def _maybe_add_summary(algorithm, sample, out):
out = []
if "summary" in sample:
if sample["summary"].get("pdf"):
out.append({
"path": sample["summary"]["pdf"],
"type": "pdf",
"ext": "summary"
})
if sample["summary"].get("qc"):
out.append({
"path": sample["summary"]["qc"],
"type": "directory",
"ext": "qc"
})
if utils.get_in(sample, ("summary", "researcher")):
out.append({
"path":
sample["summary"]["researcher"],
"type":
"tsv",
"sample":
run_info.clean_name(
utils.get_in(sample, ("upload", "researcher"))),
"ext":
"summary"
})
return out
def _maybe_add_summary(algorithm, sample, out):
out = []
if "summary" in sample:
if sample["summary"].get("pdf"):
out.append({
"path": sample["summary"]["pdf"],
"type": "pdf",
"ext": "summary"
})
if sample["summary"].get("qc"):
for program, finfo in sample["summary"]["qc"].items():
out.extend(
_flatten_file_with_secondary(finfo,
os.path.join("qc", program)))
if utils.get_in(sample, ("summary", "researcher")):
out.append({
"path":
sample["summary"]["researcher"],
"type":
"tsv",
"sample":
run_info.clean_name(
utils.get_in(sample, ("upload", "researcher"))),
"ext":
"summary"
})
return out
def _summary_csv_by_researcher(summary_yaml, researcher, descrs, data):
"""Generate a CSV file with summary information for a researcher on this project.
"""
out_file = os.path.join(utils.safe_makedir(os.path.join(data["dirs"]["work"], "researcher")),
"%s-summary.tsv" % run_info.clean_name(researcher))
metrics = ["Total reads", "Mapped reads", "Mapped reads pct", "Duplicates", "Duplicates pct"]
with open(summary_yaml) as in_handle:
with open(out_file, "w") as out_handle:
writer = csv.writer(out_handle, dialect="excel-tab")
writer.writerow(["Name"] + metrics)
for sample in yaml.safe_load(in_handle)["samples"]:
if sample["description"] in descrs:
row = [sample["description"]] + [utils.get_in(sample, ("summary", "metrics", x), "")
for x in metrics]
writer.writerow(row)
return out_file
def _maybe_add_summary(algorithm, sample, out):
out = []
if "summary" in sample:
if sample["summary"].get("pdf"):
out.append({"path": sample["summary"]["pdf"],
"type": "pdf",
"ext": "summary"})
if sample["summary"].get("qc"):
for program, finfo in sample["summary"]["qc"].iteritems():
out.extend(_flatten_file_with_secondary(finfo, os.path.join("qc", program)))
if utils.get_in(sample, ("summary", "researcher")):
out.append({"path": sample["summary"]["researcher"],
"type": "tsv",
"sample": run_info.clean_name(utils.get_in(sample, ("upload", "researcher"))),
"ext": "summary"})
return out
def _summary_csv_by_researcher(summary_yaml, researcher, descrs, data):
"""Generate a CSV file with summary information for a researcher on this project.
"""
out_file = os.path.join(utils.safe_makedir(os.path.join(data["dirs"]["work"], "researcher")),
"%s-summary.tsv" % run_info.clean_name(researcher))
metrics = ["Total_reads", "Mapped_reads", "Mapped_reads_pct", "Duplicates", "Duplicates_pct"]
with open(summary_yaml) as in_handle:
with open(out_file, "w") as out_handle:
writer = csv.writer(out_handle, dialect="excel-tab")
writer.writerow(["Name"] + metrics)
for sample in yaml.safe_load(in_handle)["samples"]:
if sample["description"] in descrs:
row = [sample["description"]] + [utils.get_in(sample, ("summary", "metrics", x), "")
for x in metrics]
writer.writerow(row)
return out_file
def _prepare_sample(data, run_folder):
"""Extract passed keywords from input LIMS information.
