def report_info(ap):
"""Generate a general report
Generates an unstructured report on the contents
of the analysis directory.
Arguments:
ap (AutoProcessor): autoprocessor pointing to the
analysis directory to be reported on
Returns:
String with the report text.
"""
report = []
report.append("Run reference: %s" % ap.run_reference_id)
report.append("Directory : %s" % ap.analysis_dir)
report.append("Platform : %s" % ap.metadata.platform)
report.append("Unaligned dir: %s" % ap.params.unaligned_dir)
if ap.readme_file:
report.append("README.txt found: %s" % ap.readme_file)
if ap.params.unaligned_dir is not None or \
not os.path.exists(ap.params.unaligned_dir):
try:
illumina_data = ap.load_illumina_data()
report.append("\nSummary of data in '%s' dir:\n" %
ap.params.unaligned_dir)
for project in illumina_data.projects:
report.append("- %s" % IlluminaData.describe_project(project))
except IlluminaData.IlluminaDataError as ex:
report.append("Failed to load data from %s:" %
ap.params.unaligned_dir)
report.append("%s" % ex)
else:
report.append("No information on source fastq data (no unaligned dir "
"found)")
try:
projects = ap.get_analysis_projects()
report.append("\n%d analysis project%s:" %
(len(projects), "s" if len(projects) != 0 else ""))
except Exception as ex:
projects = []
report.append("\nNo analysis projects found")
for project in projects:
info = project.info
report.append("\n- %s" % project.name)
report.append(" %s" % ('-' * len(project.name), ))
report.append(" User : %s" % info.user)
report.append(" PI : %s" % info.PI)
report.append(" Library : %s" % info.library_type)
report.append(" SC Plat.: %s" % info.single_cell_platform)
report.append(" Organism: %s" % info.organism)
report.append(" Dir : %s" % os.path.basename(project.dirn))
report.append(" #samples: %s" % len(project.samples))
report.append(" #cells : %s" % default_value(info.number_of_cells))
report.append(" Samples : %s" % project.prettyPrintSamples())
report.append(" QC : %s" %
('ok' if verify_qc(project) else 'not verified'))
report.append(" Comments: %s" % (project.info.comments))
return '\n'.join(report)
else:
n_fastqs = len(sample.fastq)
if n_fastqs == 1:
print "\t%s" % sample.name
else:
print "\t%s (%d fastqs)" % (sample.name, n_fastqs)
# Print fastq names
fastqs = sample.fastq_subset(read_number=1) + \
sample.fastq_subset(read_number=2)
for fastq in fastqs:
print "\t\t%s" % fastq
# Report the names of the samples in each project
if options.report:
for project in illumina_data.projects:
print "%s" % IlluminaData.describe_project(project)
# Report statistics for fastq files
if options.stats:
# Print number of reads for each file, and file size
for sample in project.samples:
for fastq in sample.fastq:
fq = os.path.join(sample.dirn, fastq)
nreads = FASTQFile.nreads(fq)
fsize = os.path.getsize(fq)
print "%s\t%s\t%d" % (
fastq, bcf_utils.format_file_size(fsize), nreads)
print ""
# Summary: short report suitable for logging file
if options.summary:
print "%s" % IlluminaData.summarise_projects(illumina_data)
else:
n_fastqs = len(sample.fastq)
if n_fastqs == 1:
print "\t%s" % sample.name
else:
print "\t%s (%d fastqs)" % (sample.name,n_fastqs)
# Print fastq names
fastqs = sample.fastq_subset(read_number=1) + \
sample.fastq_subset(read_number=2)
for fastq in fastqs:
print "\t\t%s" % fastq
# Report the names of the samples in each project
if options.report:
for project in illumina_data.projects:
print "%s" % IlluminaData.describe_project(project)
# Report statistics for fastq files
if options.stats:
# Print number of reads for each file, and file size
for sample in project.samples:
for fastq in sample.fastq:
fq = os.path.join(sample.dirn,fastq)
nreads = FASTQFile.nreads(fq)
fsize = os.path.getsize(fq)
print "%s\t%s\t%d" % (fastq,
bcf_utils.format_file_size(fsize),
nreads)
print ""
# Summary: short report suitable for logging file
if options.summary:
