def _update_data(align_file, out_dir, names, data):
data = dd.set_work_bam(data, align_file)
data = dd.set_align_bam(data, align_file)
transcriptome_file = _move_transcriptome_file(out_dir, names)
data = dd.set_transcriptome_bam(data, transcriptome_file)
sjfile = get_splicejunction_file(out_dir, data)
sjbed = junction2bed(sjfile)
data = dd.set_junction_bed(data, sjbed)
return data
def _update_data(align_file, out_dir, names, data):
data = dd.set_work_bam(data, align_file)
data = dd.set_align_bam(data, align_file)
transcriptome_file = _move_transcriptome_file(out_dir, names)
data = dd.set_transcriptome_bam(data, transcriptome_file)
sjfile = get_splicejunction_file(out_dir, data)
if sjfile:
sjbed = junction2bed(sjfile)
data = dd.set_junction_bed(data, sjbed)
return data
def align(fastq_file, pair_file, ref_file, names, align_dir, data):
paired = True if pair_file else False
hisat2 = config_utils.get_program("hisat2", data)
num_cores = dd.get_num_cores(data)
quality_flag = _get_quality_flag(data)
stranded_flag = _get_stranded_flag(data, paired)
rg_flags = _get_rg_flags(names)
out_file = os.path.join(align_dir,
"{0}-sort.bam".format(dd.get_sample_name(data)))
if data.get("align_split"):
final_file = out_file
out_file, data = alignprep.setup_combine(final_file, data)
fastq_file, pair_file = alignprep.split_namedpipe_cls(
fastq_file, pair_file, data)
else:
final_file = None
if not file_exists(out_file) and (final_file is None
or not file_exists(final_file)):
cmd = (
"{hisat2} --new-summary -x {ref_file} -p {num_cores} {quality_flag} {stranded_flag} "
"{rg_flags} ")
if paired:
cmd += "-1 {fastq_file} -2 {pair_file} "
else:
cmd += "-U {fastq_file} "
if dd.get_analysis(data).lower() == "smallrna-seq":
cmd += "-k 1000 "
# if assembling transcripts, set flags that cufflinks/stringtie can use
if dd.get_transcript_assembler(data):
cmd += "--dta-cufflinks "
if dd.get_analysis(data).lower() == "rna-seq":
splicesites = get_known_splicesites_file(align_dir, data)
if file_exists(splicesites):
cmd += "--known-splicesite-infile {splicesites} "
novel_splicesite_file = os.path.join(
align_dir,
"{0}-novelsplicesites.bed".format(dd.get_sample_name(data)))
cmd += "--novel-splicesite-outfile {novel_splicesite_file} "
# apply additional hisat2 options
cmd += " ".join(_get_options_from_config(data))
message = "Aligning %s and %s with hisat2." % (fastq_file, pair_file)
with postalign.tobam_cl(data, out_file, pair_file
is not None) as (tobam_cl, tx_out_file):
cmd += " | " + tobam_cl
do.run(cmd.format(**locals()), message)
data = dd.set_work_bam(data, out_file)
junctionbed = get_splicejunction_file(align_dir, data)
data = dd.set_junction_bed(data, junctionbed)
return data
def align(fastq_file, pair_file, ref_file, names, align_dir, data):
paired = True if pair_file else False
hisat2 = config_utils.get_program("hisat2", data)
num_cores = dd.get_num_cores(data)
quality_flag = _get_quality_flag(data)
stranded_flag = _get_stranded_flag(data, paired)
rg_flags = _get_rg_flags(names)
out_file = os.path.join(align_dir, "{0}-sort.bam".format(dd.get_sample_name(data)))
if data.get("align_split"):
final_file = out_file
out_file, data = alignprep.setup_combine(final_file, data)
fastq_file, pair_file = alignprep.split_namedpipe_cls(fastq_file, pair_file, data)
else:
final_file = None
if not file_exists(out_file) and (final_file is None or not file_exists(final_file)):
cmd = ("{hisat2} --new-summary -x {ref_file} -p {num_cores} {quality_flag} {stranded_flag} "
"{rg_flags} ")
if paired:
cmd += "-1 {fastq_file} -2 {pair_file} "
else:
cmd += "-U {fastq_file} "
if dd.get_analysis(data).lower() == "smallrna-seq":
cmd += "-k 1000 "
# if assembling transcripts, set flags that cufflinks/stringtie can use
if dd.get_transcript_assembler(data):
cmd += "--dta-cufflinks "
if dd.get_analysis(data).lower() == "rna-seq":
splicesites = get_known_splicesites_file(align_dir, data)
if file_exists(splicesites):
cmd += "--known-splicesite-infile {splicesites} "
novel_splicesite_file = os.path.join(align_dir, "{0}-novelsplicesites.bed".format(dd.get_sample_name(data)))
cmd += "--novel-splicesite-outfile {novel_splicesite_file} "
# apply additional hisat2 options
cmd += " ".join(_get_options_from_config(data))
message = "Aligning %s and %s with hisat2." % (fastq_file, pair_file)
with postalign.tobam_cl(data, out_file, pair_file is not None) as (tobam_cl, tx_out_file):
cmd += " | " + tobam_cl
do.run(cmd.format(**locals()), message)
data = dd.set_work_bam(data, out_file)
junctionbed = get_splicejunction_file(align_dir, data)
data = dd.set_junction_bed(data, junctionbed)
return data