def Fzip_inplace(input, cpus):
'''
function to zip as fast as it can, pigz -> bgzip -> gzip
'''
if lib.which('pigz'):
cmd = ['pigz', '-f', '-p', str(cpus), input]
elif lib.which('bgzip'):
cmd = ['bgzip', '-f', '-@', str(cpus), input]
else:
cmd = ['gzip', '-f', input]
try:
lib.runSubprocess(cmd, '.', lib.log)
except NameError:
subprocess.call(cmd)
def choose_aligner():
'''
function to choose alignment method for mapping reads to transcripts to determine
orientation of the trinity transcripts. rapmap -> bowtie2 -> hisat2
note hisat2 is probably not ideal for this, but should work okay.
'''
aligner = ''
if lib.which('rapmap'):
aligner = 'rapmap'
elif lib.which('bowtie2'):
aligner = 'bowtie2'
else:
aligner = 'hisat2'
return aligner
#run Phobius to predict secreted proteins and membrane, default is local if installed, otherwise remote
phobius_out = os.path.join(outputdir, 'annotate_misc', 'phobius.results.txt')
phobiusLog = os.path.join(outputdir, 'logfiles', 'phobius.log')
lib.log.info("Predicting secreted and transmembrane proteins using Phobius")
if not lib.checkannotations(phobius_out):
subprocess.call([
os.path.join(parentdir, 'util', 'phobius-multiproc.py'), '-i',
Proteins, '-o', phobius_out, '-e', args.email, '-l', phobiusLog
])
#run signalP if installed, have to manually install, so test if exists first, then run it if it does, parse results
signalp_out = os.path.join(outputdir, 'annotate_misc', 'signalp.results.txt')
secreted_out = os.path.join(outputdir, 'annotate_misc',
'annotations.secretome.txt')
membrane_out = os.path.join(outputdir, 'annotate_misc',
'annotations.transmembrane.txt')
if lib.which('signalp'):
lib.log.info("Predicting secreted proteins with SignalP")
if not lib.checkannotations(signalp_out):
lib.signalP(Proteins, os.path.join(outputdir, 'annotate_misc'),
signalp_out)
lib.parsePhobiusSignalP(phobius_out, signalp_out, membrane_out,
secreted_out)
else:
lib.log.info(
"SignalP not installed, secretome prediction less accurate using only Phobius"
)
lib.parsePhobiusSignalP(phobius_out, False, membrane_out, secreted_out)
num_secreted = lib.line_count(secreted_out)
num_mem = lib.line_count(membrane_out)
lib.log.info('{0:,}'.format(num_secreted) + ' secretome and ' +
'{0:,}'.format(num_mem) + ' transmembane annotations added')
#run BUSCO OGS search
busco_out = os.path.join(outputdir, 'annotate_misc', 'annotations.busco.txt')
lib.log.info("Annotating proteins with BUSCO %s models" % args.busco_db)
buscoDB = os.path.join(parentdir, 'DB', args.busco_db)
if not lib.checkannotations(busco_out):
lib.runBUSCO(Proteins, buscoDB, args.cpus, os.path.join(outputdir, 'annotate_misc'), busco_out)
num_annotations = lib.line_count(busco_out)
lib.log.info('{0:,}'.format(num_annotations) + ' annotations added')
#run Phobius if local is installed, otherwise use funannotate remote
phobius_out = os.path.join(outputdir, 'annotate_misc', 'phobius.results.txt')
phobiusLog = os.path.join(outputdir, 'logfiles', 'phobius.log')
if args.phobius:
phobius_out = args.phobius
else:
if lib.which('phobius.pl'):
if not lib.checkannotations(phobius_out):
lib.log.info("Predicting secreted and transmembrane proteins using Phobius")
