def test_bbduk():
bd = qc.BBmap()
bdOpts = {
"in": fq1,
"in2": fq2,
"out": testVars.testDir + "/bdo1.fq",
"out2": testVars.testDir + "/bdo2.fq"
}
st = bd.run_bbduk(**bdOpts)
assert st == True, "BBDUK failed"
def test_bbsplit():
bs = qc.BBmap()
#build index
bsOpts = {"ref_x": rRNAfasta, "path": testVars.testDir}
st = bs.run_bbsplit(**bsOpts)
assert st == True, "BBSplit index failes"
#run split
bsOpts = {
"in1": fq1,
"in2": fq2,
"outu1": testVars.testDir + "/bso1.fq",
"outu2": testVars.testDir + "/bso2.fq",
"path": testVars.testDir
}
st == bs.run_bbsplit(**bsOpts)
assert st == True, "BBSplit failed"
def test_pipeline1():
sraOb = sra.SRA(srr, workingDir)
st = sraOb.download_sra()
assert st == True, "SRA download failed"
st = sraOb.run_fasterqdump(delete_sra=False,
**{
"-e": "8",
"-f": "",
"-t": workingDir
})
assert st == True, "fqdump failed"
bbdOpts = {
"ktrim": "r",
"k": "23",
"mink": "11",
"qtrim": "'rl'",
"trimq": "10",
"--": ("-Xmx2g", ),
"ref": testVars.bbdukAdapters
}
bbdOb = qc.BBmap(**bbdOpts)
st = sraOb.perform_qc(bbdOb)
assert st == True, "bbduk failed"
tgOpts = {
"--cores": "10",
"-o": testVars.testDir,
"--paired": "",
"--": (fq1, fq2)
}
tg = qc.Trimgalore(**tgOpts)
st = sraOb.perform_qc(tg)
assert st == True, "tg failed"
#runbowtie2
bt = mapping.Bowtie2(bowtie2_index="")
assert bt.check_index() == False, "Failed bowtie2 check_index"
st = bt.build_index(testVars.testDir + "/btIndex", "bowtieIndex",
testVars.genome)
assert st == True, "Failed to build bowtie2 index"
st = bt.perform_alignment(sraOb)
assert os.path.isfile(st) == True, "bowtie failed"
hsOpts = {"--dta-cufflinks": "", "-p": "8"}
hs = mapping.Hisat2(hisat2_index="", **hsOpts)
st = hs.build_index(testVars.testDir, "hisatindex", testVars.genome)
assert st == True, "Failed to build hisat2 index"
#perform alignment with sraobject
st = hs.perform_alignment(sraOb)
assert os.path.isfile(st) == True, "hisat failed"
hisatSam = st
samOb = tools.Samtools(**{"-@": "8"})
bam = samOb.sam_sorted_bam(hisatSam, delete_sam=False, delete_bam=False)
assert os.path.isfile(bam) == True, "sam to bam failed"
stie = assembly.Stringtie(reference_gtf=testVars.gtf)
result = stie.perform_assembly(bam, out_dir=testVars.testDir)
assert pu.check_files_exist(result) == True, "Failed stringtie"
tr = assembly.Trinity()
tr_out = tr.perform_assembly(sraOb, verbose=True)
assert pu.check_files_exist(tr_out) == True, "Failed stringtie"
kl = quant.Kallisto(kallisto_index="")
assert kl.check_index() == False, "Failed kallisto check_index"
st = kl.build_index(index_path=testVars.testDir + "/kallistoIndex",
index_name="kalIndex",
fasta=testVars.cdna)
assert st == True, "Failed to build kallisto index"
st = kl.perform_quant(sraOb)
assert os.path.isdir(st) == True, "Failed to run kallisto"
sl = quant.Salmon(salmon_index="")
assert sl.check_index() == False, "Failed salmon check_index"
st = sl.build_index(index_path=testVars.testDir + "/salmonIndex",
index_name="salIndex",
fasta=testVars.cdna)
assert st == True, "Failed to build salmon index"
st = sl.perform_quant(sraOb)
assert os.path.isdir(st) == True, "Failed to run salmon"
print("Following runs downloaded:")
for ob in sraObjects:
print(ob.srr_accession)
pathToAdapters = "adapters2.fa"
bbdOpts = {
"ktrim": "r",
"k": "23",
"mink": "11",
"qtrim": "'rl'",
"trimq": "10",
"--": ("-Xmx2g", ),
"ref": pathToAdapters
}
bbdOb = qc.BBmap(**bbdOpts)
for ob in sraObjects:
ob.perform_qc(bbdOb)
for ob in sraObjects:
print("SRR Accession: {}, fastq files: {}. {}".format(
ob.srr_accession, ob.localfastq1Path, ob.localfastq2Path))
if ob.fastqFilesExistsLocally():
print("Both files exist!!")
else:
print("Error")
raise Exception("Fastq files not found")
hsOpts = {"--dta-cufflinks": "", "-p": "16"}
hs = mapping.Hisat2(hisat2_index="", **hsOpts)
#new tests
# test samtools
sam=testDir+"/test_files/athaliana/mapping/hisat2.sam"
sm=tools.Samtools(threads=5)
bam1=sm.sam_to_bam(sam,out_suffix="test2",threads=3, delete_sam=False,verbose=True,quiet=False,logs=True,objectid="NA",**{"-@":"4"})
print(bam1)
bam2=sm.sort_bam(bam1,out_suffix="test2",threads=2,delete_bam=False,verbose=True,quiet=False,logs=True,objectid="NA")
print(bam2)
#bam=sm.sam_sorted_bam(sam,delete_sam=False,delete_bam=False)
txd=tools.Transdecoder()
infa="/Users/usingh/work/urmi/tests/txd/test.fa"
outdir=txd.run_transdecoder_longorfs(infa,out_dir="/Users/usingh/work/urmi/tests/txd/mtout1")
print(outdir)
poutdir="/Users/usingh/work/urmi/tests/txd/mypredout"
predout=txd.run_transdecoder_predict(infa,longorfs_dir=outdir,out_dir=poutdir)
print(predout)
newSRA=sra.SRA('SRR5507343',testDir)
newSRA.download_fastq()
#run trimgalore
tg=qc.Trimgalore(threads=4) #specify to use 8 cores
bd=qc.BBmap(threads=4,max_memory=1)
newSRA.perform_qc(bd)
#newSRA.perform_qc(tg)
f = open('pyrpipe_conf.yaml', 'w')
f.write('dry: true\n')
f.write('threads: 1\n')
f.write('safe: true\n')
f.close()
#create objects
bbdOpts = {
"ktrim": "r",
"k": "23",
"mink": "11",
"qtrim": "'rl'",
"trimq": "10",
"ref": testVars.bbdukAdapters
}
bbdOb = qc.BBmap(None, **bbdOpts)
tg = qc.Trimgalore()
bt = mapping.Bowtie2(index=testVars.testDir + "/btIndex",
genome=testVars.genome)
hsOpts = {"--dta-cufflinks": "", "-p": "8"}
hs = mapping.Hisat2(index=testVars.testDir + "/hisatindex",
genome=testVars.genome,
**hsOpts)
star = mapping.Star(index=os.path.join(testVars.testDir, "starIndex"),
genome=testVars.genome)
samOb = tools.Samtools()
stie = assembly.Stringtie()
kl = quant.Kallisto(index=testVars.testDir + "/kallistoIndex/kalIndex",
transcriptome=testVars.cdna)
sl = quant.Salmon(index=testVars.testDir + "/salmonIndex/salIndex",
transcriptome=testVars.cdna_big)