def merge_postprocess_bams(inputs, output, tempdir, containers):
helpers.makedirs(tempdir)
merged_out = os.path.join(tempdir, 'merged_lanes.bam')
picardutils.merge_bams(inputs,
merged_out,
docker_image=containers['picard'])
bamutils.bam_index(merged_out,
merged_out + '.bai',
docker_image=containers['samtools'])
sorted_bam = os.path.join(tempdir, 'sorted.bam')
picardutils.bam_sort(merged_out,
sorted_bam,
tempdir,
docker_image=containers['picard'])
markdups_metrics = os.path.join(tempdir, 'markdups_metrics.txt')
picardutils.bam_markdups(sorted_bam,
output,
markdups_metrics,
tempdir,
docker_image=containers['picard'])
bamutils.bam_index(output,
output + '.bai',
docker_image=containers['samtools'])
def align_pe(fastq1, fastq2, output, reports, metrics, tempdir, reference,
instrument, centre, sample_info, cell_id, lane_id, library_id,
config):
readgroup = get_readgroup(lane_id, cell_id, library_id, centre,
sample_info)
run_fastqc(fastq1, fastq2, reports, tempdir, config)
aln_temp = os.path.join(tempdir, "temp_alignments.bam")
if config["aligner"] == "bwa-mem":
bwa_mem_paired_end(fastq1, fastq2, aln_temp, reference, readgroup,
tempdir, config['containers'])
elif config["aligner"] == "bwa-aln":
if not instrument == "N550":
fastq1, fastq2 = trim_fastqs(fastq1, fastq2, cell_id, tempdir,
config)
bwa_aln_paired_end(fastq1, fastq2, aln_temp, tempdir, reference,
readgroup, config['containers'])
else:
raise Exception(
"Aligner %s not supported, pipeline supports bwa-aln and bwa-mem" %
config["aligner"])
container_ctx = helpers.get_container_ctx(config['containers'],
'picard',
docker_only=True)
picardutils.bam_sort(aln_temp, output, tempdir, **container_ctx)
container_ctx = helpers.get_container_ctx(config['containers'],
'samtools',
docker_only=True)
bamutils.bam_flagstat(output, metrics, **container_ctx)
def align_pe(
fastq1, fastq2, output, reports, metrics, tempdir, reference,
trim, centre, sample_info, cell_id, lane_id, library_id, aligner,
containers, adapter, adapter2, fastqscreen_params
):
readgroup = get_readgroup(
lane_id, cell_id, library_id, centre, sample_info
)
run_fastqc(fastq1, fastq2, reports, tempdir, containers)
aln_temp = os.path.join(tempdir, "temp_alignments.bam")
if aligner == "bwa-aln" and trim:
fastq1, fastq2 = trim_fastqs(
fastq1, fastq2, cell_id, tempdir,
adapter, adapter2, containers['trimgalore']
)
align_pe_with_bwa(
fastq1, fastq2, aln_temp, reference, readgroup,
tempdir, containers, aligner=aligner
)
picardutils.bam_sort(aln_temp, output, tempdir, docker_image=containers['picard'])
bamutils.bam_flagstat(output, metrics, docker_image=containers['samtools'])
def align_pe(fastq1, fastq2, output, reports_dir, tempdir, reference, trim,
centre, sample_info, cell_id, lane_id, library_id, aligner,
containers, adapter, adapter2, fastqscreen_detailed_metrics,
fastqscreen_summary_metrics, fastqscreen_params):
fastqscreen_tempdir = os.path.join(tempdir, 'fastq_screen')
helpers.makedirs(fastqscreen_tempdir)
filtered_fastq_r1 = os.path.join(fastqscreen_tempdir, "fastq_r1.fastq.gz")
filtered_fastq_r2 = os.path.join(fastqscreen_tempdir, "fastq_r2.fastq.gz")
fastqscreen.organism_filter(
fastq1,
fastq2,
filtered_fastq_r1,
filtered_fastq_r2,
fastqscreen_detailed_metrics,
fastqscreen_summary_metrics,
fastqscreen_tempdir,
cell_id,
fastqscreen_params,
reference,
docker_image=containers['fastq_screen'],
filter_contaminated_reads=fastqscreen_params[
'filter_contaminated_reads'],
)
readgroup = get_readgroup(lane_id, cell_id, library_id, centre,
sample_info)
run_fastqc(filtered_fastq_r1, filtered_fastq_r2, reports_dir, tempdir,