subprocess.call([os.path.join(parentdir, 'util', 'phobius-multiproc.py'), '-i', Proteins, '-o', phobius_out, '-l', phobiusLog])
else:
if lib.checkannotations(phobius_out):
lib.log.info("Found phobius pre-computed results")
else:
lib.log.info("Skipping phobius predictions, try funannotate remote -m phobius")
#run signalP if installed, have to manually install, so test if exists first, then run it if it does, parse results
signalp_out = os.path.join(outputdir, 'annotate_misc', 'signalp.results.txt')
secreted_out = os.path.join(outputdir, 'annotate_misc', 'annotations.secretome.txt')
membrane_out = os.path.join(outputdir, 'annotate_misc', 'annotations.transmembrane.txt')
if lib.which('signalp'):
lib.log.info("Predicting secreted proteins with SignalP")
if not lib.checkannotations(signalp_out):
lib.log.debug(cmd_args)
#create tmpdir to store fasta files and output files
TMPDIR = 'phobius_' + str(os.getpid())
#split fasta
lib.splitFASTA(args.input, TMPDIR)
#now get list of files in tmpdir
proteins = []
for file in os.listdir(TMPDIR):
if file.endswith('.fa'):
proteins.append(file)
#now run the script
if lib.which('phobius.pl'):
lib.runMultiProgress(runPhobiusLocal, proteins, multiprocessing.cpu_count())
else:
lib.runMultiProgress(runPhobiusRemote, proteins, 29) #max is 30 jobs at a time
#collect all results
phobius = []
for file in os.listdir(TMPDIR):
if file.endswith('.phobius'):
phobius.append(os.path.join(TMPDIR,file))
#write output
TMdomain = 0
SigPep = 0
with open(args.out, 'w') as output:
output.write("%s\t%s\t%s\t%s\n" % ('ID', 'TM', 'SP', 'Prediction'))
lib.log.info("Annotating proteins with EggNog 4.5 database")
if not lib.checkannotations(eggnog_out):
lib.runEggNog(Proteins, os.path.join(parentdir, 'DB', args.eggnog_db+'_4.5.hmm'), os.path.join(parentdir, 'DB', args.eggnog_db+'.annotations.tsv'), args.cpus, 1e-10, os.path.join(outputdir, 'annotate_misc'), eggnog_out)
num_annotations = lib.line_count(eggnog_out)
lib.log.info('{0:,}'.format(num_annotations) + ' annotations added')
#run BUSCO OGS search
busco_out = os.path.join(outputdir, 'annotate_misc', 'annotations.busco.txt')
lib.log.info("Annotating proteins with BUSCO %s models" % args.busco_db)
buscoDB = os.path.join(parentdir, 'DB', args.busco_db)
if not lib.checkannotations(busco_out):
lib.runBUSCO(Proteins, buscoDB, args.cpus, os.path.join(outputdir, 'annotate_misc'), busco_out)
num_annotations = lib.line_count(busco_out)
lib.log.info('{0:,}'.format(num_annotations) + ' annotations added')
#run signalP if installed, have to manually install, so test if exists first, then run it if it does
signalp_out = os.path.join(outputdir, 'annotate_misc', 'annotations.signalp.txt')
if lib.which('signalp'):
lib.log.info("Predicting secreted proteins with SignalP")
if not lib.checkannotations(signalp_out):
lib.signalP(Proteins, os.path.join(outputdir, 'annotate_misc'), signalp_out)
num_annotations = lib.line_count(signalp_out)
lib.log.info('{0:,}'.format(num_annotations) + ' annotations added')
else:
lib.log.info("SignalP not installed, skipping")
if not args.skip_iprscan:
if not args.iprscan:
#run interpro scan
IPROUT = os.path.join(outputdir, 'annotate_misc', 'iprscan')
PROTS = os.path.join(outputdir, 'annotate_misc', 'protein_tmp')
for i in IPROUT,PROTS:
if not os.path.exists(i):
