run before is deterimined by checking if the following file exists:
`{modisco_dir}/.modisco_report_all/{command}.done`.
"""
plt.switch_backend('agg')
from bpnet.utils import ConditionalRun
modisco_dir = Path(modisco_dir)
# figure out the contribution scores used
kwargs = read_json(modisco_dir / "modisco-run.kwargs.json")
contrib_scores = kwargs["contrib_file"]
mf = ModiscoFile(f"{modisco_dir}/modisco.h5")
all_patterns = mf.pattern_names()
mf.close()
if len(all_patterns) == 0:
print("No patterns found.")
# Touch modisco-chip.html for snakemake
open(modisco_dir / 'modisco-chip.html', 'a').close()
open(modisco_dir / 'seqlets/scored_regions.bed', 'a').close()
return
# class determining whether to run the command or not (poor-man's snakemake)
cr = ConditionalRun("modisco_report_all", None, modisco_dir, force=force)
sync = []
# --------------------------------------------
if (not cr.set_cmd('modisco_plot').done()
or not cr.set_cmd('modisco_enrich_patterns').done()):
# load ContribFile and pass it to all the functions
logger.info("Loading ContribFile")
contribsf = ContribFile.from_modisco_dir(modisco_dir)
contribsf.cache()
else:
contribsf = None
# --------------------------------------------
# Basic reports
if not cr.set_cmd('modisco_plot').done():
modisco_plot(modisco_dir,
modisco_dir / 'plots',
heatmap_width=footprint_width,
figsize=(10, 10),
contribsf=contribsf)
cr.write()
sync.append("plots")
if not cr.set_cmd('modisco_report').done():
modisco_report(str(modisco_dir), str(modisco_dir))
cr.write()
sync.append("modisco-chip.html")
if not cr.set_cmd('modisco_table').done():
modisco_table(modisco_dir,
contrib_scores,
modisco_dir,
report_url=None,
contribsf=contribsf,
footprint_width=footprint_width)
cr.write()
sync.append("footprints.pkl")
sync.append("pattern_table.*")
if not cr.set_cmd('modisco_export_patterns').done():
modisco_export_patterns(modisco_dir,
output_file=modisco_dir / 'patterns.pkl',
contribsf=contribsf)
cr.write()
sync.append("patterns.pkl")
# --------------------------------------------
# Finding new instances
if run_cwm_scan:
if not cr.set_cmd('cwm_scan').done():
cwm_scan(modisco_dir,
modisco_dir / 'instances.bed.gz',
trim_frac=trim_frac,
contrib_file=None,
num_workers=num_workers)
cr.write()
# --------------------------------------------
# Export bed-files and bigwigs
# Seqlets
if not cr.set_cmd('modisco_export_seqlets').done():
modisco_export_seqlets(str(modisco_dir),
str(modisco_dir / 'seqlets'),
trim_frac=trim_frac)
cr.write()
sync.append("seqlets")
# print the rsync command to run in order to sync the output
# directories to the webserver
logger.info("Run the following command to sync files to the webserver")
dirs = " ".join(sync)
print(f"rsync -av --progress {dirs} <output_dir>/")
def modisco_plot(
modisco_dir,
output_dir,
# filter_npy=None,
# ignore_dist_filter=False,
heatmap_width=200,
figsize=(10, 10),
contribsf=None):
"""Plot the results of a modisco run
Args:
modisco_dir: modisco directory
output_dir: Output directory for writing the results
figsize: Output figure size
contribsf: [optional] modisco contribution score file (ContribFile)
"""
plt.switch_backend('agg')
add_file_logging(output_dir, logger, 'modisco-plot')
from bpnet.plot.vdom import write_heatmap_pngs
from bpnet.plot.profiles import plot_profiles
from bpnet.utils import flatten
output_dir = Path(output_dir)
output_dir.parent.mkdir(parents=True, exist_ok=True)
# load modisco
mf = ModiscoFile(f"{modisco_dir}/modisco.h5")
if contribsf is not None:
d = contribsf
else:
d = ContribFile.from_modisco_dir(modisco_dir)
logger.info("Loading the contribution scores")
d.cache() # load all
thr_one_hot = d.get_seq()
# thr_hypothetical_contribs
tracks = d.get_profiles()
thr_hypothetical_contribs = dict()
thr_contrib_scores = dict()
# TODO - generalize this
thr_hypothetical_contribs['profile'] = d.get_hyp_contrib()
thr_contrib_scores['profile'] = d.get_contrib()
tasks = d.get_tasks()
# Count contribution (if it exists)
if d.contains_contrib_score("counts/pre-act"):
count_contrib_score = "counts/pre-act"
thr_hypothetical_contribs['count'] = d.get_hyp_contrib(
contrib_score=count_contrib_score)
thr_contrib_scores['count'] = d.get_contrib(
contrib_score=count_contrib_score)
elif d.contains_contrib_score("count"):
count_contrib_score = "count"
thr_hypothetical_contribs['count'] = d.get_hyp_contrib(
contrib_score=count_contrib_score)
thr_contrib_scores['count'] = d.get_contrib(
contrib_score=count_contrib_score)
else:
# Don't do anything
pass
thr_hypothetical_contribs = OrderedDict(
flatten(thr_hypothetical_contribs, separator='/'))
thr_contrib_scores = OrderedDict(flatten(thr_contrib_scores,
separator='/'))
# -------------------------------------------------
all_seqlets = mf.seqlets()
all_patterns = mf.pattern_names()
if len(all_patterns) == 0:
print("No patterns found")
return
# 1. Plots with tracks and contrib scores
print("Writing results for contribution scores")
plot_profiles(all_seqlets,
thr_one_hot,
tracks=tracks,
contribution_scores=thr_contrib_scores,
legend=False,
flip_neg=True,
rotate_y=0,
seq_height=.5,
patterns=all_patterns,
n_bootstrap=100,
fpath_template=str(output_dir /
"{pattern}/agg_profile_contribcores"),
mkdir=True,
figsize=figsize)
# 2. Plots only with hypothetical contrib scores
print("Writing results for hypothetical contribution scores")
plot_profiles(all_seqlets,
thr_one_hot,
tracks={},
contribution_scores=thr_hypothetical_contribs,
legend=False,
flip_neg=True,
rotate_y=0,
seq_height=1,
patterns=all_patterns,
n_bootstrap=100,
fpath_template=str(output_dir /
"{pattern}/agg_profile_hypcontribscores"),
figsize=figsize)
print("Plotting heatmaps")
for pattern in tqdm(all_patterns):
write_heatmap_pngs(all_seqlets[pattern],
d,
tasks,
pattern,
output_dir=str(output_dir / pattern),
resize_width=heatmap_width)
mf.close()