def read_metrics(self):
cg_out_dir = self.cg_out_dir
if not os.path.isdir(cg_out_dir):
os.makedirs(cg_out_dir)
print("Directory for CG Pipeline output made: ", cg_out_dir)
for read in self.runfiles.reads:
#get id
id = self.runfiles.reads[read].id
cgp_result = id + "_readMetrics.tsv"
if not os.path.isfile(cg_out_dir + cgp_result):
# change self.path to local dir if path is a basemounted dir
if os.path.isdir(self.path + "/AppResults"):
self.path = self.output_dir
# get paths to fastq files
fwd = os.path.abspath(self.runfiles.reads[read].fwd).replace(self.path, "")
if "_R1" in fwd:
reads = fwd.replace("_R1", "*")
else:
reads = fwd.replace("_1", "*")
# create paths for data
mounting = {self.path:'/datain', cg_out_dir:'/dataout'}
out_dir = '/dataout'
in_dir = '/datain'
fastani_obj = run_fastani.FastANI(path=self.path, output_dir=self.output_dir)
fastani_reference = fastani_obj.fastani()[1][id]
if "LMP18" in fastani_reference:
genome_length = 3.0
elif "SAP18" in fastani_reference:
genome_length = 5.0
else:
genome_length = input("In Mbp, what is the expected genome size of %s?" % (id))
try:
float(genome_length)
except ValueError:
print("A number was not entered")
genome_length = float(genome_length)*1000000
print("Estimated genome length for isolate %s: " % id + str(int(genome_length)))
# build command for running run_assembly_readMetrics.pl
command = "bash -c 'run_assembly_readMetrics.pl {in_dir}/{reads} -e {genome_length} > " \
"{out_dir}/{cgp_result}'".format(in_dir=in_dir,out_dir=out_dir,reads=reads,
genome_length=genome_length,cgp_result=cgp_result)
# call the docker process
print("Getting read metrics for isolate %s"%(id))
calldocker.call("staphb/lyveset",command,'/dataout',mounting)
print("CG Pipeline results for isolate %s saved to: %s%s"%(id,cg_out_dir,cgp_result))
def spades(self):
# create output directory
spades_out_dir = self.spades_out_dir
if not os.path.isdir(spades_out_dir):
os.makedirs(spades_out_dir)
print("Directory for spades output made: ", spades_out_dir)
for read in self.runfiles.reads:
# get id
id = self.runfiles.reads[read].id
spades_results = "%s/%s/" % (spades_out_dir, id)
if not os.path.isdir(spades_results):
os.makedirs(spades_results)
if not os.path.isfile(spades_results + "/contigs.fasta"):
# change self.path to local dir if path is a basemounted dir
if os.path.isdir(self.path + "/AppResults"):
self.path = self.output_dir
# get paths to fastq files
if self.runfiles.reads[read].paired:
fwd = os.path.abspath(
self.runfiles.reads[read].fwd).replace(self.path, "")
rev = os.path.abspath(
self.runfiles.reads[read].rev).replace(self.path, "")
# create paths for data
mounting = {self.path: '/datain', spades_results: '/dataout'}
out_dir = '/dataout'
in_dir = '/datain'
# build command for creating sketches and generating mash distance table
# TODO write elif to catch single read data
if self.runfiles.reads[read].paired:
command = "bash -c 'spades.py -1 {in_dir}/{fwd} -2 {in_dir}/{rev} -o " \
"{out_dir}/ -t {threads} {extra_params}'".format(in_dir=in_dir,
spades_results=spades_results,
out_dir=out_dir,
threads=self.threads,
extra_params=self.extra_params,
fwd=fwd,rev=rev)
# call the docker process
print("Generating SPAdes assembly for sample " + id)
calldocker.call("staphb/spades", command, '/dataout', mounting)
print("SPAdes assembly for isolate %s saved to: %s" %
(id, spades_results))
def quast(self):
# create output directory
quast_out_dir = self.quast_out_dir
if not os.path.isdir(quast_out_dir):
os.makedirs(quast_out_dir)
print("Directory for Quast output made: ", quast_out_dir)
for read in self.runfiles.reads:
# get id
id = self.runfiles.reads[read].id
# change self.path to local dir if path is a basemounted dir
if os.path.isdir(self.path + "/AppResults"):
self.path = self.output_dir
print(self.path)
fastani_obj = run_fastani.FastANI(path=self.path,
output_dir=self.output_dir)
fastani_reference = fastani_obj.fastani()[1][id]
reference_genome = "/%s" % fastani_reference
assembly = "/spades_output/%s/contigs.fasta" % id
quast_results = "%s/%s/" % (quast_out_dir, id)
if not os.path.isdir(quast_results):
os.makedirs(quast_results)
# create paths for data
mounting = {
self.path: '/datain',
quast_results: '/dataout',
self.db: '/db'
}
out_dir = '/dataout/'
in_dir = '/datain/'
db = '/db/'
command = "bash -c 'quast.py {in_dir}{assembly} -r {db}{reference_genome} -o {out_dir}'".format(
assembly=assembly,
id=id,
out_dir=out_dir,
reference_genome=reference_genome,
in_dir=in_dir,
db=db)
# call the docker process
#print("Generating Quast assembly metrics")
