def script__test_ssi_stamper(sample, sample_yaml, sample_component):
comps = get_components(sample)
if "detected_species" in sample["properties"]:
species = datahandling.load_species(
sample["properties"]["detected_species"])
else:
species = datahandling.load_species(None)
results, summary, stamp = stamps.ssi_stamp.test(comps['whats_my_species'],
comps['qcquickie'],
comps['assemblatron'],
species, sample)
datadump_dict = datahandling.load_sample_component(sample_component)
datadump_dict["summary"] = summary
datadump_dict["results"] = results
datahandling.save_sample_component(datadump_dict, sample_component)
# Get the _id back
datadump_dict = datahandling.load_sample_component(sample_component)
stamp["_sample_component"] = datadump_dict["_id"]
stamp_list = sample.get("stamps", [])
stamp_list.append(stamp)
sample["stamps"] = stamp_list
datahandling.save_sample(sample, sample_yaml)
return 0
def script__test_ssi_stamper(sample, sample_yaml, sample_component, log_err):
# Genering error handling to redirect output to stderr file
try:
comps = get_components(sample)
if "detected_species" in sample["properties"]:
species = datahandling.load_species(
sample["properties"]["detected_species"])
else:
species = datahandling.load_species(None)
results, summary, stamp = stamps.ssi_stamp.test(
comps['whats_my_species'], comps['assemblatron'], species, sample)
datadump_dict = datahandling.load_sample_component(sample_component)
datadump_dict["summary"] = summary
datadump_dict["results"] = results
datahandling.save_sample_component(datadump_dict, sample_component)
# Get the _id back
datadump_dict = datahandling.load_sample_component(sample_component)
stamp["_sample_component"] = datadump_dict["_id"]
stamp_dict = sample.get("stamps", {})
stamp_list = stamp_dict.get("stamp_list", [])
stamp_list.append(stamp)
stamp_dict["stamp_list"] = stamp_list
stamp_dict[stamp["name"]] = stamp
sample["stamps"] = stamp_dict
datahandling.save_sample(sample, sample_yaml)
return 0
except Exception:
datahandling.log(log_err, str(traceback.format_exc()))
exit(1)
def script__datadump_assemblatron(folder, sample):
folder = str(folder)
sample = str(sample)
data_dict = datahandling.load_sample_component(sample)
data_dict["summary"] = data_dict.get("summary", {})
data_dict["results"] = data_dict.get("results", {})
data_dict = datahandling.datadump_template(data_dict, folder,
"contigs.sum.cov",
extract_contigs_sum_cov)
data_dict = datahandling.datadump_template(data_dict, folder,
"contigs.bin.cov",
extract_contigs_bin_cov)
data_dict = datahandling.datadump_template(
data_dict, folder, "log/setup__filter_reads_with_bbduk.err.log",
extract_bbuk_log)
data_dict = datahandling.datadump_template(data_dict, folder,
"quast/report.tsv",
extract_quast_report)
data_dict = datahandling.datadump_template(data_dict, folder,
"contigs.variants",
extract_contig_variants)
data_dict = datahandling.datadump_template(data_dict, folder,
"contigs.stats",
extract_contig_stats)
data_dict = datahandling.datadump_template(data_dict, folder,
"contigs.sketch",
extract_contig_sketch)
datahandling.save_sample_component(data_dict, sample)
return 0
def script__datadump_whats_my_species(folder, sample):
folder = str(folder)
sample = str(sample)
data_dict = datahandling.load_sample_component(sample)
data_dict["summary"] = data_dict.get("summary", {})
data_dict["results"] = data_dict.get("results", {})
data_dict = datahandling.datadump_template(
data_dict, folder, "log/setup__filter_reads_with_bbduk.err.log",
extract_bbuk_log)
data_dict = datahandling.datadump_template(data_dict, folder,
"bracken.txt",
extract_bracken_txt)
data_dict = datahandling.datadump_template(
data_dict, folder, "kraken_report_bracken.txt",
extract_kraken_report_bracken_txt)
data_dict = datahandling.datadump_template(data_dict, folder,
"kraken_report.txt",
extract_kraken_report_txt)
data_dict = combine_bbduk_log_bracken_txt_kraken_report_bracken_txt(
data_dict)
datahandling.save_sample_component(data_dict, sample)