containers)
aln_temp = os.path.join(tempdir, "temp_alignments.bam")
if aligner == "bwa-aln" and trim:
filtered_fastq_r1, filtered_fastq_r2 = trim_fastqs(
filtered_fastq_r1, filtered_fastq_r2, cell_id, tempdir, adapter,
adapter2, containers['trimgalore'])
align_pe_with_bwa(filtered_fastq_r1,
filtered_fastq_r2,
aln_temp,
reference,
readgroup,
tempdir,
containers,
aligner=aligner)
picardutils.bam_sort(aln_temp,
output,
tempdir,
docker_image=containers['picard'])
metrics = os.path.join(reports_dir, 'flagstat_metrics.txt')
bamutils.bam_flagstat(output, metrics, docker_image=containers['samtools'])
def merge_postprocess_bams(inputs, output, tempdir):
helpers.makedirs(tempdir)
merged_out = os.path.join(tempdir, 'merged_lanes.bam')
picardutils.merge_bams(inputs, merged_out)
bamutils.bam_index(merged_out, merged_out + '.bai')
sorted_bam = os.path.join(tempdir, 'sorted.bam')
picardutils.bam_sort(merged_out, sorted_bam, tempdir)
markdups_metrics = os.path.join(tempdir, 'markdups_metrics.txt')
picardutils.bam_markdups(sorted_bam, output, markdups_metrics, tempdir)
bamutils.bam_index(output, output + '.bai')
def postprocess_bam(infile, outfile, tempdir, containers):
outfile_index = outfile + '.bai'
if not os.path.exists(tempdir):
helpers.makedirs(tempdir)
sorted_bam = os.path.join(tempdir, 'sorted.bam')
picardutils.bam_sort(infile, sorted_bam, tempdir,
docker_image=containers['picard'])
markdups_metrics = os.path.join(tempdir, 'markdups_metrics.txt')
picardutils.bam_markdups(sorted_bam, outfile, markdups_metrics, tempdir,
docker_image=containers['picard'])
bamutils.bam_index(outfile, outfile_index, docker_image=containers['samtools'])
def postprocess_bam(infile, outfile, outfile_index, tempdir, config,
markdups_metrics, flagstat_metrics):
if not os.path.exists(tempdir):
helpers.makedirs(tempdir)
container_ctx = helpers.get_container_ctx(config['containers'],
'picard',
docker_only=True)
sorted_bam = os.path.join(tempdir, 'sorted.bam')
picardutils.bam_sort(infile, sorted_bam, tempdir, **container_ctx)
picardutils.bam_markdups(sorted_bam, outfile, markdups_metrics, tempdir,
**container_ctx)
container_ctx = helpers.get_container_ctx(config['containers'],
'samtools',
docker_only=True)
bamutils.bam_index(outfile, outfile_index, **container_ctx)
bamutils.bam_flagstat(outfile, flagstat_metrics, **container_ctx)
def align_pe(
fastq1, fastq2, output, reports_dir, tempdir, reference,
trim, center, sample_info, cell_id, lane_id, library_id,
adapter, adapter2, fastqscreen_detailed_metrics,
fastqscreen_summary_metrics, fastqscreen_params,
):
fastqscreen_tempdir = os.path.join(tempdir, 'fastq_screen')
helpers.makedirs(fastqscreen_tempdir)
filtered_fastq_r1 = os.path.join(fastqscreen_tempdir, "fastq_r1.fastq.gz")
filtered_fastq_r2 = os.path.join(fastqscreen_tempdir, "fastq_r2.fastq.gz")
fastqscreen.organism_filter(
fastq1, fastq2, filtered_fastq_r1, filtered_fastq_r2,
fastqscreen_detailed_metrics, fastqscreen_summary_metrics,
fastqscreen_tempdir, cell_id, fastqscreen_params
)
readgroup = get_readgroup(
lane_id, cell_id, library_id, center, sample_info
)
# run_fastqc(filtered_fastq_r1, filtered_fastq_r2, reports_dir, tempdir)
aln_temp = os.path.join(tempdir, "temp_alignments.bam")
if trim:
filtered_fastq_r1, filtered_fastq_r2 = trim_fastqs(
filtered_fastq_r1, filtered_fastq_r2, cell_id, tempdir,
adapter, adapter2
)
align_pe_with_bwa(
filtered_fastq_r1, filtered_fastq_r2, aln_temp, reference, readgroup,
tempdir
)
picardutils.bam_sort(aln_temp, output, tempdir)
metrics = os.path.join(reports_dir, 'flagstat_metrics.txt')
bamutils.bam_flagstat(output, metrics)