def blast_db(self):
"""A blastable database of refseq + all marine organism genes"""
blast_db = BLASTdb(self.p.genes, 'prot')
if not self.p.genes.exists:
# We are going to cat a whole of files together #
print "Regrouping all fasta files together..."
all_genes = self.refseq_bact_orig \
+ self.refseq_arch_orig \
+ self.missing_marine \
+ self.missing_fresh
shell_output("zcat %s > %s" % (' '.join(all_genes), self.p.genes))
self.timer.print_elapsed()
# Check that all files ended with a newline #
print "Checking that sequence counts match..."
assert len(blast_db) == sum(map(len,self.refseq_bact_orig)) \
+ sum(map(len,self.refseq_arch_orig)) \
+ sum(map(len,self.missing_marine)) \
+ sum(map(len,self.missing_fresh))
self.timer.print_elapsed()
if not self.p.pin.exists:
# Call make DB #
print "Building a BLAST database..."
blast_db.makeblastdb(logfile=self.p.log, out=self.p.out)
self.timer.print_elapsed()
return blast_db
def blast_db(self):
"""A blastable database of refseq + all marine organism genes"""
blast_db = BLASTdb(self.p.genes, 'prot')
if not self.p.genes.exists:
# We are going to cat a whole of files together #
print "Regrouping all fasta files together..."
all_genes = self.refseq_bact_orig \
+ self.refseq_arch_orig \
+ self.missing_marine \
+ self.missing_fresh
shell_output("zcat %s > %s" % (' '.join(all_genes), self.p.genes))
self.timer.print_elapsed()
# Check that all files ended with a newline #
print "Checking that sequence counts match..."
assert len(blast_db) == sum(map(len,self.refseq_bact_orig)) \
+ sum(map(len,self.refseq_arch_orig)) \
+ sum(map(len,self.missing_marine)) \
+ sum(map(len,self.missing_fresh))
self.timer.print_elapsed()
if not self.p.pin.exists:
# Call make DB #
print "Building a BLAST database..."
blast_db.makeblastdb(logfile=self.p.log, out=self.p.out)
self.timer.print_elapsed()
return blast_db
def retrieve_from_nt(self):
"""Get all GI numbers with their length from local NT database.
Then filter out the ones that are too long."""
temp_file = new_temp_file()
shell_output("blastdbcmd -db nt -entry all -outfmt '%g %l' > " + temp_file)
with_len = (map(int,line.strip('\n').split()) for line in temp_file)
self.writelines(str(gid) + '\n' for gid, length in with_len if length < self.length_cutoff)
temp_file.remove()
def sqlite_by_shell(self, destination):
"""Method with shell and a temp file. This is hopefully fast."""
script_path = new_temp_path()
self.sqlite_dump_shell(script_path)
from shell_command import shell_output
shell_output('sqlite3 -bail -init "%s" "%s" .quit' %
(script, destination))
script.remove()
def count(self):
# Import module #
from shell_command import shell_output
# Case when we are not compressed #
if not self.gzipped:
return int(int(shell_output("cat %s | wc -l" % self.path)) / 4)
# If we are gzipped we can just use zcat or gzcat on macOS #
program = 'gzcat' if sys.platform != 'linux' else 'zcat'
command = "%s %s | wc -l" % (program, self.path)
return int(int(shell_output(command)) / 4)
def blast_db(self):
"""A blastable database of all genes"""
db = BLASTdb(self.p.all_fasta, self.seq_type)
if not self.p.all_nin and not self.p.all_pin:
print "--> STEP 1: Building BLASTable database with all genes..."
shell_output('gunzip -c %s > %s' % (' '.join(genomes.values()), db))
assert len(db) == sum(map(len, genomes.values()))
db.makeblastdb()
self.timer.print_elapsed()
return db
def fresh_fasta(self):
"""A file containing all the fresh water genes"""
fasta = FASTA(self.p.fresh_fasta)
if not fasta.exists:
print "Building fasta file with all fresh genes..."
fresh = [g for g in genomes.values() if g.fresh]
shell_output('gunzip -c %s > %s' % (' '.join(fresh), fasta))
assert len(fasta) == sum(map(len, fresh))
self.timer.print_elapsed()
return fasta
def fresh_fasta(self):
"""A file containing all the fresh water genes"""
fasta = FASTA(self.p.fresh_fasta)
if not fasta.exists:
print "Building fasta file with all fresh genes..."
fresh = [g for g in genomes.values() if g.fresh]
shell_output('gunzip -c %s > %s' % (' '.join(fresh), fasta))
assert len(fasta) == sum(map(len, fresh))
self.timer.print_elapsed()
return fasta
def retrieve_from_nt(self):
"""Get all GI numbers with their length from local NT database.
