def runDiamond(input, query, cpus, output):
#create DB of protein sequences
cmd = [
'diamond', 'makedb', '--threads',
str(cpus), '--in', query, '--db', 'diamond'
]
lib.runSubprocess4(cmd, output, lib.log)
#now run search
cmd = [
'diamond', 'blastx', '--threads',
str(cpus), '-q', input, '--db', 'diamond', '-o', 'diamond.matches.tab',
'-e', '1e-10', '-k', '0', '--more-sensitive', '-f', '6', 'sseqid',
'slen', 'sstart', 'send', 'qseqid', 'qlen', 'qstart', 'qend', 'pident',
'length', 'evalue', 'score', 'qcovhsp', 'qframe'
]
lib.runSubprocess4(cmd, output, lib.log)
def removeAntiSense(input, readTuple, output):
'''
function will map reads to the input transcripts, determine strandedness, and then filter
out transcripts that were assembled in antisense orientation. idea here is that the antisense
transcripts, while potentially valid, aren't going to help update the gene models and perhaps
could hurt the annotation effort?
'''
lib.log.info("Running anti-sense filtering of Trinity transcripts")
bamthreads = (
args.cpus +
2 // 2) // 2 #use half number of threads for bam compression threads
aligner = choose_aligner()
if aligner == 'hisat2':
bowtie2bam = os.path.join(tmpdir, 'hisat2.transcripts.coordSorted.bam')
if not os.path.isfile(bowtie2bam):
lib.log.info("Building Hisat2 index of " +
"{0:,}".format(lib.countfasta(input)) +
" trinity transcripts")
cmd = [
'hisat2-build', input,
os.path.join(tmpdir, 'hisat2.transcripts')
]
lib.runSubprocess4(cmd, '.', lib.log)
#now launch the aligner
lib.log.info("Aligning reads to trinity transcripts with Hisat2")
hisat2cmd = [
'hisat2', '-p',
str(args.cpus), '-k', '50', '--max-intronlen',
str(args.max_intronlen), '-x',
os.path.join(tmpdir, 'hisat2.transcripts')
]
if readTuple[2]:
hisat2cmd = hisat2cmd + ['-U', readTuple[2]]
if readTuple[0] and readTuple[1]:
hisat2cmd = hisat2cmd + [
'-1', readTuple[0], '-2', readTuple[1]
]
cmd = [
os.path.join(parentdir, 'util', 'sam2bam.sh'),
" ".join(hisat2cmd),
str(bamthreads), bowtie2bam
]
lib.runSubprocess4(cmd, '.', lib.log)
elif aligner == 'bowtie2':
#using bowtie2
bowtie2bam = os.path.join(tmpdir,
'bowtie2.transcripts.coordSorted.bam')
if not os.path.isfile(bowtie2bam):
lib.log.info("Building Bowtie2 index of " +
"{0:,}".format(lib.countfasta(input)) +
" trinity transcripts")
cmd = [
'bowtie2-build', input,
os.path.join(tmpdir, 'bowtie2.transcripts')
]
lib.runSubprocess4(cmd, '.', lib.log)
#now launch the subprocess commands in order
lib.log.info("Aligning reads to trinity transcripts with Bowtie2")
bowtie2cmd = [
'bowtie2', '-p',
str(args.cpus), '-k', '50', '--local', '--no-unal', '-x',
os.path.join(tmpdir, 'bowtie2.transcripts')
]
if readTuple[2]:
bowtie2cmd = bowtie2cmd + ['-U', readTuple[2]]
if readTuple[0] and readTuple[1]:
bowtie2cmd = bowtie2cmd + [
'-1', readTuple[0], '-2', readTuple[1]
]
cmd = [
os.path.join(parentdir, 'util', 'sam2bam.sh'),
" ".join(bowtie2cmd),
str(bamthreads), bowtie2bam
]
lib.runSubprocess4(cmd, '.', lib.log)
elif aligner == 'rapmap':
#using bowtie2
bowtie2bam = os.path.join(tmpdir, 'rapmap.transcripts.coordSorted.bam')
if not os.path.isfile(bowtie2bam):
lib.log.info("Building RapMap index of " +
"{0:,}".format(lib.countfasta(input)) +
" trinity transcripts")
cmd = [
'rapmap', 'quasiindex', '-t', input, '-i',
os.path.join(tmpdir, 'rapmap_index')
]
lib.runSubprocess4(cmd, '.', lib.log)
#now launch the subprocess commands in order
lib.log.info("Aligning reads to trinity transcripts with RapMap")
rapmapcmd = [
'rapmap', 'quasimap', '-t',
str(args.cpus), '-i',
os.path.join(tmpdir, 'rapmap_index'), '-1', readTuple[0], '-2',
readTuple[1]
]
cmd = [
os.path.join(parentdir, 'util', 'sam2bam.sh'),
" ".join(rapmapcmd),
str(bamthreads), bowtie2bam
]
lib.runSubprocess(cmd, '.', lib.log)
#now run Trinity examine strandeness tool
lib.log.info("Examining strand specificity")
cmd = [
os.path.join(TRINITY, 'util', 'misc', 'examine_strand_specificity.pl'),
bowtie2bam,
os.path.join(tmpdir, 'strand_specific')
]
lib.runSubprocess(cmd, '.', lib.log)
#parse output dat file and get list of transcripts to remove
removeList = []
with open(os.path.join(tmpdir, 'strand_specific.dat'), 'rU') as infile:
for line in infile:
line = line.replace('\n', '')
