def _run_mpileup(cls, bam, ref, outfile):
cmd = ' '.join([
'samtools mpileup --skip-indels -d 500 -t INFO/AD,INFO/ADF,INFO/ADR -C50 -uv',
'-f', ref, bam, '>', outfile
])
utils.syscall(cmd)
def _run_mccortex_view_kmers(self):
# Example filename we're looking for:
# cortex.out/binaries/cleaned/k31/sample_name.kmer31.q5cleaned_1.ctx
cleaned_dir = os.path.join(self.cortex_outdir, 'binaries', 'cleaned')
if not os.path.exists(cleaned_dir):
print('Cleaned directory not found ' + cleaned_dir +
' ... cannot run mccortex view kmers',
file=sys.stderr)
return
kmer_dirs = [x for x in os.listdir(cleaned_dir) if x.startswith('k')]
if len(kmer_dirs) != 1:
print('Error finding kmers directory inside ' + cleaned_dir +
' ... cannot run mccortex view kmers',
file=sys.stderr)
kmer_dir = os.path.join(cleaned_dir, kmer_dirs[0])
ctx_files = [x for x in os.listdir(kmer_dir) if x.endswith('.ctx')]
if len(ctx_files) != 1:
print('Error finding ctx file inside ' + kmer_dir +
' ... cannot run mccortex view kmers',
file=sys.stderr)
ctx_file = os.path.join(kmer_dir, ctx_files[0])
assert os.path.exists(ctx_file)
command = ' '.join([
self.mccortex, 'view', '--kmers', ctx_file,
r'''| awk '{print $1,$2}' | gzip -9 > ''', self.kmer_counts_file
])
utils.syscall(command)
def validate(filenames):
assert 1 <= len(filenames) <= 2
cmd = 'fqtools validate ' + ' '.join(filenames)
try:
utils.syscall(cmd)
except:
raise Error('Error running ' + cmd)
def validate(filenames):
assert 1 <= len(filenames) <= 2
cmd = "fqtools validate " + " ".join(filenames)
try:
utils.syscall(cmd)
except:
raise Error("Error running " + cmd)
def test_map_reads(self):
'''test map_reads'''
reads1 = os.path.join(data_dir, 'reads.1.fq')
reads2 = os.path.join(data_dir, 'reads.2.fq')
ref_fasta = os.path.join(data_dir, 'ref.fa')
tmp_sam = 'tmp.test_map_reads.sam'
if os.path.exists(tmp_sam):
os.unlink(tmp_sam)
read_map.map_reads(ref_fasta,
reads1,
reads2,
tmp_sam,
read_group=('1', 'GROUP_NAME'))
self.assertTrue(os.path.exists(tmp_sam))
tmp_stats = tmp_sam + '.stats'
expected_stats = os.path.join(data_dir, 'flagstat')
utils.syscall('samtools flagstat ' + tmp_sam + ' > ' + tmp_stats)
self.assertTrue(filecmp.cmp(expected_stats, tmp_stats, shallow=False))
found_rg_line = False
with open(tmp_sam) as f:
for line in f:
if line == '@RG\tLB:LIB\tID:1\tSM:GROUP_NAME\n':
found_rg_line = True
break
self.assertTrue(found_rg_line)
os.unlink(tmp_sam)
os.unlink(tmp_stats)
def submit_xml_files(ini_file,
outfile,
files=None,
use_test_server=False,
unit_test=None,
unit_test_obj_type=None):
username, password = parse_config_file(ini_file)
if files is None:
files_command = None
else:
files_command_list = [
'-F "' + key + '=@' + value + '"' for key, value in files.items()
]
