cig.sseg != (result[4], result[5]) or \
cig.swatscor != result[6]:
exit("Unexpected result for read '%s'" % cig.qnam)
infil.close()
def prep_fasta(filnam):
from testdata import openFile
infil = openFile(filnam, 'w')
for seq in READSEQS:
for i in range(len(seq)):
infil.write("%c" % seq[i])
infil.close()
if __name__ == '__main__':
from testdata import DataFiles
df = DataFiles()
#refnam = df.unpack(REFSEQ)
#refnam = df.addTMP(REFSEQ)
refnam = df.joinData(REFSEQ)
indexnam = df.addIndex(TMPFIL_PREFIX)
readfilnam = df.addTMP(TMPFIL_PREFIX + ".fq")
oufilnam = df.addTMP(TMPFIL_PREFIX + ".cig")
prep_fasta(readfilnam)
smalt_index(df,indexnam, refnam, KMER, NSKIP)
smalt_map(df,oufilnam, indexnam, readfilnam)
compare_result(oufilnam)
df.cleanup()
def smalt_map(df, oufilnam, indexnam, readfil, typ="fastq", matefil=""):
from sys import exit
from subprocess import call
tup = (PROGNAM, 'map', '-r', '-1', '-F', typ, '-o', oufilnam, indexnam,
readfil, matefil)
df.call(tup, "when mapping")
if __name__ == '__main__':
from testdata import DataFiles, areFilesIdentical
df = DataFiles()
refnam = df.joinData(REF_FASTA_NAME)
readnamA = df.joinData(READ_PREFIX + "_nonam_1.fq.gz")
readnamB = df.joinData(READ_PREFIX + "_nonam_2.fq.gz")
bamnam = df.joinData(READ_PREFIX + ".bam")
samnam = df.unpack(READ_PREFIX + ".sam")
indexnam = df.addIndex(TMPFIL_PREFIX)
oufilnam_fastq = df.addTMP(TMPFIL_PREFIX + "fastq.sam")
oufilnam_bam = df.addTMP(TMPFIL_PREFIX + "bam.sam")
oufilnam_sam = df.addTMP(TMPFIL_PREFIX + "sam.sam")
oufilnam2_sam = df.addTMP(TMPFIL_PREFIX + "sam2.sam")
smalt_index(df, indexnam, refnam, KMER, NSKIP)
smalt_map(df, oufilnam_fastq, indexnam, readnamA, "fastq", readnamB)
smalt_map(df, oufilnam_bam, indexnam, bamnam, "bam")
if cmp(cig1,cig2) and cig1.mapq > 5 and cig2.mapq > 5:
exit("mappings don't match for read '%s'" % \
cig1.qnam)
infil2.close()
infil1.close()
if ctr1 != ctr1:
exit("Expected the same number of mates, got %i (A) and %i (B)" % \
ctr1, ctr2)
if ctr1 != 20000:
exit("Expected 20,000 reads, got %i." % ctr1)
if __name__ == '__main__':
from testdata import DataFiles
df = DataFiles()
refnam = df.joinData(REF_FASTA_NAME)
readnamA = df.joinData(READ_PREFIX + "_1.fq.gz")
readnamB = df.joinData(READ_PREFIX + "_2.fq.gz")
indexnam = df.addIndex(TMPFIL_PREFIX)
samplenam1 = df.addTMP(TMPFIL_PREFIX + ".1.txt")
samplenam2 = df.addTMP(TMPFIL_PREFIX + ".2.txt")
oufilnam1 = df.addTMP(TMPFIL_PREFIX + ".1.cig")
oufilnam2 = df.addTMP(TMPFIL_PREFIX + ".2.cig")
oufilnam3 = df.addTMP(TMPFIL_PREFIX + ".3.cig")
smalt_check(df,readnamA, readnamB)
smalt_index(df,indexnam, refnam, KMER, NSKIP)
okflgs[expected_tup.index(observed_tup)] = True
linctr = linctr + 1
for i in range(n_tup):
if not okflgs[i]:
print "ERROR: could not find tuple: ", expected_tup[i]
allok = False
if not allok:
exit("ERROR when checking. Test not passed.")