calldocker.call("staphb/quast:5.0.0", command, '/dataout/',
mounting)
def fastani(self):
# create output directory
fastani_out_dir = self.fastani_out_dir
if not os.path.isdir(fastani_out_dir):
os.makedirs(fastani_out_dir)
print("Directory for fastani output made: ", fastani_out_dir)
taxons = {}
reference_genomes = {}
for read in self.runfiles.reads:
# get id
id = self.runfiles.reads[read].id
fastani_result = "/fastani_%s.out" % id
# change self.path to local dir if path is a basemounted dir
if os.path.isdir(self.path + "/AppResults"):
self.path = self.output_dir
assembly = "/spades_output/%s/contigs.fasta" % id
if not os.path.isfile(assembly):
spades_obj = run_spades.Spades(path=self.path,
output_dir=self.output_dir)
spades_obj.spades()
# create paths for data
mounting = {
self.path: '/datain',
fastani_out_dir: '/dataout',
self.db: '/db'
}
ref_list = "/reference_list.txt"
out_dir = '/dataout/'
in_dir = '/datain/'
db = '/db/'
command = "bash -c 'fastANI -q {in_dir}{assembly} --rl {db}{ref_list} -o " \
"{out_dir}/{fastani_result}'".format(assembly=assembly,out_dir=out_dir,db=db, in_dir=in_dir,
ref_list=ref_list, fastani_result=fastani_result)
# call the docker process
if not os.path.isfile("%s/%s" % (fastani_out_dir, fastani_result)):
print("Generating FastANI report for sample " + id)
calldocker.call("staphb/fastani", command, '/dataout',
mounting)
with open("%s/%s" % (fastani_out_dir, fastani_result)) as file:
tsv_reader = csv.reader(file, delimiter="\t", quotechar='"')
predicted_taxon = ""
reference_genome = str(os.path.basename(next(tsv_reader)[1]))
if "SAP18-0432" in reference_genome:
predicted_taxon = "Salmonella enterica subsp. enterica serover Enteritidis"
elif "SAP18-H9654" in reference_genome:
predicted_taxon = "Salmonella enterica subsp. enterica serover Enteritidis"
elif "SAP18-6199" in reference_genome:
predicted_taxon = "Salmonella enterica subsp. enterica serover Typhimurium"
elif "SAP18-8729" in reference_genome:
predicted_taxon = "Salmonella enterica subsp. enterica serover Newport"
elif "LMP18-H2446" in reference_genome:
predicted_taxon = "Listeria monocytogenes"
elif "LMP18-H8393" in reference_genome:
predicted_taxon = "Listeria monocytogenes"
else:
raise ValueError(
"Sample %s not identified as a 2018 PT isolate" % id)
taxons[id] = predicted_taxon
reference_genomes[id] = reference_genome
return [taxons, reference_genomes]
def cfsansnp(self):
# create output directory
cfsansnp_out_dir = self.cfsansnp_out_dir
cfsan_read_dir = cfsansnp_out_dir + "/cfsan-reads/"
if not os.path.isdir(cfsansnp_out_dir):
os.makedirs(cfsansnp_out_dir)
print("Directory for cfsansnp output made: ", cfsansnp_out_dir)
for read in self.runfiles.reads:
# get id
id = self.runfiles.reads[read].id
cfsansnp_result = "/%s/%s/snpma.fasta" % (cfsansnp_out_dir, id)
# change self.path to local dir if path is a basemounted dir
if os.path.isdir(self.path + "/AppResults"):
self.path = self.output_dir
fastani_obj = run_fastani.FastANI(path=self.path,
output_dir=self.output_dir)
fastani_reference = fastani_obj.fastani()[1][id]
# create paths for data
mounting = {
self.path: '/datain',
cfsansnp_out_dir: '/dataout',
self.db: '/db'
}
out_dir = '/dataout/'
in_dir = '/datain/'
db = '/db/'
fwd_read = "/%s/raw_reads/" % in_dir + os.path.basename(
self.runfiles.reads[read].fwd)
rev_read = "/%s/raw_reads/" % in_dir + os.path.basename(
self.runfiles.reads[read].rev)
if not os.path.isdir(cfsan_read_dir):
os.makedirs(cfsan_read_dir)
print("Directory for cfsansnp read dir made: ", cfsan_read_dir)
if not os.path.isdir(cfsan_read_dir + id):
os.makedirs(cfsan_read_dir + id)
if not os.path.islink(
cfsan_read_dir + id + "/" +
os.path.basename(self.runfiles.reads[read].fwd)):
os.symlink(
fwd_read, cfsan_read_dir + id + "/" +
os.path.basename(self.runfiles.reads[read].fwd))
if not os.path.islink(
cfsan_read_dir + id + "/" +
os.path.basename(self.runfiles.reads[read].rev)):
os.symlink(
rev_read, cfsan_read_dir + id + "/" +
os.path.basename(self.runfiles.reads[read].rev))
reference_genome = "/%s" % fastani_reference
command = "bash -c 'run_snp_pipeline.sh -m soft -o {out_dir}{id} -s {out_dir}cfsan-reads " \
"{db}{reference_genome}'".format(out_dir=out_dir,db=db, in_dir=in_dir, id=id,
reference_genome=reference_genome)
# call the docker process
if not os.path.isfile(cfsansnp_result):
print("Generating cfsansnp output for sample " + id)
calldocker.call("staphb/cfsan-snp-pipeline:2.0.2", command,
'/dataout', mounting)
shutil.rmtree(cfsan_read_dir, ignore_errors=True)