files_command = ' '.join(files_command_list)
if use_test_server:
url = 'https://www-test.ebi.ac.uk/ena/submit/drop-box/submit/?auth=ENA%20'
else:
url = 'https://www.ebi.ac.uk/ena/submit/drop-box/submit/?auth=ENA%20'
command_list = [
'curl -k', files_command,
'"' + url + username + '%20' + password + '"', '>', outfile
]
command = ' '.join([x for x in command_list if x is not None])
if unit_test is None:
utils.syscall(command)
elif unit_test == 'success':
_make_dummy_success_receipt(outfile, unit_test_obj_type)
elif unit_test == 'fail':
_make_dummy_fail_receipt(outfile)
else:
raise Error('unit_test must be None, success, or fail. Got: ' +
unit_test)
def test_nextflow_qc_using_fastq_input(self):
'''test nextflow_qc using fastq input'''
reads1 = os.path.join(data_dir, 'Reads', 'reads.1.1.fq.gz')
reads2 = os.path.join(data_dir, 'Reads', 'reads.1.2.fq.gz')
output_dir = 'tmp.test_nextflow_qc_using_fastq_input'
nextflow_file = os.path.join(nextflow_helper.nextflow_dir, 'qc.nf')
nextflow_helper.write_config_file()
work_dir = 'tmp.nextflow_qc.work'
dag_file = 'nextflow.qc.dag.no_db.pdf'
try:
os.unlink(dag_file)
except:
pass
command = ' '.join([
'nextflow run', '--reads_in1', reads1, '--reads_in2', reads2,
'--output_dir', output_dir, '--ref_fasta',
os.path.join(data_dir, 'Reference',
'ref.fa'), '-with-dag', dag_file, '-c',
nextflow_helper.config_file, '-w', work_dir, nextflow_file
])
utils.syscall(command)
os.unlink(nextflow_helper.config_file)
shutil.rmtree(work_dir)
self.assertTrue(os.path.exists(output_dir))
for method in ['fastqc', 'samtools_qc']:
qc_dir = os.path.join(output_dir, method)
self.assertTrue(os.path.exists(qc_dir))
self.assertTrue(len(os.listdir(qc_dir)) >= 1)
shutil.rmtree(output_dir)
nextflow_helper.clean_files()
def mark_duplicates(sorted_bam_in, bam_out, xmx=2):
# The picard jar file in the singularity container is /bioinf-tools/picard.jar.
# If we're not using the container, then need to set the env variable
# CLOCKWORK_PICARD_JAR instead
PICARD_JAR = os.environ.get("CLOCKWORK_PICARD_JAR",
"/bioinf-tools/picard.jar")
if not os.path.exists(PICARD_JAR):
raise Error(
"Picard jar file not found. Please set environment variable CLOCKWORK_PICARD_JAR, or put it here: /bioinf-tools/picard.jar"
)
tmpdir = tempfile.mkdtemp(prefix=bam_out + ".tmp.markdups.",
dir=os.path.dirname(bam_out))
m_file = os.path.join(tmpdir, "covfefe")
cmd = " ".join([
"java",
"-Xmx" + str(xmx) + "g",
"-jar",
PICARD_JAR,
"MarkDuplicates",
"VALIDATION_STRINGENCY=LENIENT",
"INPUT=" + sorted_bam_in,
"OUTPUT=" + bam_out,
"M=" + m_file,
])
try:
utils.syscall(cmd)
except:
shutil.rmtree(tmpdir)
raise Error("Error runnin mark_duplicates: " + cmd)
shutil.rmtree(tmpdir)
def mark_duplicates(sorted_bam_in, bam_out, xmx=2):
