def main():
# read params
args = parse_arguments()
ALIGNED_BAM = args.bam
OUTPUT_PREFIX = os.path.join(args.out_dir,
os.path.basename(strip_ext_bam(ALIGNED_BAM)))
RG_FREE_ALIGNED_BAM = remove_read_group(ALIGNED_BAM)
JAVA_HEAP = args.picard_java_heap
# Library complexity: Preseq results, NRF, PBC1, PBC2
if args.paired_end:
picard_est_lib_size = get_picard_complexity_metrics(
RG_FREE_ALIGNED_BAM, OUTPUT_PREFIX, JAVA_HEAP)
else:
picard_est_lib_size = None
preseq_data, preseq_log = run_preseq(ALIGNED_BAM,
OUTPUT_PREFIX) # SORTED BAM
get_preseq_plot(preseq_data, OUTPUT_PREFIX)
# write picard_est_lib_size to file
if picard_est_lib_size is not None:
picard_est_lib_size_file = OUTPUT_PREFIX + '.picard_est_lib_size.qc'
with open(picard_est_lib_size_file, 'w') as fp:
fp.write(str(picard_est_lib_size) + '\n')
rm_f(RG_FREE_ALIGNED_BAM)
log.info('List all files in output directory...')
ls_l(args.out_dir)
log.info('All done.')
def main():
# read params
args = parse_arguments()
REF = args.ref_fa
FINAL_BAM = args.nodup_bam
OUTPUT_PREFIX = os.path.join(
args.out_dir,
os.path.basename(strip_ext_bam(FINAL_BAM)))
RG_FREE_FINAL_BAM = remove_read_group(FINAL_BAM)
JAVA_HEAP = args.picard_java_heap
gc_out, gc_plot_pdf, gc_summary = get_gc(RG_FREE_FINAL_BAM,
REF,
OUTPUT_PREFIX,
JAVA_HEAP)
# will generate PNG format from gc_out
plot_gc(gc_out, OUTPUT_PREFIX)
rm_f(RG_FREE_FINAL_BAM)
log.info('List all files in output directory...')
ls_l(args.out_dir)
log.info('All done.')
def main():
# read params
args = parse_arguments()
CHROMSIZES = args.chrsz
TSS = args.tss if args.tss and os.path.basename(args.tss) != 'null' else ''
FINAL_BAM = args.nodup_bam
OUTPUT_PREFIX = os.path.join(args.out_dir,
os.path.basename(strip_ext_bam(FINAL_BAM)))
samtools_index(FINAL_BAM) # make an index first
RG_FREE_FINAL_BAM = remove_read_group(FINAL_BAM)
log.info('Initializing and making output directory...')
mkdir_p(args.out_dir)
# Also get read length
# read_len = get_read_length(FASTQ)
if args.read_len_log:
with open(args.read_len_log, 'r') as fp:
read_len = int(fp.read().strip())
elif args.read_len:
read_len = args.read_len
else:
read_len = None
# Enrichments: V plot for enrichment
# Use final to avoid duplicates
tss_plot, tss_large_plot, tss_enrich_qc = \
make_tss_plot(FINAL_BAM,
TSS,
OUTPUT_PREFIX,
CHROMSIZES,
read_len)
# remove temporary files
rm_f(RG_FREE_FINAL_BAM)
log.info('List all files in output directory...')
ls_l(args.out_dir)
log.info('All done.')
def main():
# read params
args = parse_arguments()
FINAL_BAM = args.nodup_bam
OUTPUT_PREFIX = os.path.join(args.out_dir,
os.path.basename(strip_ext_bam(FINAL_BAM)))
RG_FREE_FINAL_BAM = remove_read_group(FINAL_BAM)
# Insert size distribution - CAN'T GET THIS FOR SE FILES
insert_data, insert_plot = get_insert_distribution(RG_FREE_FINAL_BAM,
OUTPUT_PREFIX)
# Also need to run n-nucleosome estimation
fragment_length_qc(read_picard_histogram(insert_data), OUTPUT_PREFIX)
fragment_length_plot(insert_data, OUTPUT_PREFIX)
rm_f(RG_FREE_FINAL_BAM)
log.info('List all files in output directory...')
ls_l(args.out_dir)
log.info('All done.')