def count(data): """ count reads mapping to genes using featureCounts http://subread.sourceforge.net """ in_bam = dd.get_work_bam(data) sorted_bam = bam.sort(in_bam, dd.get_config(data), order="queryname") gtf_file = dd.get_gtf_file(data) work_dir = dd.get_work_dir(data) out_dir = os.path.join(work_dir, "htseq-count") safe_makedir(out_dir) count_file = os.path.join(out_dir, dd.get_sample_name(data)) + ".counts" summary_file = os.path.join(out_dir, dd.get_sample_name(data)) + ".counts.summary" if file_exists(count_file): return count_file featureCounts = config_utils.get_program("featureCounts", dd.get_config(data)) paired_flag = _paired_flag(in_bam) strand_flag = _strand_flag(data) filtered_bam = bam.filter_primary(sorted_bam, data) cmd = "{featureCounts} -a {gtf_file} -o {tx_count_file} -s {strand_flag} " "{paired_flag} {filtered_bam}" message = "Count reads in {tx_count_file} mapping to {gtf_file} using " "featureCounts" with file_transaction(data, [count_file, summary_file]) as tx_files: tx_count_file, tx_summary_file = tx_files do.run(cmd.format(**locals()), message.format(**locals())) fixed_count_file = _format_count_file(count_file, data) fixed_summary_file = _change_sample_name(summary_file, dd.get_sample_name(data), data=data) shutil.move(fixed_count_file, count_file) shutil.move(fixed_summary_file, summary_file) return count_file
def count(data): """ count reads mapping to genes using featureCounts http://subread.sourceforge.net """ in_bam = dd.get_work_bam(data) sorted_bam = bam.sort(in_bam, dd.get_config(data), order="queryname") gtf_file = dd.get_gtf_file(data) work_dir = dd.get_work_dir(data) out_dir = os.path.join(work_dir, "htseq-count") safe_makedir(out_dir) count_file = os.path.join(out_dir, dd.get_sample_name(data)) + ".counts" if file_exists(count_file): return count_file featureCounts = config_utils.get_program("featureCounts", dd.get_config(data)) paired_flag = _paired_flag(in_bam) strand_flag = _strand_flag(data) filtered_bam = bam.filter_primary(sorted_bam, data) cmd = ("{featureCounts} -a {gtf_file} -o {tx_count_file} -s {strand_flag} " "{paired_flag} {filtered_bam}") message = ("Count reads in {tx_count_file} mapping to {gtf_file} using " "featureCounts") with file_transaction(data, count_file) as tx_count_file: do.run(cmd.format(**locals()), message.format(**locals())) fixed_count_file = _format_count_file(count_file, data) shutil.move(fixed_count_file, count_file) return count_file
def count(data): """ count reads mapping to genes using featureCounts http://subread.sourceforge.net """ in_bam = dd.get_work_bam(data) or dd.get_align_bam(data) out_dir = os.path.join(dd.get_work_dir(data), "align", dd.get_sample_name(data)) if dd.get_aligner(data) == "star": out_dir = os.path.join( out_dir, "%s_%s" % (dd.get_sample_name(data), dd.get_aligner(data))) sorted_bam = bam.sort(in_bam, dd.get_config(data), order="queryname", out_dir=safe_makedir(out_dir)) gtf_file = dd.get_transcriptome_gtf(data, default=dd.get_gtf_file(data)) work_dir = dd.get_work_dir(data) out_dir = os.path.join(work_dir, "htseq-count") safe_makedir(out_dir) count_file = os.path.join(out_dir, dd.get_sample_name(data)) + ".counts" summary_file = os.path.join(out_dir, dd.get_sample_name(data)) + ".counts.summary" if file_exists(count_file) and _is_fixed_count_file(count_file): return count_file featureCounts = config_utils.get_program("featureCounts", dd.get_config(data)) paired_flag = _paired_flag(in_bam) strand_flag = _strand_flag(data) filtered_bam = bam.filter_primary(sorted_bam, data) cmd = ("{featureCounts} -a {gtf_file} -o {tx_count_file} -s {strand_flag} " "{paired_flag} {filtered_bam}") resources = config_utils.get_resources("featureCounts", data["config"]) if resources: options = resources.get("options") if options: cmd += " %s" % " ".join([str(x) for x in options]) message = ("Count reads in {tx_count_file} mapping to {gtf_file} using " "featureCounts") with file_transaction(data, [count_file, summary_file]) as tx_files: tx_count_file, tx_summary_file = tx_files do.run(cmd.format(**locals()), message.format(**locals())) fixed_count_file = _format_count_file(count_file, data) fixed_summary_file = _change_sample_name(summary_file, dd.get_sample_name(data), data=data) shutil.move(fixed_count_file, count_file) shutil.move(fixed_summary_file, summary_file) return count_file