def modisco_table(modisco_dir,
contrib_scores,
output_dir,
report_url=None,
contribsf=None,
footprint_width=200):
"""Write the pattern table to as .html and .csv
"""
plt.switch_backend('agg')
from bpnet.modisco.table import ModiscoData, modisco_table, write_modisco_table
from bpnet.modisco.motif_clustering import hirearchically_reorder_table
add_file_logging(output_dir, logger, 'modisco-table')
print("Loading required data")
data = ModiscoData.load(modisco_dir,
contrib_scores,
contribsf=contribsf,
footprint_width=footprint_width)
print("Generating the table")
df = modisco_table(data)
print("Writing the results")
write_modisco_table(df, output_dir, report_url, 'pattern_table')
print("Writing clustered table")
write_modisco_table(hirearchically_reorder_table(df, data.tasks),
output_dir, report_url, 'pattern_table.sorted')
print("Writing footprints")
profiles = OrderedDict([(pattern, {
task: data.get_profile_wide(pattern, task).mean(axis=0)
for task in data.tasks
}) for pattern in data.mf.pattern_names()])
write_pkl(profiles, Path(output_dir) / 'footprints.pkl')
print("Done!")
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>/")