"""
want = set(["description", "files", "genome_build", "name", "analysis", "upload", "algorithm"])
out = {}
for k, v in data.items():
if k in want:
out[k] = _relative_paths(v, run_folder)
if "algorithm" not in out:
analysis, algorithm = _select_default_algorithm(out.get("analysis"))
out["algorithm"] = algorithm
out["analysis"] = analysis
description = "%s-%s" % (out["name"], clean_name(out["description"]))
out["name"] = [out["name"], description]
out["description"] = description
return out
def _flatten_lane_details(runinfo):
"""Provide flattened lane information with multiplexed barcodes separated.
"""
out = []
for ldetail in runinfo["details"]:
# handle controls
if "project_name" not in ldetail and ldetail["description"] == "control":
ldetail["project_name"] = "control"
for i, barcode in enumerate(ldetail.get("multiplex", [{}])):
cur = copy.deepcopy(ldetail)
cur["name"] = "%s-%s" % (ldetail["name"], i + 1)
cur["description"] = barcode.get("name", ldetail["description"])
cur["bc_index"] = barcode.get("sequence", "")
cur["project_name"] = clean_name(ldetail["project_name"])
out.append(cur)
return out
def _prepare_sample(data, run_folder):
"""Extract passed keywords from input LIMS information.
"""
want = set(["description", "files", "genome_build", "name", "analysis", "upload", "algorithm"])
out = {}
for k, v in data.items():
if k in want:
out[k] = _relative_paths(v, run_folder)
if "algorithm" not in out:
analysis, algorithm = _select_default_algorithm(out.get("analysis"))
out["algorithm"] = algorithm
out["analysis"] = analysis
description = "%s-%s" % (out["name"], clean_name(out["description"]))
out["name"] = [out["name"], description]
out["description"] = description
return out
def _flatten_lane_details(runinfo):
"""Provide flattened lane information with multiplexed barcodes separated.
"""
out = []
for ldetail in runinfo["details"]:
# handle controls
if "project_name" not in ldetail and ldetail["description"] == "control":
ldetail["project_name"] = "control"
for i, barcode in enumerate(ldetail.get("multiplex", [{}])):
cur = copy.deepcopy(ldetail)
cur["name"] = "%s-%s" % (ldetail["name"], i + 1)
cur["description"] = barcode.get("name", ldetail["description"])
cur["bc_index"] = barcode.get("sequence", "")
cur["project_name"] = clean_name(ldetail["project_name"])
out.append(cur)
return out
def _maybe_add_summary(algorithm, sample, out):
out = []
if "summary" in sample:
if sample["summary"].get("pdf"):
out.append({"path": sample["summary"]["pdf"],
"type": "pdf",
"ext": "summary"})
if sample["summary"].get("qc"):
out.append({"path": sample["summary"]["qc"],
"type": "directory",
"ext": "qc"})
if utils.get_in(sample, ("summary", "researcher")):
out.append({"path": sample["summary"]["researcher"],
"type": "tsv",
"sample": run_info.clean_name(utils.get_in(sample, ("upload", "researcher"))),
"ext": "summary"})
return out
def _add_meta(xs, sample=None, config=None):
out = []
for x in xs:
x["mtime"] = shared.get_file_timestamp(x["path"])
if sample and "sample" not in x:
if isinstance(sample["name"], (tuple, list)):
name = sample["name"][-1]
else:
name = "%s-%s" % (sample["name"], run_info.clean_name(sample["description"]))
x["sample"] = name
if config:
if "fc_name" in config and "fc_date" in config:
x["run"] = "%s_%s" % (config["fc_date"], config["fc_name"])
else:
x["run"] = "project_%s" % datetime.datetime.now().strftime("%Y-%m-%d")
out.append(x)
return out
def _add_meta(xs, sample=None, config=None):
out = []
for x in xs:
x["mtime"] = shared.get_file_timestamp(x["path"])
if sample and "sample" not in x:
if isinstance(sample["name"], (tuple, list)):
name = sample["name"][-1]
else:
name = "%s-%s" % (sample["name"], run_info.clean_name(sample["description"]))
x["sample"] = name
if config:
if "fc_name" in config and "fc_date" in config:
x["run"] = "%s_%s" % (config["fc_date"], config["fc_name"])
else:
x["run"] = "project_%s" % datetime.datetime.now().strftime("%Y-%m-%d")
out.append(x)
return out