if line.startswith('#'):
continue
cols = line.split('\t')
if args.stranded == 'RF': #then we want to keep negative ratios in cols[4]
if not cols[4].startswith('-'):
removeList.append(cols[0])
elif args.stranded == 'FR': #keep + values
if cols[4].startswith('-'):
removeList.append(cols[0])
#now parse the input fasta file removing records in list
with open(output, 'w') as outfile:
with open(input, 'rU') as infile:
for record in SeqIO.parse(infile, 'fasta'):
if not record.id in removeList:
outfile.write(">%s\n%s\n" %
(record.description, str(record.seq)))
lib.log.info("Removing %i antisense transcripts" % (len(removeList)))
def runTrinityGG(genome, readTuple, output):
'''
function will run genome guided Trinity. First step will be to run hisat2 to align reads
to the genome, then pass that BAM file to Trinity to generate assemblies
'''
#build hisat2 index, using exons and splice sites
lib.log.info("Starting Trinity genome guided")
lib.log.info("Building Hisat2 genome index")
cmd = ['hisat2-build', genome, os.path.join(tmpdir, 'hisat2.genome')]
lib.runSubprocess4(cmd, '.', lib.log)
#align reads using hisat2
lib.log.info("Aligning reads to genome using Hisat2")
hisat2bam = os.path.join(tmpdir, 'hisat2.coordSorted.bam')
#use bash wrapper for samtools piping for SAM -> BAM -> sortedBAM
bamthreads = (
args.cpus +
2 // 2) // 2 #use half number of threads for bam compression threads
if args.stranded != 'no' and not readTuple[2]:
hisat2cmd = [
'hisat2', '-p',
str(args.cpus), '--max-intronlen',
str(args.max_intronlen), '--dta', '-x',
os.path.join(tmpdir, 'hisat2.genome'), '--rna-strandness',
args.stranded
]
else:
hisat2cmd = [
'hisat2', '-p',
str(args.cpus), '--max-intronlen',
str(args.max_intronlen), '--dta', '-x',
os.path.join(tmpdir, 'hisat2.genome')
]
if readTuple[0] and readTuple[1]:
hisat2cmd = hisat2cmd + ['-1', readTuple[0], '-2', readTuple[1]]
if readTuple[2]:
hisat2cmd = hisat2cmd + ['-U', readTuple[2]]
cmd = [
os.path.join(parentdir, 'util', 'sam2bam.sh'), " ".join(hisat2cmd),
str(bamthreads), hisat2bam
]
lib.runSubprocess(cmd, '.', lib.log)
#now launch Trinity genome guided
TrinityLog = os.path.join(tmpdir, 'Trinity-gg.log')
lib.log.info("Running genome-guided Trinity, logfile: %s" % TrinityLog)
lib.log.info(
"Clustering of reads from BAM and preparing assembly commands")
jaccard_clip = []
if args.jaccard_clip:
jaccard_clip = ['--jaccard_clip']
if args.stranded != 'no' and not readTuple[2]:
cmd = [
'Trinity', '--SS_lib_type', args.stranded,
'--no_distributed_trinity_exec', '--genome_guided_bam', hisat2bam,
'--genome_guided_max_intron',
str(args.max_intronlen), '--CPU',
str(args.cpus), '--max_memory', args.memory, '--output',
os.path.join(tmpdir, 'trinity_gg')
]
else:
cmd = [
'Trinity', '--no_distributed_trinity_exec', '--genome_guided_bam',
hisat2bam, '--genome_guided_max_intron',
str(args.max_intronlen), '--CPU',
str(args.cpus), '--max_memory', args.memory, '--output',
os.path.join(tmpdir, 'trinity_gg')
]
cmd = cmd + jaccard_clip
lib.runSubprocess2(cmd, '.', lib.log, TrinityLog)
commands = os.path.join(tmpdir, 'trinity_gg', 'trinity_GG.cmds')
#this will create all the Trinity commands, will now run these in parallel using multiprocessing in Python (seems to be much faster than Parafly on my system)
file_list = []
with open(commands, 'rU') as cmdFile:
for line in cmdFile:
line = line.replace('\n', '')
line = line.replace(
'--no_distributed_trinity_exec',
'') #don't think this should be appended to every command....
line = line.replace('"', '') #don't need these double quotes
file_list.append(line)
lib.log.info("Assembling " + "{0:,}".format(len(file_list)) +
" Trinity clusters using %i CPUs" % (args.cpus - 1))
lib.runMultiProgress(safe_run, file_list, args.cpus - 1)
#collected output files and clean
outputfiles = os.path.join(tmpdir, 'trinity_gg',
'trinity_output_files.txt')
with open(outputfiles, 'w') as fileout:
for filename in find_files(os.path.join(tmpdir, 'trinity_gg'),
'*inity.fasta'):
fileout.write('%s\n' % filename)
#now grab them all using Trinity script
cmd = [
os.path.join(TRINITY, 'util', 'support_scripts',
'GG_partitioned_trinity_aggregator.pl'), 'Trinity_GG'
]
lib.runSubprocess5(cmd, '.', lib.log, outputfiles, output)