# The picard jar file in the singularity container is /bioinf-tools/picard.jar.
# If we're not using the container, then need to set the env variable
# CLOCKWORK_PICARD_JAR instead
PICARD_JAR = os.environ.get('CLOCKWORK_PICARD_JAR',
'/bioinf-tools/picard.jar')
if not os.path.exists(PICARD_JAR):
raise Error(
'Picard jar file not found. Please set environment variable CLOCKWORK_PICARD_JAR, or put it here: /bioinf-tools/picard.jar'
)
tmpdir = tempfile.mkdtemp(prefix=bam_out + '.tmp.markdups.',
dir=os.path.dirname(bam_out))
m_file = os.path.join(tmpdir, 'covfefe')
cmd = ' '.join([
'java', '-Xmx' + str(xmx) + 'g', '-jar', PICARD_JAR, 'MarkDuplicates',
'VALIDATION_STRINGENCY=LENIENT', 'INPUT=' + sorted_bam_in,
'OUTPUT=' + bam_out, 'M=' + m_file
])
try:
utils.syscall(cmd)
except:
shutil.rmtree(tmpdir)
raise Error('Error runnin mark_duplicates: ' + cmd)
shutil.rmtree(tmpdir)
def run(self):
self._make_input_files()
ref_fai = os.path.join(self.ref_dir, 'ref.fa.fai')
genome_size = pyfastaq.tasks.stats_from_fai(ref_fai)['total_length']
cmd = ' '.join([
self.cortex_run_calls,
'--fastaq_index', self.cortex_reads_index,
'--auto_cleaning yes',
'--first_kmer 31',
'--bc yes',
'--pd no',
'--outdir', self.cortex_outdir,
'--outvcf cortex',
'--ploidy 2',
'--stampy_hash', os.path.join(self.ref_dir, 'ref.stampy'),
'--stampy_bin', self.stampy_script,
'--list_ref_fasta', self.cortex_ref_fofn,
'--refbindir', self.ref_dir,
'--genome_size', str(genome_size),
'--qthresh 5',
'--mem_height', str(self.mem_height),
'--mem_width 100',
'--vcftools_dir', self.vcftools_dir,
'--do_union yes',
'--ref CoordinatesAndInCalling',
'--workflow independent',
'--logfile', self.cortex_log,
])
utils.syscall(cmd)
self._tidy_files()
def test_map_reads(self):
"""test map_reads"""
reads1 = os.path.join(data_dir, "reads.1.fq")
reads2 = os.path.join(data_dir, "reads.2.fq")
ref_fasta = os.path.join(data_dir, "ref.fa")
tmp_sam = "tmp.test_map_reads.sam"
if os.path.exists(tmp_sam):
os.unlink(tmp_sam)
read_map.map_reads(ref_fasta,
reads1,
reads2,
tmp_sam,
read_group=("1", "GROUP_NAME"))
self.assertTrue(os.path.exists(tmp_sam))
tmp_stats = tmp_sam + ".stats"
expected_stats = os.path.join(data_dir, "flagstat")
utils.syscall("samtools flagstat " + tmp_sam +
" | grep -v primary > " + tmp_stats)
self.assertTrue(filecmp.cmp(expected_stats, tmp_stats, shallow=False))
found_rg_line = False
with open(tmp_sam) as f:
for line in f:
if line == "@RG\tLB:LIB\tID:1\tSM:GROUP_NAME\n":
found_rg_line = True
break
self.assertTrue(found_rg_line)
os.unlink(tmp_sam)
os.unlink(tmp_stats)
def test_nextflow_variant_call_using_fastq_input(self):
"""test nextflow_variant_call using fastq input"""
reads1 = os.path.join(data_dir, "Reads", "reads.1.1.fq.gz")
reads2 = os.path.join(data_dir, "Reads", "reads.1.2.fq.gz")
outdir = os.path.abspath(
"tmp.test_nextflow_variant_call_fastq_input.out")
tmp_data_dir = "tmp.nextflow_variant_call_fastq_input.data"
if os.path.exists(tmp_data_dir):
shutil.rmtree(tmp_data_dir)
shutil.copytree(data_dir, tmp_data_dir)
nextflow_file = os.path.join(nextflow_helper.nextflow_dir,
"variant_call.nf")
nextflow_helper.write_config_file()
work_dir = "tmp.nextflow_variant_call_fastq_input.work"
sample_name = "test_sample_name"
dag_file = "nextflow.variant_call.dag.no_db.pdf"
try:
os.unlink(dag_file)
