b=existing_files,
c=sample_files))
output_dict[sample_name] = sample_files
output_dict = dict(sorted(output_dict.items()))
return output_dict
# Create sampledata for Illumina raw reads
raw_reads_dict = create_sampledata_dict(raw_reads_dirs)
raw_reads_dict = {
k: raw_reads_dict[k]
for k in raw_reads_dict if "HP" in k and not os.path.isfile(
"/data2/bio/Metagenomes/HG19/Unmapped_reads/{}_no_hg19.1.gz".format(k))
}
Utilities.dump_2d_array([[k] + raw_reads_dict[k] for k in raw_reads_dict],
file=projectDescriber.sampledata)
# Prepare deploy charts
launchGuideLiner = LaunchGuideLiner(
charts_dir="{}{}/charts/".format(
Utilities.ends_with_slash(projectDescriber.directory), "hg19"),
deploy_prefix=projectDescriber.owner + "-hg19",
nodes_number=7,
threads_number="half",
sampledata_file=projectDescriber.sampledata,
refdata_file="/data/reference/homo_sapiens/hg/hg19/hg19.refdata",
output_mask="hg19",
output_dir="/data2/bio/Metagenomes/HG19")
launchGuideLiner.generate_config()
launchGuideLiner.get_deploy_guide()
"""
def dump_counter(counter: Counter, file: str):
Utilities.dump_2d_array([("keyword", "occurrences")] +
counter.most_common(),
file=file)
def dump_groupdata_dict(groupdata: dict, file: str):
array = [[j, k] for k in groupdata for j in groupdata[k] if len(groupdata[k]) > 0]
Utilities.dump_2d_array(array=array, file=file)
