def perform_alignment(self,
sra_object,
out_suffix="_bowtie2",
out_dir="",
objectid="NA"):
"""Function to perform alignment using sra_object.
Parameters
----------
sra_object SRA object
An object of type SRA. The path to fastq files will be obtained from this object.
out_suffix: string
Suffix for the output sam file
out_dir: string
Directory to save the results. Default value is sra_object.directory
objectid: str
Provide an id to attach with this command e.g. the SRR accession. This is useful for debugging, benchmarking and reports.
:return: Returns the sorted bam file path after converting sam to bam and sorting it
:rtype: string
"""
if not out_dir:
out_dir = sra_object.directory
else:
if not pu.check_paths_exist(out_dir):
pu.mkdir(out_dir)
#create path to output sam file
outSamFile = os.path.join(
out_dir, sra_object.srr_accession + out_suffix + ".sam")
#outBamFile=os.path.join(out_dir,sra_object.srr_accession+out_suffix+"_sorted.bam")
#find layout and fq file paths
if sra_object.layout == 'PAIRED':
internal_kwargs = {
"-1": sra_object.fastq_path,
"-2": sra_object.fastq2_path,
"-S": outSamFile
}
else:
internal_kwargs = {"-U": sra_object.fastq_path, "-S": outSamFile}
status = self.run(None,
objectid=sra_object.srr_accession,
target=outSamFile,
**internal_kwargs)
if status:
if not pu.check_files_exist(outSamFile) and not _dryrun:
return ""
#convert to bam before returning; returns outBamFile
return tools.Samtools().sam_sorted_bam(outSamFile)
return ""
def test_samtools():
#test sam to sorted bam
sm=tools.Samtools()
sortedBam=sm.sam_sorted_bam(testVars.hisatSam,out_dir=testVars.testDir)
print("check:"+sortedBam)
st=pu.check_files_exist(sortedBam)
assert st==True, "Failed to convert sam to sorted bam"
#test merge
mergedBam=sm.merge_bam(testVars.hisatSortedBam,testVars.starSortedBam,out_dir=testVars.testDir,**{"-f":""})
st=pu.check_files_exist(mergedBam)
assert st==True, "Failed to merge bam"
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"
if hs.build_index(workingDir + "/maizeIndex", "maizeInd", GENOME,
**hisat2_buildArgs):
print("Indexing done.")
if hs.check_index():
print("Index {} exists".format(hs.hisat2_index))
samList = []
for ob in sraObjects:
print("Processing {}...".format(ob.srr_accession))
thisSam = hs.perform_alignment(ob, **{"-p": "16"})
if thisSam:
samList.append(thisSam)
print("Alignment done!! Sam files:" + ",".join(samList))
samOb = tools.Samtools(**{"-@": "16"})
bamList = []
i = 0
for sam in samList:
print("Processing:" + sam)
thisBam = samOb.sam_sorted_bam(sam,
delete_sam=True,
delete_bam=True,
objectid=sraObjects[i].srr_accession)
i += 1
if thisBam:
bamList.append(thisBam)
print("Sorted bam files:" + ",".join(bamList))
st = assembly.Stringtie()
gtfList = []
dm.build_index(infa,"diamondDB",out_dir="/Users/usingh/work/urmi/tests/mikado/dout",threads=8)
listFile="/Users/usingh/work/urmi/tests/mikado/list.txt"
genome="/Users/usingh/work/urmi/tests/mikado/chr5.fas"
mode="permissive"
scoring="plants.yaml"
junctions="/Users/usingh/work/urmi/tests/mikado/junctions.bed"
mk=tools.Mikado()
mk.runMikadoFull(listFile,genome,mode,scoring,junctions,"mkconf",infa,dm,8,out_dir="/Users/usingh/work/urmi/tests/mikado/pyrout",verbose=False)
"""
#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)
"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)
#sra ob
sraOb = sra.SRA(srr, workingDir)
st = sraOb.fastq_exists()
assert st == True, "fasterq-dump failed"
def test_pipeline1():
st = sraOb.trim(bbdOb).align(hs).assemble(stie).quant(kl)
assert st != None, "pipeline 1 failed"
#sraOb.localfastqPath=unMappedReads
#build hisat index
hsOpts={"--dta-cufflinks":"","-p":"12","--mp": "1,1", "--no-spliced-alignment":"", "--rdg": "10000,10000", "--rfg": "10000,10000"}
hs=mapping.Hisat2(hisat2_index="/home/usingh/work/urmi/hoap/test/yeastInd2/index22",**hsOpts)
#hsbArgs={"-p":"8","-a":"","-q":""}
#if hs.buildHisat2Index("/home/usingh/work/urmi/hoap/test/yeastInd2","index22","/home/usingh/work/urmi/hoap/test/hisatYeast/S288C_reference_genome_R64-2-1_20150113/S288C_reference_sequence_R64-2-1_20150113.fsa",**hsbArgs):
# print("Success")
#run hisat
sam=hs.perform_alignment(sraOb,**{"--dta-cufflinks":"","-p":"8"})
#get sorted bam
samOb=tools.Samtools(**{"-@":"8"})
bam=samOb.sam_sorted_bam(sam,delete_sam=True,delete_bam=True)
#bt2=mapping.Bowtie2("/home/usingh/work/urmi/hoap/test/bowtieIndex/rRNAindex")
#bt2.performAlignment(sraOb)
#run stringtie
st=assembly.Stringtie()
g1=st.perform_assembly(bam,objectid="myob")
#gtfs=(g1,)
#test stmerge
#merged=st.performStringtieMerge(g1,g1,outFileSuffix="_stOUT",overwrite=True)
#if not merged:
