def sample_annotation(data):
"""
Annotate miRNAs using miRBase database with seqbuster tool
"""
names = data["rgnames"]['sample']
tools = dd.get_expression_caller(data)
work_dir = os.path.join(dd.get_work_dir(data), "mirbase")
out_dir = os.path.join(work_dir, names)
utils.safe_makedir(out_dir)
out_file = op.join(out_dir, names)
if dd.get_mirbase_hairpin(data):
mirbase = op.abspath(op.dirname(dd.get_mirbase_hairpin(data)))
if utils.file_exists(data["collapse"]):
data['transcriptome_bam'] = _align(data["collapse"], dd.get_mirbase_hairpin(data), out_file, data)
data['seqbuster'] = _miraligner(data["collapse"], out_file, dd.get_species(data), mirbase, data['config'])
else:
logger.debug("Trimmed collapsed file is empty for %s." % names)
else:
logger.debug("No annotation file from miRBase.")
sps = dd.get_species(data) if dd.get_species(data) else "None"
logger.debug("Looking for mirdeep2 database for %s" % names)
if file_exists(op.join(dd.get_work_dir(data), "mirdeep2", "novel", "hairpin.fa")):
data['seqbuster_novel'] = _miraligner(data["collapse"], "%s_novel" % out_file, sps, op.join(dd.get_work_dir(data), "mirdeep2", "novel"), data['config'])
if "trna" in tools:
data['trna'] = _mint_trna_annotation(data)
data = spikein.counts_spikein(data)
return [[data]]
def sample_annotation(data):
"""
Annotate miRNAs using miRBase database with seqbuster tool
"""
names = data["rgnames"]['sample']
tools = dd.get_expression_caller(data)
work_dir = os.path.join(dd.get_work_dir(data), "mirbase")
out_dir = os.path.join(work_dir, names)
utils.safe_makedir(out_dir)
out_file = op.join(out_dir, names)
if dd.get_mirbase_hairpin(data):
mirbase = op.abspath(op.dirname(dd.get_mirbase_hairpin(data)))
data['seqbuster'] = _miraligner(data["collapse"], out_file,
dd.get_species(data), mirbase,
data['config'])
else:
logger.debug("No annotation file from miRBase.")
sps = dd.get_species(data) if dd.get_species(data) else "None"
logger.debug("Looking for mirdeep2 database for %s" % names)
if file_exists(
op.join(dd.get_work_dir(data), "mirdeep2", "novel", "hairpin.fa")):
data['seqbuster_novel'] = _miraligner(
data["collapse"], "%s_novel" % out_file, sps,
op.join(dd.get_work_dir(data), "mirdeep2", "novel"),
data['config'])
if "trna" in tools:
data['trna'] = _trna_annotation(data)
data = spikein.counts_spikein(data)
return [[data]]
def generate_transcript_counts(data):
"""Generate counts per transcript and per exon from an alignment"""
data["count_file"] = featureCounts.count(data)
if dd.get_transcriptome_align(data):
# to create a disambiguated transcriptome file realign with bowtie2
if dd.get_disambiguate(data):
logger.info("Aligning to the transcriptome with bowtie2 using the "
"disambiguated reads.")
bam_path = data["work_bam"]
fastq_paths = alignprep._bgzip_from_bam(
bam_path,
data["dirs"],
data,
is_retry=False,
output_infix='-transcriptome')
if len(fastq_paths) == 2:
file1, file2 = fastq_paths
else:
file1, file2 = fastq_paths[0], None
ref_file = dd.get_ref_file(data)
data = bowtie2.align_transcriptome(file1, file2, ref_file, data)
else:
file1, file2 = dd.get_input_sequence_files(data)
if not dd.get_transcriptome_bam(data):
ref_file = dd.get_ref_file(data)
logger.info(
"Transcriptome alignment was flagged to run, but the "
"transcriptome BAM file was not found. Aligning to the "
"transcriptome with bowtie2.")
data = bowtie2.align_transcriptome(file1, file2, ref_file, data)
data = spikein.counts_spikein(data)
return [[data]]
def generate_transcript_counts(data):
"""Generate counts per transcript and per exon from an alignment"""
data["count_file"] = featureCounts.count(data)
if dd.get_fusion_mode(data, False):
oncofuse_file = oncofuse.run(data)
if oncofuse_file:
data = dd.set_oncofuse_file(data, oncofuse_file)
if dd.get_transcriptome_align(data):
# to create a disambiguated transcriptome file realign with bowtie2
if dd.get_disambiguate(data):
logger.info("Aligning to the transcriptome with bowtie2 using the "
"disambiguated reads.")
bam_path = data["work_bam"]
fastq_paths = alignprep._bgzip_from_bam(bam_path, data["dirs"], data["config"], is_retry=False, output_infix='-transcriptome')
if len(fastq_paths) == 2:
file1, file2 = fastq_paths
else:
file1, file2 = fastq_paths[0], None
ref_file = dd.get_ref_file(data)
data = bowtie2.align_transcriptome(file1, file2, ref_file, data)
else:
file1, file2 = dd.get_input_sequence_files(data)
if not dd.get_transcriptome_bam(data):
ref_file = dd.get_ref_file(data)
logger.info("Transcriptome alignment was flagged to run, but the "
"transcriptome BAM file was not found. Aligning to the "
"transcriptome with bowtie2.")
data = bowtie2.align_transcriptome(file1, file2, ref_file, data)
data = spikein.counts_spikein(data)
return [[data]]