except:
pass
command = " ".join([
"nextflow run",
"--reads_in1",
reads1,
"--reads_in2",
reads2,
"--output_dir",
outdir,
"--ref_dir",
os.path.join(tmp_data_dir, "Reference"),
"--sample_name",
sample_name,
"--cortex_mem_height 17",
"--gvcf",
"--testing",
"-with-dag",
dag_file,
"-c",
nextflow_helper.config_file,
"-w",
work_dir,
nextflow_file,
])
utils.syscall(command)
self._files_are_present_and_correct(outdir,
sample_name,
expect_rmdup_bam=True,
expect_ref_check_files=False)
self.assertTrue(
os.path.exists(os.path.join(outdir, "minos", "gvcf.fasta")))
self.assertTrue(
os.path.exists(os.path.join(outdir, "minos", "gvcf.vcf")))
os.unlink(nextflow_helper.config_file)
shutil.rmtree(work_dir)
shutil.rmtree(tmp_data_dir)
shutil.rmtree(outdir)
nextflow_helper.clean_files()
def _download_run(run_id, outdir):
cmd = ' '.join([
'enaDataGet',
'-f fastq',
'-d', outdir,
run_id,
])
print(cmd)
utils.syscall(cmd)
def _download_sample(sample_id, outdir):
cmd = ' '.join([
'enaGroupGet',
'-f fastq',
'-d', outdir,
sample_id,
])
print(cmd)
utils.syscall(cmd)
def _run_fastqc(outdir, infiles):
assert isinstance(infiles, list)
try:
os.mkdir(outdir)
except:
raise Error('Error mkdir ' + outdir)
command = 'fastqc --threads 1 --extract -o ' + outdir + ' ' + ' '.join(infiles)
utils.syscall(command)
def _run_fastqc(outdir, infiles):
assert isinstance(infiles, list)
try:
os.mkdir(outdir)
except:
raise Exception("Error mkdir " + outdir)
command = "fastqc --threads 1 --extract -o " + outdir + " " + " ".join(
infiles)
utils.syscall(command)
def _run_mpileup(cls, bam, ref, outfile):
cmd = " ".join([
"samtools mpileup --skip-indels -d 500 -t INFO/AD,INFO/ADF,INFO/ADR -C50 -uv",
"-f",
ref,
bam,
">",
outfile,
])
utils.syscall(cmd)
def _run_mpileup(cls, bam, ref, outfile):
cmd = " ".join([
"bcftools mpileup --skip-indels -d 500 -a INFO/AD,INFO/ADF,INFO/ADR -C50 --output-type v",
"-f",
ref,
bam,
">",
outfile,
])
utils.syscall(cmd)
def upload_file_to_ena_ftp(ini_file, filename, uploaded_name):
# paranoid about passwords and running ps? Looks like curl is ok:
# https://unix.stackexchange.com/questions/385339/how-does-curl-protect-a-password-from-appearing-in-ps-output
# "wipe the next argument out so that the username:password isn't
# displayed in the system process list"
username, password = parse_config_file(ini_file)
cmd = ' '.join([
'curl -T', filename, 'ftp://webin.ebi.ac.uk/' + uploaded_name,
'--user', username + ':' + password
])
utils.syscall(cmd)
def run_trimmomatic(
reads1,
reads2,
out1,
out2,
trimmo_root=None,
adapters="TruSeq3-PE-2.fa",
minlen=50,
verbose=0,
threads=1,
qual_trim="",
adapters_included=True,
quality_encoding="phred33",
):
if trimmo_root is None:
trimmo_root = os.environ.get("CLOCKWORK_TRIMMO_DIR",
"/bioinf-tools/Trimmomatic-0.36")
trimmo_root = os.path.abspath(trimmo_root)
jar_files = [x for x in os.listdir(trimmo_root) if x.endswith(".jar")]
if len(jar_files) != 1:
raise Exception('Error finding Trimmoatic jar file in directory "' +
trimmo_root + '". Found ' + str(len(jar_files)) +
" jar files. Cannot continue")
jar_file = os.path.join(trimmo_root, jar_files[0])
if adapters_included:
adapters = os.path.join(trimmo_root, "adapters", adapters)
if not os.path.exists(adapters):
raise Exception('Cannot find adapters file "' + adapters + '".')
