예제 #1
0
def test_hisat2():
    #test hisat build and hisat mapping
    hs=mapping.Hisat2(index=os.path.join(testVars.testDir,"hisatindex"),genome=testVars.genome)
    assert hs.check_index()==True, "Failed hisat buildindex"
    #perform alignment without sraobject
    kwargs={"-1":testVars.fq1,"-2":testVars.fq2,"-S":testVars.testDir+"/hisatTest.sam","--dta-cufflinks":"","-p":"4"}
    st=hs.run(**kwargs)
    assert st==True, "Failed to run hisat"
예제 #2
0
def test_hisat2():
    #test hisat build and hisat mapping
    hsOpts = {"--dta-cufflinks": "", "-p": "10"}
    hs = mapping.Hisat2(hisat2_index="", **hsOpts)
    assert hs.check_index() == False, "Failed hisat check_index"
    #build index
    st = hs.build_index(testVars.testDir, "hisatindex", testVars.genome)
    assert st == True, "Failed to build hisat2 index"
    #perform alignment without sraobject
    hsMapOpts = {
        "-1": testVars.fq1,
        "-2": testVars.fq2,
        "-S": testVars.testDir + "/hisatTest.sam"
    }
    st = hs.run_hisat2(**hsMapOpts)
    assert st == True, "Failed to run hisat"
예제 #3
0
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"
예제 #4
0
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)
hisat2_buildArgs = {"-p": "16", "-a": "", "-q": ""}

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)
예제 #5
0
#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)

#sra ob
sraOb = sra.SRA(srr, workingDir)
st = sraOb.fastq_exists()
assert st == True, "fasterq-dump failed"
예제 #6
0
#run bbmap
#bd=qc.BBmap()
#sraOb.performQC(bd)

#run bowtie
#bob=mapping.Bowtie2(btIndex)
#unMappedReads=bob.runBowTie2(sraOb)

#update fastq as
#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)