return 0
def script__datadump_ariba_mlst(folder, sample, sample_yaml):
folder = str(folder)
sample = str(sample)
datadump_dict = datahandling.load_sample_component(sample)
datadump_dict["summary"] = datadump_dict.get("summary", {})
datadump_dict["results"] = datadump_dict.get("results", {})
mlst_database = datahandling.get_mlst_species_DB(sample_yaml)
datadump_dict["results"]["mlst_db"] = mlst_database
datadump_dict["summary"]["mlst_db"] = mlst_database
datadump_dict = extract_tsv(datadump_dict, folder, "ariba_mlst/report.tsv")
datadump_dict = extract_tsv(datadump_dict, folder,
"ariba_mlst/mlst_report.tsv")
# Summary:
try:
datadump_dict["summary"]["mlst_report"] = ",".join([
"{}:{}".format(key, val) for key, val in datadump_dict["results"]
["ariba_mlst/mlst_report_tsv"]["values"][0].items()
])
except KeyError as e:
datadump_dict["summary"]["mlst_report"] = "KeyError: {}".format(e)
datahandling.save_sample_component(datadump_dict, sample)
return 0
def script__datadump(folder, sample, sample_file_name, component_file_name):
db_sample = datahandling.load_sample(sample_file_name)
db_component = datahandling.load_component(component_file_name)
folder = str(folder)
sample = str(sample)
datadump_dict = datahandling.load_sample_component(sample)
datadump_dict["summary"] = datadump_dict.get("summary", {})
datadump_dict["results"] = datadump_dict.get("results", {})
species = db_sample["properties"]["species"]
datadump_dict["summary"]["db"] = []
datadump_dict["summary"]["strain"] = []
datadump_dict["summary"]["alleles"] = []
datadump_dict["summary"]["component"] = {"id": db_component["_id"], "date": datetime.datetime.utcnow()}
mlst_species = db_component["mlst_species_mapping"][species]
for mlst_entry in mlst_species:
mlst_entry_db = datahandling.load_yaml("cge_mlst/" + mlst_entry + "/data.json")
datadump_dict["results"][mlst_entry] = mlst_entry_db
datadump_dict["summary"]["db"].append(mlst_entry)
datadump_dict["summary"]["strain"].append(mlst_entry_db["mlst"]["results"].get("sequence_type","NA"))
datadump_dict["summary"]["alleles"].append(",".join([mlst_entry_db["mlst"]["results"]["allele_profile"][i]["allele_name"] for i in [i for i in mlst_entry_db["mlst"]["results"]["allele_profile"]]]))
db_sample["properties"]["mlst"] = datadump_dict["summary"]
datahandling.save_sample_component(datadump_dict, sample)
datahandling.save_sample(db_sample, sample_file_name)
return 0
def script__datadump_analyzer(folder, sample):
folder = str(folder)
sample = str(sample)
datadump_dict = datahandling.load_sample_component(sample)
datadump_dict["summary"] = datadump_dict.get("summary", {})
datadump_dict["results"] = datadump_dict.get("results", {})
datadump_dict = extract_tsv(datadump_dict, folder,
"abricate_on_plasmidfinder_from_ariba.tsv")
datadump_dict = extract_tsv(datadump_dict, folder,
"ariba_plasmidfinder/report.tsv")
# Summary:
try:
datadump_dict["summary"]["ariba_plasmidfinder"] = datadump_dict[
"results"]["abricate_on_plasmidfinder_from_ariba_tsv"]["values"]
except KeyError as e:
datadump_dict["summary"][
"ariba_plasmidfinder"] = "KeyError: {}".format(e)
datahandling.save_sample_component(datadump_dict, sample)
return 0
def set_status_to_running(sample_component):
sample_component = str(sample_component)
sample_component_entry = datahandling.load_sample_component(
sample_component)
sample_component_entry["status"] = "Running"
datahandling.save_sample_component(sample_component_entry,
sample_component)
return 0
def script__datadump_kma_pointmutations(folder, sample):
folder = str(folder)
sample = str(sample)
data_dict = datahandling.load_sample_component(sample)
data_dict["summary"] = data_dict.get("summary", {})
data_dict["results"] = data_dict.get("results", {})
data_dict = extract_tsv(data_dict, folder, "contigs_blastn_results.tsv")
datahandling.save_sample_component(data_dict, sample)
return 0
def script__datadump_min_read_check(folder, sample):
folder = str(folder)