cmd = " ".join([
"java -Xmx1000m -jar",
jar_file,
"PE",
"-threads",
str(threads),
reads1,
reads2,
out1,
"/dev/null",
out2,
"/dev/null",
"ILLUMINACLIP:" + os.path.abspath(adapters) + ":2:30:10",
qual_trim,
"MINLEN:" + str(minlen),
"-" + quality_encoding,
])
if verbose:
print("Run trimmomatic:", cmd)
utils.syscall(cmd)
def make_index_files(self,
fasta_in,
genome_is_big,
using_cortex,
cortex_mem_height=22):
# seqtk just hangs if the input file doesn't exist, so check
# it first instead
if not os.path.exists(fasta_in):
raise Error("File not found: " + fasta_in)
try:
os.makedirs(self.directory)
except:
raise Error("Error mkdir " + self.directory)
# ensure sequence lines are 60 nt long, and remove comments from
# header lines
utils.syscall("seqtk seq -C -l 60 " + fasta_in + " > " +
self.ref_fasta)
utils.syscall("samtools faidx " + self.ref_fasta)
if genome_is_big:
utils.syscall("bwa index -a bwtsw " + self.ref_fasta)
else:
utils.syscall("bwa index " + self.ref_fasta)
if using_cortex:
cortex.make_run_calls_index_files(self.ref_fasta,
self.ref_fasta_prefix,
mem_height=cortex_mem_height)
def _make_stats_and_plots(cls, samfile, ref_fasta, outprefix):
stats_file = outprefix + ".stats"
cmd = " ".join(
["samtools stats", "-r", ref_fasta, samfile, ">", stats_file])
utils.syscall(cmd)
cmd = " ".join(
["plot-bamstats", "-p", outprefix + ".plot", stats_file])
utils.syscall(cmd)
for filename in glob.glob(outprefix + "*"):
if filename.endswith(".gp") or filename.endswith(".html"):
os.unlink(filename)
def _make_stats_and_plots(cls, samfile, ref_fasta, outprefix):
stats_file = outprefix + '.stats'
cmd = ' '.join(
['samtools stats', '-r', ref_fasta, samfile, '>', stats_file])
utils.syscall(cmd)
cmd = ' '.join(
['plot-bamstats', '-p', outprefix + '.plot', stats_file])
utils.syscall(cmd)
for filename in glob.glob(outprefix + '*'):
if filename.endswith('.gp') or filename.endswith('.html'):
os.unlink(filename)
def test_nextflow_remove_contam_using_fastq_input(self):
'''test nextflow_remove_contam using fastq input'''
reads1 = os.path.join(data_dir, 'Reads', 'reads.1.1.fq.gz')
reads2 = os.path.join(data_dir, 'Reads', 'reads.1.2.fq.gz')
outprefix = 'tmp.test_nextflow_remove_contam_using_fastq_input'
nextflow_file = os.path.join(nextflow_helper.nextflow_dir,
'remove_contam.nf')
nextflow_helper.write_config_file()
work_dir = 'tmp.nextflow_remove_contam.work'
dag_file = 'nextflow.remove_contam.dag.no_db.pdf'
try:
os.unlink(dag_file)
except:
pass
command = ' '.join([
'nextflow run', '--reads_in1', reads1, '--reads_in2', reads2,
'--outprefix', outprefix, '--ref_metadata_tsv',
os.path.join(data_dir, 'Reference',
'remove_contam_metadata.tsv'), '--ref_fasta',
os.path.join(data_dir, 'Reference',
'ref.fa'), '--testing', '-with-dag', dag_file, '-c',
nextflow_helper.config_file, '-w', work_dir, nextflow_file
