def illumina_files(runobj):
logger.debug("Start Overlap, filter and unique reads")
utils = PipelneUtils()
start = time.time()
# illumina_files_demultiplex_only(runobj)
illumina_files_inst = IlluminaFiles(runobj)
if runobj.do_perfect:
# illumina_files_inst.perfect_reads()
script_file_name = illumina_files_inst.merge_perfect()
utils.run_until_done_on_cluster(script_file_name)
script_file_name = illumina_files_inst.trim_primers_perfect()
utils.run_until_done_on_cluster(script_file_name)
else:
# illumina_files_inst.partial_overlap_reads()
# pass
# TODO: test utils.run_until_done_on_cluster(illumina_files_inst.partial_overlap_reads_cluster())
# TODO: add cutting to 251
script_file_name = illumina_files_inst.partial_overlap_reads_cluster()
utils.run_until_done_on_cluster(script_file_name)
script_file_name = illumina_files_inst.filter_mismatches_cluster()
utils.run_until_done_on_cluster(script_file_name)
# illumina_files_inst.filter_mismatches()
# illumina_files_inst.uniq_fa()
script_file_name = illumina_files_inst.uniq_fa_cluster()
utils.run_until_done_on_cluster(script_file_name)
# illumina_chimera(runobj)
elapsed = (time.time() - start)
logger.debug("illumina_files time = %s" % str(elapsed))
def illumina_files_demultiplex_only(runobj):
logger.debug("Start Demultiplex Illumina files by index/run_key/lane")
start = time.time()
illumina_files_inst = IlluminaFiles(runobj)
illumina_files_inst.open_dataset_files()
illumina_files_inst.split_files(compressed=runobj.compressed)
elapsed = (time.time() - start)
logger.debug("illumina_files demultiplex only time = %s" % str(elapsed))
