def _wrapper(path):
p = validate_file(path)
sx = _get_size_mb(path)
if sx > max_size_mb:
raise argparse.ArgumentTypeError("Fasta file is too large {s:.2f} MB > {m:.2f} MB. Create a ReferenceSet using {e}, then import using `pbservice import-dataset /path/to/referenceset.xml` ".format(e=Constants.FASTA_TO_REFERENCE, s=sx, m=Constants.MAX_FASTA_FILE_MB))
else:
return p
def _validate_analysis_job_json(path):
px = validate_file(path)
with open(px, 'r') as f:
d = json.loads(f.read())
try:
load_analysis_job_json(d)
return px
except (KeyError, TypeError, ValueError) as e:
raise argparse.ArgumentTypeError("Invalid analysis.json format for '{p}' {e}".format(p=px, e=repr(e)))
def _validate_analysis_job_json(path):
px = validate_file(path)
with open(px, 'r') as f:
d = json.loads(f.read())
try:
load_analysis_job_json(d)
return px
except (KeyError, TypeError, ValueError) as e:
raise argparse.ArgumentTypeError("Invalid analysis.json format for '{p}' {e}".format(p=px, e=repr(e)))
def _wrapper(path):
p = validate_file(path)
sx = _get_size_mb(path)
if sx > max_size_mb:
raise argparse.ArgumentTypeError(
"Fasta file is too large {s:.2f} MB > {m:.2f} MB. Create a ReferenceSet using {e}, then import using `pbservice import-dataset /path/to/referenceset.xml` "
.format(e=Constants.FASTA_TO_REFERENCE,
s=sx,
m=Constants.MAX_FASTA_FILE_MB))
else:
return p
def _validate_report(path):
p = validate_file(path)
_ = load_report_from_json(path)
return p
def _f(path):
path = validate_file(path)
return _f(path)
def to_report(filtered_csv,
output_dir,
dpi=DEFAULT_DPI,
thumb_dpi=DEFAULT_THUMB_DPI):
"""
Run Report
"""
validate_file(filtered_csv)
validate_dir(output_dir)
aggregators = {
'nbases': SumAggregator('length'),
'nreads': CountAggregator('length'),
'mean_subreadlength': MeanSubreadLengthAggregator('length'),
'max_readlength': MaxAggregator('length'),
'n50': N50Aggregator('length'),
'readlength_histogram': HistogramAggregator('length',
0,
100,
nbins=10000),
'subread': SubreadLengthHistogram(dx=100)
}
passed_filter = lambda record: record.passed_filter is True
passed_filter_func = functools.partial(_apply, [passed_filter],
aggregators.values())
all_subread_aggregators = {
'raw_nreads':
SumAggregator('length'),
'max_raw_readlength':
MaxAggregator('length'),
'raw_readlength_histogram':
HistogramAggregator('length', 0, 100, nbins=10000)
}
all_filter_func = functools.partial(_apply, [null_filter],
all_subread_aggregators.values())
funcs = [passed_filter_func, all_filter_func]
with open(filtered_csv, 'r') as f:
# read in header
header = f.readline()
# validate_header(header)
applyer(to_record, f, funcs)
for aggregator in itertools.chain(aggregators.values(),
all_subread_aggregators.values()):
log.info(aggregator)
# Check if any reads are found
if all_subread_aggregators['raw_nreads'].attribute == 0:
raise NoSubreadsFound(
"No subreads found in {f}".format(f=filtered_csv))
# Now check
if aggregators['nreads'].attribute == 0:
msg = "No subreads passed the filter in {f}.".format(f=filtered_csv)
raise NoSubreadsPassedFilter(msg)
# this is where you change the plotting options
plot_view = PlotViewProperties(Constants.P_POST_FILTER,
Constants.PG_SUBREAD_LENGTH,
custom_subread_length_histogram,
Constants.I_FILTER_SUBREADS_HIST,
xlabel=get_plot_xlabel(
spec, Constants.PG_SUBREAD_LENGTH,
Constants.P_POST_FILTER),
ylabel="Subreads",
rlabel="bp > Subread Length",
thumb="filtered_subread_report_thmb.png",
use_group_thumb=True,
color=get_green(3),
edgecolor=get_green(2))
view_config_d = {'post_filter': plot_view}
id_aggregators = {'post_filter': aggregators['subread']}
plot_groups = to_plot_groups(view_config_d, output_dir, id_aggregators)
to_a = lambda n: aggregators[n].attribute
attributes = _to_attributes(to_a('nreads'), to_a('nbases'),
to_a('mean_subreadlength'), to_a('n50'))
report = Report(Constants.R_ID,
plotgroups=plot_groups,
attributes=attributes)
log.debug(str(report))
return spec.apply_view(report)
def validate_file_and_load_manifest(path):
rt = RunnableTask.from_manifest_json(validate_file(path))
# if we got here everything is valid
return path
def _f(path):
path = validate_file(path)
return _f(path)
def validate_file_and_load_manifest(path):
rt = RunnableTask.from_manifest_json(validate_file(path))
# if we got here everything is valid
return path