def _file_type_to_output_file_type(file_type, index):
fid = "_".join([file_type.file_type_id, str(index)])
return OutputFileType(file_type.file_type_id,
"Label " + fid,
repr(file_type),
"description for {f}".format(f=file_type),
file_type.default_name)
def _to_output(i, file_type):
default_name = "_".join(
[file_type.file_type_id, file_type.base_name + "_" + str(i)])
label = "label_" + file_type.file_type_id
desc = "File {f}".format(f=file_type)
return OutputFileType(file_type.file_type_id, label, repr(file_type), desc,
default_name)
def FT(file_type, basename, title):
# (file_type_id, label, display_name, description, default_name)
return OutputFileType(file_type.file_type_id,
basename + '_id',
title,
"description for {f}".format(f=file_type),
basename)
log = logging.getLogger(__name__)
TOOL_NAMESPACE = 'pbcoretools'
DRIVER_BASE = "python -m pbcoretools.tasks.filters "
registry = registry_builder(TOOL_NAMESPACE, DRIVER_BASE)
rl_opt = QuickOpt(0, "Minimum subread length", "Minimum length of subreads")
filters_opt = QuickOpt(
"", "Filters to add to the DataSet",
"A comma separated list of other filters to add to the DataSet")
subreads_file_type = OutputFileType(FileTypes.DS_SUBREADS.file_type_id,
"SubreadSet", "Filtered SubreadSet XML",
"Filtered SubreadSet XML", "filtered")
def sanitize_read_length(read_length):
if read_length:
if not re.search('^-?\d*(\.\d*)?$', str(read_length).strip()):
raise ValueError('read_length filter value "{v}" is not a '
'number'.format(v=read_length))
try:
return int(read_length)
except ValueError:
return int(float(read_length))
def run_filter_dataset(in_file, out_file, read_length, other_filters):
FT_DUMMY = FileTypes.TXT
FT_SUBREADS = FileTypes.DS_SUBREADS
FT_CONTIGS = FileTypes.DS_CONTIG
FT_FASTA = FileTypes.FASTA
FT_REPORT = FileTypes.REPORT
FT_LOG = FileTypes.LOG
def FT(file_type, basename, title):
# (file_type_id, label, display_name, description, default_name)
return OutputFileType(file_type.file_type_id, basename + '_id', title,
"description for {f}".format(f=file_type), basename)
FT_DB = FT(FT_DUMMY, 'dazzler.db', "DAZZ_DB (implies dot-files too)")
FT_JSON_OUT = OutputFileType(FileTypes.JSON.file_type_id, "json_id", "JSON",
"Generic JSON file", "file")
FT_FASTA_OUT = OutputFileType(FileTypes.FASTA.file_type_id, "fasta_id",
"FASTA", "FASTA sequences", "reads")
FT_CONTIGS_OUT = OutputFileType(FileTypes.DS_CONTIG.file_type_id, "contig_id",
"contigset",
"Contigset of polished FASTA sequences",
"polished.contigset")
FT_FOFN_OUT = OutputFileType(
FileTypes.FOFN.file_type_id, "fofn_id",
"FOFN of daligner input (.fasta paths, possibly relative)",
"file of file names of fasta input", "file")
@registry('task_falcon_config_get_fasta',
'0.0.0', [FT_CFG], [FT_FOFN_OUT],
def _file_type_to_output_file_type(file_type):
return OutputFileType(file_type.file_type_id,
"Label " + file_type.file_type_id, repr(file_type),
"description for {f}".format(f=file_type),
file_type.default_name)
ref_file = op.join(output_dir_name, reference_name, "referenceset.xml")
assert op.isfile(ref_file)
with ReferenceSet(ref_file, strict=True) as ds_ref:
ds_ref.makePathsAbsolute()
log.info("saving final ReferenceSet to {f}".format(f=output_file_name))
ds_ref.write(output_file_name)
return 0
run_bam_to_fasta = functools.partial(_run_bam_to_fastx, "bam2fasta",
FastaReader, FastaWriter)
run_bam_to_fastq = functools.partial(_run_bam_to_fastx, "bam2fastq",
FastqReader, FastqWriter)
subreads_from_h5_file_type = OutputFileType(FileTypes.DS_SUBREADS.file_type_id,
"SubreadSet", "SubreadSet",
"Imported SubreadSet", "subreads")
subreads_barcoded_file_type = OutputFileType(
FileTypes.DS_SUBREADS.file_type_id, "SubreadSet", "Barcoded SubreadSet",
"Barcoded SubreadSet", "subreads_barcoded")
@registry("h5_subreads_to_subread",
"0.1.0",
FileTypes.DS_SUBREADS_H5,
subreads_from_h5_file_type,
is_distributed=True,
nproc=1)
def run_bax2bam(rtc):
return run_bax_to_bam(rtc.task.input_files[0], rtc.task.output_files[0])
run_fasta_to_reference = functools.partial(__run_fasta_to_reference,
"fasta-to-reference", ReferenceSet)
run_fasta_to_gmap_reference = functools.partial(__run_fasta_to_reference,
"fasta-to-gmap-reference", GmapReferenceSet)
run_bam_to_fasta = functools.partial(_run_bam_to_fastx, "bam2fasta",
FastaReader, FastaWriter)
run_bam_to_fastq = functools.partial(_run_bam_to_fastx, "bam2fastq",
FastqReader, FastqWriter)
subreads_from_h5_file_type = OutputFileType(FileTypes.DS_SUBREADS.file_type_id,
"Subreads", "Subread data in XML dataset",
"Imported SubreadSet", "subreads")
subreads_barcoded_file_type = OutputFileType(FileTypes.DS_SUBREADS.file_type_id,
"SubreadSet",
"Barcoded Subreads",
"Barcoded Subreads DataSet XML",
"subreads_barcoded")
@registry("h5_subreads_to_subread", "0.1.0",
FileTypes.DS_SUBREADS_H5,
subreads_from_h5_file_type, is_distributed=True, nproc=1)
def run_bax2bam(rtc):
return run_bax_to_bam(rtc.task.input_files[0], rtc.task.output_files[0])
@registry("bam2bam_barcode", "0.1.0",