def run(name, chip_bam, input_bam, genome_build, out_dir, method, resources, data): """ Run macs2 for chip and input samples avoiding errors due to samples. """ # output file name need to have the caller name config = dd.get_config(data) out_file = os.path.join(out_dir, name + "_peaks_macs2.xls") macs2_file = os.path.join(out_dir, name + "_peaks.xls") if utils.file_exists(out_file): _compress_and_sort_bdg_files(out_dir, data) return _get_output_files(out_dir) macs2 = config_utils.get_program("macs2", config) antibody = dd.get_antibody(data) if antibody: antibody = antibody.lower() if antibody not in antibodies.SUPPORTED_ANTIBODIES: logger.error( f"{antibody} specified, but not listed as a supported antibody. Valid antibodies are {antibodies.SUPPORTED_ANTIBODIES}. If you know your antibody " f"should be called with narrow or broad peaks, supply 'narrow' or 'broad' as the antibody." f"It will run 'narrow' if the antibody is not supported.") antibody = 'narrow' antibody = antibodies.ANTIBODIES[antibody] logger.info( f"{antibody.name} specified, using {antibody.peaktype} peak settings." ) peaksettings = select_peak_parameters(antibody) elif method == "atac": logger.info(f"ATAC-seq specified, using narrow peak settings.") peaksettings = " " else: peaksettings = " " options = " ".join(resources.get("macs2", {}).get("options", "")) genome_size = bam.fasta.total_sequence_length(dd.get_ref_file(data)) genome_size = "" if options.find("-g") > -1 else "-g %s" % genome_size paired = "-f BAMPE" if bam.is_paired(chip_bam) else "" with utils.chdir(out_dir): cmd = _macs2_cmd(data) cmd += peaksettings try: do.run(cmd.format(**locals()), "macs2 for %s" % name) utils.move_safe(macs2_file, out_file) except subprocess.CalledProcessError: raise RuntimeWarning( "macs2 terminated with an error. " "Please, check the message and report " "error if it is related to bcbio. " "You can add specific options for the sample " "setting resources as explained in docs: " "https://bcbio-nextgen.readthedocs.org/en/latest/contents/configuration.html#sample-specific-resources" ) _compress_and_sort_bdg_files(out_dir, data) return _get_output_files(out_dir)
def run(name, chip_bam, input_bam, genome_build, out_dir, method, resources, data): """ Run macs2 for chip and input samples avoiding errors due to samples. """ # output file name need to have the caller name config = dd.get_config(data) out_file = os.path.join(out_dir, name + "_peaks_macs2.xls") macs2_file = os.path.join(out_dir, name + "_peaks.xls") if utils.file_exists(out_file): _compress_bdg_files(out_dir) return _get_output_files(out_dir) macs2 = config_utils.get_program("macs2", config) antibody = antibodies.ANTIBODIES.get(dd.get_antibody(data).lower(), None) if antibody: logger.info( f"{antibody.name} specified, using {antibody.peaktype} peak settings." ) peaksettings = select_peak_parameters(antibody) else: peaksettings = "" options = " ".join(resources.get("macs2", {}).get("options", "")) genome_size = bam.fasta.total_sequence_length(dd.get_ref_file(data)) genome_size = "" if options.find("-g") > -1 else "-g %s" % genome_size paired = "-f BAMPE" if bam.is_paired(chip_bam) else "" with utils.chdir(out_dir): cmd = _macs2_cmd(data) cmd += peaksettings try: do.run(cmd.format(**locals()), "macs2 for %s" % name) utils.move_safe(macs2_file, out_file) except subprocess.CalledProcessError: raise RuntimeWarning( "macs2 terminated with an error.\n" "Please, check the message and report " "error if it is related to bcbio.\n" "You can add specific options for the sample " "setting resources as explained in docs: " "https://bcbio-nextgen.readthedocs.org/en/latest/contents/configuration.html#sample-specific-resources" ) _compress_bdg_files(out_dir) return _get_output_files(out_dir)