Then filter out the ones that are too long."""
temp_file = new_temp_file()
shell_output("blastdbcmd -db nt -entry all -outfmt '%g %l' > " +
temp_file)
with_len = (map(int, line.strip('\n').split()) for line in temp_file)
self.writelines(
str(gid) + '\n' for gid, length in with_len
if length < self.length_cutoff)
temp_file.remove()
def run(self):
# Combine reads but in fastq format this time #
paths = [sample.renamed for sample in self.cluster]
shell_output("cat %s > %s" % (" ".join(paths), self.reads))
# Clean #
shutil.rmtree(self.p.clusters_dir)
# Run command #
cdhit = sh.Command(cdhit_script)
cdhit("-i", self.reads, "-o", self.p.clusters_dir, "-p", TmpFile.from_string("[ACTG]"))
# Create the centers file with good names #
self.cdhit_centers.rename_with_num("OTU-", self.centers)
def run(self):
# Combine reads but in fastq format this time #
paths = [sample.renamed for sample in self.cluster]
shell_output('cat %s > %s' % (' '.join(paths), self.reads))
# Clean #
shutil.rmtree(self.p.clusters_dir)
# Run command #
cdhit = sh.Command(cdhit_script)
cdhit('-i', self.reads, '-o', self.p.clusters_dir, '-p',
TmpFile.from_string('[ACTG]'))
# Create the centers file with good names #
self.cdhit_centers.rename_with_num('OTU_', self.centers)
def sqlite_dump_shell(self, script_path):
"""Generate a text dump compatible with SQLite by using
shell commands. Place this script at *script_path*."""
# First the schema #
shell_output('mdb-schema "%s" sqlite >> "%s"' % (self.path, script_path))
# Start a transaction, speeds things up when importing #
script_path.append("\n\n\nBEGIN TRANSACTION;\n")
# Then export every table #
for table in self.tables:
command = 'mdb-export -I sqlite "%s" "%s" >> "%s"'
shell_output(command % (self.path, table, script_path))
# End the transaction
script_path.append("\n\n\nEND TRANSACTION;\n")
def sqlite_dump_shell(self, script_path):
"""Generate a text dump compatible with SQLite by using
shell commands. Place this script at *script_path*."""
# First the schema #
from shell_command import shell_output
shell_output('mdb-schema "%s" sqlite >> "%s"' %
(self.path, script_path))
# Start a transaction, speeds things up when importing #
script_path.append("\n\n\nBEGIN TRANSACTION;\n")
# Then export every table #
for table in self.tables:
command = 'mdb-export -I sqlite "%s" "%s" >> "%s"'
shell_output(command % (self.path, table, script_path))
# End the transaction
script_path.append("\n\n\nEND TRANSACTION;\n")
def run(self):
# Make preferences files #
with open(self.p.config, 'w') as handle: handle.write(default_config)
with open(self.p.param, 'w') as handle: handle.write(default_param)
# Make symlink for the input #
if os.path.lexists(self.fasta_path): os.remove(self.fasta_path)
os.symlink(self.sample.p.clean_fasta, self.fasta_path)
# Remove the PGDB if it exists #
if os.path.exists(self.pgdb_path): shutil.rmtree(self.pgdb_path)
# Make a stupid link #
if os.path.lexists("blastDB"): os.remove("blastDB")
os.symlink(metapath_dir + "blastDB/", "blastDB")
# The command #
with open(self.p.out, 'w') as handle: handle.write(self.bash_str + '\n\n')
shell_output(self.bash_str)
# Clean up #
if os.path.exists("blastDB"): os.remove("blastDB")
if os.path.exists(self.fasta_path): os.remove(self.fasta_path)
# Check for errors #
with open(self.p.out, 'r') as handle: log = handle.read()
if 'Error!' in log: raise Exception('Metapathway tools reported an error in file "%s".' % self.p.out)
def extract(self):
# Call extraction #
shell_output('sffinfo -s %s > %s' % (self.p.raw_sff, self.p.raw_fasta))
shell_output('sffinfo -q %s > %s' % (self.p.raw_sff, self.p.raw_qual))
shell_output('sffinfo -m %s > %s' % (self.p.raw_sff, self.p.manifest))
# Convert #
sh.fasta_to_fastq(self.p.raw_fasta, self.p.raw_qual, self.p.raw_fastq)
def extract(self):
# Call extraction #
shell_output('sffinfo -s %s > %s' % (self.p.raw_sff, self.p.raw_fasta))
shell_output('sffinfo -q %s > %s' % (self.p.raw_sff, self.p.raw_qual))
shell_output('sffinfo -m %s > %s' % (self.p.raw_sff, self.p.manifest))
# Convert #
sh.fasta_to_fastq(self.p.raw_fasta, self.p.raw_qual, self.p.raw_fastq)
def raw(self):
# Call extraction #
shell_output('sffinfo -s %s > %s' % (self.p.raw_sff, self.p.raw_fasta))
shell_output('sffinfo -q %s > %s' % (self.p.raw_sff, self.p.raw_qual))
