def _bcbio_tophat_wrapper(fastq_file, pair_file, ref_file,
stage_name, config):
bcbio_config = {}
stage_config = config["stage"][stage_name]
cores = stage_config.get("cores", 1)
# use the listed quality format, if there isn't one, try to figure
# out what format it is
quality_format = stage_config.get("quality_format", None)
if quality_format is None:
fastq_format = fastqc.detect_fastq_format(fastq_file)
quality_format = FASTQ_FORMAT_TO_BCBIO[fastq_format]
max_errors = stage_config.get("max_errors", None)
options = stage_config.get("options", {})
tophat_loc = config["program"].get("tophat", "tophat")
bowtie_loc = config["program"].get("bowtie", "bowtie")
out_base = remove_suffix(os.path.basename(fastq_file))
align_dir = os.path.join(config["dir"]["results"], stage_name)
bcbio_config["resources"] = {"tophat": {"cores": cores,
"options": options}}
bcbio_config["algorithm"] = {}
bcbio_config["program"] = {}
bcbio_config["algorithm"]["quality_format"] = quality_format
bcbio_config["algorithm"]["max_errors"] = max_errors
bcbio_config["gtf"] = config.get("gtf", None)
if bcbio_config["gtf"]:
if not file_exists(bcbio_config["gtf"]):
raise ValueError("GTF file does not exist. Please check to make sure that "
"the value of gtf is set corretly in the configuration file.")
sys.exit(1)
bcbio_config["program"]["tophat"] = tophat_loc
bcbio_config["program"]["bowtie"] = bowtie_loc
bcbio_config["program"]["picard"] = config["program"]["picard"]
bcbio_config["program"]["gatk"] = {"dir": ""}
out_file = tophat.align(fastq_file, pair_file, ref_file, out_base,
align_dir, bcbio_config)
return out_file
def _bcbio_tophat_wrapper(fastq_file, pair_file, ref_file,
stage_name, config):
bcbio_config = {}
stage_config = config["stage"][stage_name]
cores = config["cluster"].get("cores", None)
# use the listed quality format, if there isn't one, try to figure
# out what format it is
quality_format = stage_config.get("quality_format", None)
if quality_format is None:
fastq_format = fastqc.detect_fastq_format(fastq_file)
quality_format = FASTQ_FORMAT_TO_BCBIO[fastq_format]
max_errors = stage_config.get("max_errors", None)
tophat_loc = config["program"].get("tophat", "tophat")
bowtie_loc = config["program"].get("bowtie", "bowtie")
out_base = remove_suffix(os.path.basename(fastq_file))
align_dir = os.path.join(config["dir"]["results"], stage_name)
bcbio_config["resources"] = {"tophat": {"cores": cores}}
bcbio_config["algorithm"] = {}
bcbio_config["program"] = {}
bcbio_config["algorithm"]["quality_format"] = quality_format
bcbio_config["algorithm"]["max_errors"] = max_errors
bcbio_config["gtf"] = config.get("gtf", None)
bcbio_config["program"]["tophat"] = tophat_loc
bcbio_config["program"]["bowtie"] = bowtie_loc
out_file = tophat.align(fastq_file, pair_file, ref_file, out_base,
align_dir, bcbio_config)
os.remove(out_file)
out_dir = os.path.dirname(out_file)
out_file_fixed = os.path.join(out_dir, out_base + ".sam")
os.symlink("accepted_hits.sam", out_file_fixed)
return out_file_fixed
def _get_quality_type(in_file):
""" get fastq quality format. if multiple types are detected,
pick the first one. no quality type is found assume sanger """
fastq_format = detect_fastq_format(in_file)
return _FASTQ_TYPE_TO_FLAG.get(fastq_format[0], "sanger")