])
utils.syscall(command)
os.unlink(nextflow_helper.config_file)
shutil.rmtree(work_dir)
for reads_type in ('contam', 'remove_contam'):
for i in ('1', '2'):
filename = outprefix + '.' + reads_type + '.' + i + '.fq.gz'
self.assertTrue(os.path.exists(filename))
os.unlink(filename)
expected_counts_lines = [
'Name\tIs_contam\tReads\n',
'contam\t1\t40\n',
'ref\t0\t132\n',
'Unmapped\t0\t26\n',
'Reads_kept_after_remove_contam\t0\t158\n',
]
counts_tsv = outprefix + '.counts.tsv'
with open(counts_tsv) as f:
got_counts_lines = f.readlines()
self.assertEqual(expected_counts_lines, got_counts_lines)
os.unlink(counts_tsv)
nextflow_helper.clean_files()
def test_map_reads_markdup(self):
"""test map_reads markdup"""
reads1 = os.path.join(data_dir, "reads.1.fq")
reads2 = os.path.join(data_dir, "reads.2.fq")
ref_fasta = os.path.join(data_dir, "ref.fa")
tmp_sam = "tmp.test_map_reads.sam"
if os.path.exists(tmp_sam):
os.unlink(tmp_sam)
read_map.map_reads(ref_fasta, reads1, reads2, tmp_sam, markdup=True)
self.assertTrue(os.path.exists(tmp_sam))
tmp_stats = tmp_sam + ".stats"
expected_stats = os.path.join(data_dir, "markdup.flagstat")
utils.syscall("samtools flagstat " + tmp_sam + " > " + tmp_stats)
self.assertTrue(filecmp.cmp(expected_stats, tmp_stats, shallow=False))
os.unlink(tmp_sam)
os.unlink(tmp_stats)
def test_map_reads_markdup(self):
'''test map_reads markdup'''
reads1 = os.path.join(data_dir, 'reads.1.fq')
reads2 = os.path.join(data_dir, 'reads.2.fq')
ref_fasta = os.path.join(data_dir, 'ref.fa')
tmp_sam = 'tmp.test_map_reads.sam'
if os.path.exists(tmp_sam):
os.unlink(tmp_sam)
read_map.map_reads(ref_fasta, reads1, reads2, tmp_sam, markdup=True)
self.assertTrue(os.path.exists(tmp_sam))
tmp_stats = tmp_sam + '.stats'
expected_stats = os.path.join(data_dir, 'markdup.flagstat')
utils.syscall('samtools flagstat ' + tmp_sam + ' > ' + tmp_stats)
self.assertTrue(filecmp.cmp(expected_stats, tmp_stats, shallow=False))
os.unlink(tmp_sam)
os.unlink(tmp_stats)
def test_nextflow_qc_using_fastq_input(self):
"""test nextflow_qc using fastq input"""
reads1 = os.path.join(data_dir, "Reads", "reads.1.1.fq.gz")
reads2 = os.path.join(data_dir, "Reads", "reads.1.2.fq.gz")
output_dir = "tmp.test_nextflow_qc_using_fastq_input"
nextflow_file = os.path.join(nextflow_helper.nextflow_dir, "qc.nf")
nextflow_helper.write_config_file()
work_dir = "tmp.nextflow_qc.work"
dag_file = "nextflow.qc.dag.no_db.pdf"
try:
os.unlink(dag_file)
except:
pass
command = " ".join([
"nextflow run",
"--reads_in1",
reads1,
"--reads_in2",
reads2,
"--output_dir",
output_dir,
"--ref_fasta",
os.path.join(data_dir, "Reference", "ref.fa"),
"-with-dag",
dag_file,
"-c",
nextflow_helper.config_file,
"-w",
work_dir,
nextflow_file,
])
utils.syscall(command)
os.unlink(nextflow_helper.config_file)
shutil.rmtree(work_dir)
self.assertTrue(os.path.exists(output_dir))