shell_output('sffinfo -m %s > %s' % (self.p.raw_sff, self.p.manifest))
# Convert #
sh.fasta_to_fastq(self.p.raw_fasta, self.p.raw_qual, self.p.raw_fastq)
# Fast QC #
sh.fastqc(self.p.raw_fastq, '-o', self.p.raw_dir, '-q')
if os.path.exists(self.p.raw_dir + 'raw_fastqc.zip'): os.remove(self.p.raw_dir + 'raw_fastqc.zip')
def combine_reads(self):
paths = [sample.fasta.path for sample in self]
shell_output('cat %s > %s' % (' '.join(paths), self.reads))
for pool in pools: over.add_iterator(over_iterator(pool.good_barcodes.assembled.good_primers.qual_filtered))
over.close()
over.graphs[-1].plot()
crest = SimpleCrestTaxonomy(over, folder)
crest.assign()
crest.composition.graph.plot()
rdp = SimpleRdpTaxonomy(over, folder)
rdp.assign()
rdp.composition.graph.plot()
# Check unassembled mate pairs #
unassembled = [p.good_barcodes.unassembled for p in pools]
paths = [u.flipped_reads.path for u in unassembled]
folder = DirectoryPath(illumitag.projects['evaluation'].base_dir + "unassembled_taxonomy/")
all_unassembled = FASTA(folder + 'unassembled_reads.fasta')
shell_output('cat %s > %s' % (' '.join(paths), all_unassembled))
tax = SimpleRdpTaxonomy(all_unassembled, folder)
tax.assign()
tax.composition.graph.plot()
# Upload raw samples for ENA #
for pool in pools: pool.create_raw_samples()
for s in samples:
print s.short_name
s.ena.upload_to_ena()
# Submit to ENA #
from illumitag.helper.ena import MakeAllXML
make_xml = MakeAllXML(proj, cluster)
make_xml.write_files()
def combine_reads(self):
"""This is the first function should call. It will combine all the
reads of all the samples of this cluster into one big FASTA file."""
paths = [sample.fasta.path for sample in self]
shell_output('cat %s > %s' % (' '.join(paths), self.reads))
return self.reads
def regroup(self):
if self.format == 'xml':
with open(self.out_path, 'w') as handle:
merge_blast_xml(map(open,(q.out_path for q in self.sub_queries)), handle)
else:
shell_output("cat %s > %s" % (' '.join(q.out_path for q in self.sub_queries), self.out_path))
def sqlite_by_shell(self, destination):
"""Method with shell and a temp file. This is hopefully fast."""
script_path = new_temp_path()
self.sqlite_dump_shell(script_path)
shell_output('sqlite3 -bail -init "%s" "%s" .quit' % (script, destination))
script.remove()
def uncompress(self):
shell_output('gunzip -c %s > %s' % (self.fwd_path, self.fwd))
shell_output('gunzip -c %s > %s' % (self.rev_path, self.rev))
$ ./gen_test.py
"""
# Built-in modules #
import time, datetime
# Internal modules #
from gefes import projects
# Third party modules #
from shell_command import shell_output
import playdoh
# Timer #
now = time.time()
###############################################################################
print "Making test files"
# Do it #
pairs = []
pairs += [(projects['humic'][i].fwd_path, projects['test'][i].fwd_path) for i in range(3)]
pairs += [(projects['humic'][i].rev_path, projects['test'][i].rev_path) for i in range(3)]
process = lambda x : shell_output('zcat %s |head -n 4000| gzip > %s' % (x[0],x[1]))
# Run it in parallel #
playdoh.map(process, pairs, cpu=len(pairs))
# Report Success #
run_time = datetime.timedelta(seconds=round(time.time()-now))
print "\033[0;32mRun time: '%s'\033[0m" % (run_time)
def no_barcode_split(self):
"""Will translate the SFF files without barcodes. Just to explore an SFF file."""
shell_output('sffinfo -s %s > %s' % (self.path, self.raw_fasta_path))
shell_output('sffinfo -q %s > %s' % (self.path, self.raw_qual_path))
sh.fasta_to_fastq(self.raw_fasta_path, self.raw_qual_path, self.fastq)
def compress_fast(self, new_path):
"""Do the compression with an external shell command call."""
# We don't want python to be buffering the text for speed #
from shell_command import shell_output
cmd = 'gzip --stdout %s > %s' % (self.path, new_path)
return shell_output(cmd)
def join_outputs(self):
"""Join the outputs"""
shell_output('cat %s > %s' % (' '.join(q.out_path for q in self.queries), self.out_path))
def no_barcode_split(self):
"""Will translate the SFF files without barcodes. Just to explore an SFF file."""
shell_output('sffinfo -s %s > %s' % (self.path, self.raw_fasta_path))
shell_output('sffinfo -q %s > %s' % (self.path, self.raw_qual_path))
sh.fasta_to_fastq(self.raw_fasta_path, self.raw_qual_path, self.fastq)