sample = str(sample)
data_dict = datahandling.load_sample_component(sample)
data_dict["summary"] = data_dict.get("summary", {})
data_dict["results"] = data_dict.get("results", {})
data_dict = datahandling.datadump_template(
data_dict, folder, "log/setup__filter_reads_with_bbduk.err.log",
extract_bbuk_log)
datahandling.save_sample_component(data_dict, sample)
return 0
def script__initialization(requirements_file, sample, sample_component,
output_file, log_out, log_err):
set_status_to_running(sample_component)
if requirements_met(requirements_file, sample, log_out, log_err) == True:
datahandling.log(log_out, "{}\n{}\n".format(os.getcwd(), output_file))
with open(str(output_file), "w") as handle:
handle.write("Requirements met")
pass
else:
datahandling.log(log_err, "Requirements not met")
sample_component_entry = datahandling.load_sample_component(
sample_component)
sample_component_entry["status"] = "Requirements not met"
datahandling.save_sample_component(sample_component_entry,
sample_component)
return 0
def script__datadump_analyzer(analyzer_folder, sample):
analyzer_folder = str(analyzer_folder)
sample = str(sample)
datadump_dict = datahandling.load_sample_component(sample)
datadump_dict["summary"] = datadump_dict.get("summary", {})
datadump_dict["results"] = datadump_dict.get("results", {})
datadump_dict = extract_tsv(datadump_dict, analyzer_folder,
"ariba_mlst/report.tsv")
datadump_dict = extract_tsv(datadump_dict, analyzer_folder,
"ariba_mlst/mlst_report.tsv")
datadump_dict = extract_tsv(datadump_dict, analyzer_folder,
"abricate_on_plasmidfinder_from_ariba.tsv")
datadump_dict = extract_tsv(datadump_dict, analyzer_folder,
"ariba_plasmidfinder/report.tsv")
datadump_dict = extract_tsv(datadump_dict, analyzer_folder,
"ariba_resfinder/report.tsv")
datadump_dict = extract_tsv(datadump_dict, analyzer_folder,
"abricate_on_resfinder_from_ariba.tsv")
## Summary:
try:
datadump_dict["summary"]["ariba_resfinder"] = datadump_dict["results"][
"abricate_on_plasmidfinder_from_ariba_tsv"]["values"]
except KeyError as e:
datadump_dict["summary"]["ariba_resfinder"] = "KeyError: {}".format(e)
try:
datadump_dict["summary"]["mlst_report"] = ",".join([
"{}:{}".format(key, val) for key, val in datadump_dict["results"]
["ariba_mlst/mlst_report_tsv"]["values"][0].items()
])
except KeyError as e:
datadump_dict["summary"]["mlst_report"] = "KeyError: {}".format(e)
datahandling.save_sample_component(datadump_dict, sample)
return 0
def script__datadump_whats_my_species(folder, sample):
folder = str(folder)
sample = str(sample)
data_dict = datahandling.load_sample_component(sample)
data_dict["summary"] = data_dict.get("summary", {})
data_dict["results"] = data_dict.get("results", {})
data_dict = datahandling.datadump_template(data_dict, folder,
"bracken.txt",
extract_bracken_txt)
data_dict = datahandling.datadump_template(
data_dict, folder, "kraken_report_bracken.txt",
extract_kraken_report_bracken_txt)
data_dict = datahandling.datadump_template(data_dict, folder,
"kraken_report.txt",
extract_kraken_report_txt)
data_dict = species_math(data_dict)
datahandling.save_sample_component(data_dict, sample)
return 0
test_samples = extract_tsv(samples_file)
samples = []
for i in range(len(test_samples)):
samples.append(test_samples[i]['sample'])
output = []
for sample in samples:
temp = []
genes = []
bs = []
bgs = []
file = sample + "/" + sample + "__pointfinder.yaml"
file2 = sample + "/" + sample + "__ariba_resfinder.yaml"
data = datahandling.load_sample_component(file)
data2 = datahandling.load_sample_component(file2)
matchinfo_short = ""
row = pd.DataFrame(0, index=range(1), columns=range(96))
row.columns = template.columns
row['isolate'] = sample
if 'summary' in data2:
for n in range(len(data2['summary']['ariba_resfinder'])):
if 'DATABASE' in data2['summary']['ariba_resfinder'][n]:
temp.append(
data2['summary']['ariba_resfinder'][n]['DATABASE'][13:])
if 'GENE' in data2['summary']['ariba_resfinder'][n]:
genes.append(