for method in ["fastqc", "samtools_qc"]:
qc_dir = os.path.join(output_dir, method)
self.assertTrue(os.path.exists(qc_dir))
self.assertTrue(len(os.listdir(qc_dir)) >= 1)
shutil.rmtree(output_dir)
nextflow_helper.clean_files()
def run(self):
self._make_input_files()
ref_fai = os.path.join(self.ref_dir, "ref.fa.fai")
genome_size = pyfastaq.tasks.stats_from_fai(ref_fai)["total_length"]
cmd = " ".join([
self.cortex_run_calls,
"--fastaq_index",
self.cortex_reads_index,
"--auto_cleaning yes",
"--first_kmer 31",
"--bc yes",
"--pd no",
"--outdir",
self.cortex_outdir,
"--outvcf cortex",
"--ploidy 2",
"--stampy_hash",
os.path.join(self.ref_dir, "ref.stampy"),
"--stampy_bin",
self.stampy_script,
"--list_ref_fasta",
self.cortex_ref_fofn,
"--refbindir",
self.ref_dir,
"--genome_size",
str(genome_size),
"--qthresh 5",
"--mem_height",
str(self.mem_height),
"--mem_width 100",
"--vcftools_dir",
self.vcftools_dir,
"--do_union yes",
"--ref CoordinatesAndInCalling",
"--workflow independent",
"--logfile",
self.cortex_log,
])
utils.syscall(cmd)
self._tidy_files()
self._run_mccortex_view_kmers()
def _run_mccortex_view_kmers(self):
# Example filename we're looking for:
# cortex.out/binaries/cleaned/k31/sample_name.kmer31.q5cleaned_1.ctx
cleaned_dir = os.path.join(self.cortex_outdir, "binaries", "cleaned")
if not os.path.exists(cleaned_dir):
print(
"Cleaned directory not found " + cleaned_dir +
" ... cannot run mccortex view kmers",
file=sys.stderr,
)
return
kmer_dirs = [x for x in os.listdir(cleaned_dir) if x.startswith("k")]
if len(kmer_dirs) != 1:
print(
"Error finding kmers directory inside " + cleaned_dir +
" ... cannot run mccortex view kmers",
file=sys.stderr,
)
kmer_dir = os.path.join(cleaned_dir, kmer_dirs[0])
ctx_files = [x for x in os.listdir(kmer_dir) if x.endswith(".ctx")]
if len(ctx_files) != 1:
print(
"Error finding ctx file inside " + kmer_dir +
" ... cannot run mccortex view kmers",
file=sys.stderr,
)
ctx_file = os.path.join(kmer_dir, ctx_files[0])
assert os.path.exists(ctx_file)
command = " ".join([
self.mccortex,
"view",
"--kmers",
ctx_file,
r"""| awk '{print $1,$2}' | gzip -9 > """,
self.kmer_counts_file,
])
utils.syscall(command)
def run(options):
if len(options.reads_files) % 2 != 0:
raise Exception(
f"Must provide even number of reads files. Got these files: {', '.join(options.reads_files)}"
)
reads1 = [f for i, f in enumerate(options.reads_files) if i % 2 == 0]
reads2 = [f for i, f in enumerate(options.reads_files) if i % 2 != 0]
assert len(reads1) == len(reads2)
if options.force and os.path.exists(options.outdir):
utils.syscall(f"rm -r {options.outdir}")
var_call_one_sample_pipeline.run(
reads1,
reads2,
options.ref_dir,
options.outdir,
sample_name=options.sample_name,
cortex_mem_height=options.mem_height,
debug=options.debug,
keep_bam=options.keep_bam,
)