def runPASAtrain(genome, transcripts, stranded, intronlen, cpus, dbname,
output):
'''
function will run PASA align assembly and then choose best gene models for training
'''
if cpus > 2:
pasa_cpus = cpus / 2
else:
pasa_cpus = 2
#create tmpdir
folder = os.path.join(tmpdir, 'pasa')
if not os.path.isdir(folder):
os.makedirs(folder)
#create pasa and transdecoder logfiles
pasa_log = os.path.join(folder, 'pasa.log')
transdecoder_log = os.path.join(folder, 'transdecoder.log')
#get config files and edit
alignConfig = os.path.join(folder, 'alignAssembly.txt')
pasaDBname = dbname.replace('-', '_')
with open(alignConfig, 'w') as config1:
with open(
os.path.join(PASA, 'pasa_conf',
'pasa.alignAssembly.Template.txt'),
'rU') as template1:
for line in template1:
line = line.replace('<__MYSQLDB__>', pasaDBname)
config1.write(line)
if not os.path.isfile(
os.path.join(folder, pasaDBname + '.assemblies.fasta')):
#now run first PASA step, note this will dump any database with same name
lib.log.info(
"Running PASA alignment step using {:,} transcripts".format(
lib.countfasta(transcripts)))
cmd = [
os.path.join(PASA, 'scripts', 'Launch_PASA_pipeline.pl'), '-c',
os.path.abspath(alignConfig), '-r', '-C', '-R', '-g',
os.path.abspath(genome), '--ALIGNERS', 'blat,gmap', '-t',
os.path.abspath(transcripts), '--stringent_alignment_overlap',
args.pasa_alignment_overlap, '--TRANSDECODER',
'--MAX_INTRON_LENGTH',
str(intronlen), '--CPU',
str(pasa_cpus)
]
if stranded != 'no':
cmd = cmd + ['--transcribed_is_aligned_orient']
lib.runSubprocess(cmd, folder, lib.log)
else:
lib.log.info('Existing PASA assemblies found {:}'.format(
os.path.join(folder, pasaDBname + '.assemblies.fasta')))
#generate TSV gene-transcripts
numLoci = getPASAtranscripts2genes(
os.path.join(folder, pasaDBname + '.pasa_assemblies.gff3'),
os.path.join(folder, 'pasa.gene2transcripts.tsv'))
numTranscripts = lib.countfasta(
os.path.join(folder, pasaDBname + '.assemblies.fasta'))
lib.log.info(
"Assigned {:,} transcipts to {:,} loci using {:}% overlap threshold".
format(numTranscripts, numLoci, args.pasa_alignment_overlap))
lib.log.info("Getting PASA models for training with TransDecoder")
pasa_training_gff = os.path.join(
folder, pasaDBname + '.assemblies.fasta.transdecoder.genome.gff3')
if lib.which('TransDecoder.LongOrfs') and lib.which(
'TransDecoder.Predict'):
cmd = [
'TransDecoder.LongOrfs', '-t', pasaDBname + '.assemblies.fasta',
'--gene_trans_map', 'pasa.gene2transcripts.tsv'
]
lib.runSubprocess(cmd, folder, lib.log)
cmd = [
'TransDecoder.Predict', '-t', pasaDBname + '.assemblies.fasta',
'--single_best_only'
]
lib.runSubprocess(cmd, folder, lib.log)
cmd = [
os.path.join(PASA, 'pasa-plugins', 'transdecoder',
'cdna_alignment_orf_to_genome_orf.pl'),
pasaDBname + '.assemblies.fasta.transdecoder.gff3',
pasaDBname + '.pasa_assemblies.gff3',
pasaDBname + '.assemblies.fasta'
]
lib.runSubprocess2(cmd, folder, lib.log, pasa_training_gff)
else:
cmd = [
os.path.join(PASA, 'scripts', 'pasa_asmbls_to_training_set.dbi'),
'--pasa_transcripts_fasta', pasaDBname + '.assemblies.fasta',
'--pasa_transcripts_gff3', pasaDBname + '.pasa_assemblies.gff3'
]
lib.runSubprocess(cmd, folder, lib.log)
#grab final result
shutil.copyfile(pasa_training_gff, output)