def runFasta(seq_dir, genomes_dir, fasta_dir):
"""
Run FASTA on protein sequences between new genome against all in house genomes
FASTA searches a protein or DNA sequence data bank
version 35.04 Aug. 25, 2009
W.R. Pearson & D.J. Lipman PNAS (1988) 85:2444-2448
"""
util.createDir(fasta_dir)
# List of in-house genomes
util.checkDir(genomes_dir)
genome_files = []
logger.info("Create fasta results directory for each in-house reference genome")
for genome_file in os.listdir(genomes_dir):
if '.faa' in genome_file:
genome_files.append(genome_file)
# Create fasta results directory for each in-house genome
util.createDir("%s/%s" % (fasta_dir, genome_file.split(".")[0]))
logger.info(genome_file)
util.checkDir(seq_dir)
if IS_LSF:
# Rename new genome sequences for job array to be mygenome_1.faa mygenome_2.faa ...
seq_num = 0
for seq_file in os.listdir(seq_dir):
if not '.faa' in seq_file:
continue
seq_num += 1
if 'mygenome_' in seq_file and '.faa' in seq_file:
continue
seq_newfilepath = "%s/mygenome_%s.faa" % (seq_dir, seq_num)
seq_filepath = "%s/%s" % (seq_dir, seq_file)
os.rename(seq_filepath, seq_newfilepath)
# Submit bsub job array on mygenome_${LSB_JOBINDEX}.faa against one refgenome at a time
bsub_dir = "bsub"
util.checkDir(bsub_dir)
for genome_file in genome_files:
res_dir = "%s/%s" % (fasta_dir, genome_file.split(".")[0])
cmd = "fasta35 -z 1 -Q -H -S -m 10 %s/mygenome_${LSB_JOBINDEX}.faa %s/%s > %s/mygenome_${LSB_JOBINDEX}.fa" % (seq_dir, genomes_dir, genome_file, res_dir)
util.submitJobArray(jobname="genepy-fasta", jobnum=seq_num, jobdir=bsub_dir, cmd=cmd)
util.submitJobDependency('genepy-fasta')
logger.info("Fasta on LSF finished")
else:
# List of new genome sequences
for seq_file in os.listdir(seq_dir):
if not '.faa' in seq_file:
continue
res_file = seq_file.split(".")[0] + ".fa"
for genome_file in genome_files:
res_dir = "%s/%s" % (fasta_dir, genome_file.split(".")[0])
cmd = "fasta35 -z 1 -Q -H -S -m 10 %s/%s %s/%s > %s/%s" % (seq_dir, seq_file, genomes_dir, genome_file, res_dir, res_file)
util.runProcess(cmd)
logger.info(seq_file)
logger.info("Fasta finished")
def runReciprocalFasta(seq_dir, genome_file, fasta_dir):
"""
Run FASTA between extracted in-house protein sequences against new genome
FASTA searches a protein or DNA sequence data bank
version 35.04 Aug. 25, 2009
W.R. Pearson & D.J. Lipman PNAS (1988) 85:2444-2448
"""
util.createDir(fasta_dir)
# Check new genome
util.checkFile(genome_file)
# Check ref genome extracted sequences
util.checkDir(seq_dir)
res_dir = fasta_dir
if IS_LSF:
# Rename new genome sequences for job array to be refgenome_1.faa refgenome_2.faa ...
seq_num = 0
for seq_file in os.listdir(seq_dir):
if not '.faa' in seq_file:
continue
seq_num += 1
if 'refgenome_' in seq_file and '.faa' in seq_file:
continue
seq_newfilepath = "%s/refgenome_%s.faa" % (seq_dir, seq_num)
seq_filepath = "%s/%s" % (seq_dir, seq_file)
os.rename(seq_filepath, seq_newfilepath)
# Submit bsub job array on refgenome_${LSB_JOBINDEX}.faa against mygenome
bsub_dir = "bsub"
util.checkDir(bsub_dir)
cmd = "fasta35 -z 1 -Q -H -S -m 10 %s/refgenome_${LSB_JOBINDEX}.faa %s > %s/refgenome_${LSB_JOBINDEX}.fa" % (seq_dir, genome_file, res_dir)
util.submitJobArray(jobname="genepy-recipfasta", jobnum=seq_num, jobdir=bsub_dir, cmd=cmd)
util.submitJobDependency('genepy-recipfasta')
logger.info("Reciprocal Fasta on LSF finished")
else:
# List of inhouse extracted genome sequences
for seq_file in os.listdir(seq_dir):
if not '.faa' in seq_file:
continue
res_file = seq_file.split(".")[0] + ".fa"
cmd = "fasta35 -z 1 -Q -H -S -m 10 %s/%s %s > %s/%s" % (seq_dir, seq_file, genome_file, res_dir, res_file)
util.runProcess(cmd)
logger.info(seq_file)
logger.info("Reciprocal Fasta finished")
def runHamapScan(seq_dir, hamap_dir):
"""
HAMAP: High-quality Automated and Manual Annotation of microbial Proteomes
ftp download site: ftp://ftp.expasy.org/databases/hamap/
pfscan compares a protein or nucleic acid sequence against a profile
library. The result is an unsorted list of profile-sequence matches.
download site: http://www.isrec.isb-sib.ch/ftp-server/pftools/pft2.3/
"""
util.createDir(hamap_dir)
util.checkDir(seq_dir)
hamap_profile_file = "%s/hamap/hamap.prf" % os.path.dirname(__file__)
if IS_LSF:
# Rename new genome sequences for job array to be mygenome_1.faa mygenome_2.faa ...
seq_num = 0
for seq_file in os.listdir(seq_dir):
if not '.faa' in seq_file:
continue
seq_num += 1
if 'mygenome_' in seq_file and '.faa' in seq_file:
continue
seq_newfilepath = "%s/mygenome_%s.faa" % (seq_dir, seq_num)
seq_filepath = "%s/%s" % (seq_dir, seq_file)
os.rename(seq_filepath, seq_newfilepath)
# Submit bsub job array on mygenome_${LSB_JOBINDEX}.faa against hamap profile
bsub_dir = "bsub"
util.checkDir(bsub_dir)
cmd = "pfscan -klf %s/mygenome_${LSB_JOBINDEX}.faa %s > %s/mygenome_${LSB_JOBINDEX}.out" % (seq_dir, hamap_profile_file, hamap_dir)
util.submitJobArray(jobname='genepy-hamap', jobnum=seq_num, jobdir=bsub_dir, cmd=cmd)
util.submitJobDependency('genepy-hamap')
logger.info("HAMAP scan on LSF finished")
else:
# List of new genome sequences
for seq_file in os.listdir(seq_dir):
if not '.faa' in seq_file:
continue
res_file = seq_file.split(".")[0] + ".out"
cmd = "pfscan -klf %s/%s %s > %s/%s" % (seq_dir, seq_file, hamap_profile_file, hamap_dir, res_file)
util.runProcess(cmd)
logger.info("HAMAP scan finished")