if __name__ == '__main__':
from testdata import DataFiles
df = DataFiles()
refnam = df.joinData(REF_FASTA_NAME)
indexnam = df.addIndex(TMPFIL_PREFIX)
readfilA = df.addTMP(TMPFIL_PREFIX + "_1.fa")
readfilB = df.addTMP(TMPFIL_PREFIX + "_2.fa")
oufilnam = df.addTMP(TMPFIL_PREFIX + ".cig")
makeFastqPair(readfilA, readfilB)
smalt_index(df, indexnam, refnam, KMER, NSKIP)
smalt_map(df, oufilnam, indexnam, readfilA, readfilB, ['-p'])
checkOutput(oufilnam, MAPPED_CIGAR)
df.cleanup()
exit(0)
if cigA2 != cigB2:
if is_verbose:
print "Not matching:\n%s\n%s" % (cigA2.lin, cigB2.lin)
if cigA2.mapq > MAPQ_THRESH and cigB2.mapq > MAPQ_THRESH:
exit("Discrepancy:\n%s\n%s" % (cigA2.lin, cigB2.lin))
ctr = ctr + 1
if not isOK and isEOF:
isOK = True
return isOK, ctr
if __name__ == '__main__':
from testdata import DataFiles, areFilesIdentical
df = DataFiles()
refnam = df.joinData(DATA[0])
readfilnamA = df.joinData(DATA[1])
readfilnamB = df.joinData(DATA[2])
n_pairs_expected = DATA[3]
indexnam = df.addIndex(TMPFIL_PREFIX)
oufilnam_ref = df.addTMP(TMPFIL_PREFIX + ".n0.cig")
oufilnam_thread = df.addTMP(TMPFIL_PREFIX + ".n%i.cig" % NTHREADS)
smalt_index(df, indexnam, refnam, KMER, NSKIP);
smalt_map(df, oufilnam_ref, indexnam, readfilnamA, readfilnamB);
smalt_map(df, oufilnam_thread, indexnam, readfilnamA, readfilnamB,
["-n", "%i" % NTHREADS, "-O"]);
nmtag = sam.tags["NM"]
if nmtag:
tagstr = "NM:%s:%s" % nmtag
if tagstr != rdat[2]:
df.exitErr("Unexpected tag '%s' (expected '%s')" % (tagstr, rdat[2]))
linctr = linctr + 1
if linctr < len(readdat):
df.exitErr("CIGAR strings incomplete");
infil.close()
if __name__ == '__main__':
from testdata import DataFiles
df = DataFiles()
reffilnam = df.addTMP(TMPFIL_PREFIX + "ref.fa")
writeFASTAref(reffilnam)
indexnam = df.addIndex(TMPFIL_PREFIX)
smalt_index(df, indexnam, reffilnam, KMER, NSKIP)
readfilnam = df.addTMP(TMPFIL_PREFIX + "read.fa")
mate1filnam = df.addTMP(TMPFIL_PREFIX_PAIRED + "mate1.fa")
mate2filnam = df.addTMP(TMPFIL_PREFIX_PAIRED + "mate2.fa")
writeFASTAreads(READSEQ, readfilnam)
writeFASTAreadPairs(READSEQ_PAIR, mate1filnam, mate2filnam)
samoufilnam = df.addTMP(TMPFIL_PREFIX + "out.sam")
def smalt_map(df, oufilnam, indexnam, readfil, matefil, typ="fastq", flags=[]):
from sys import exit
from subprocess import call
tup = [PROGNAM, 'map']
if len(flags) > 0:
tup.extend(flags)
tup.extend(['-f', typ, '-o', oufilnam, indexnam, readfil, matefil])
df.call(tup, "when mapping")
if __name__ == '__main__':
from testdata import DataFiles
df = DataFiles()
refnam = df.joinData(FNAM_REF)
readnamA = df.joinData(FNAM_READ1)
readnamB = df.joinData(FNAM_READ2)
indexnam = df.addIndex(TMPFIL_PREFIX)
oufilnam = df.addTMP(TMPFIL_PREFIX + ".sam")
smalt_index(df, indexnam, refnam, KMER, NSKIP)
smalt_map(df, oufilnam, indexnam, readnamA, readnamB, "sam", ["-x"])
#print "Test ok."
df.cleanup()
exit()
tagstr = "NM:%s:%s" % nmtag
if tagstr != rdat[2]:
df.exitErr("Unexpected tag '%s' (expected '%s')" %
(tagstr, rdat[2]))
linctr = linctr + 1
if linctr < len(readdat):
df.exitErr("CIGAR strings incomplete")
infil.close()
if __name__ == '__main__':
from testdata import DataFiles
df = DataFiles()
reffilnam = df.addTMP(TMPFIL_PREFIX + "ref.fa")
writeFASTAref(reffilnam)
indexnam = df.addIndex(TMPFIL_PREFIX)
smalt_index(df, indexnam, reffilnam, KMER, NSKIP)
readfilnam = df.addTMP(TMPFIL_PREFIX + "read.fa")
mate1filnam = df.addTMP(TMPFIL_PREFIX_PAIRED + "mate1.fa")
mate2filnam = df.addTMP(TMPFIL_PREFIX_PAIRED + "mate2.fa")
writeFASTAreads(READSEQ, readfilnam)
writeFASTAreadPairs(READSEQ_PAIR, mate1filnam, mate2filnam)
samoufilnam = df.addTMP(TMPFIL_PREFIX + "out.sam")
bamoufilnam = df.addTMP(TMPFIL_PREFIX + "out.bam")
exit("Discrepancy:\n%s\n%s" % (cigA1.lin, cigB1.lin))
if cigA2 != cigB2:
if is_verbose:
print "Not matching:\n%s\n%s" % (cigA2.lin, cigB2.lin)
if cigA2.mapq > MAPQ_THRESH and cigB2.mapq > MAPQ_THRESH:
exit("Discrepancy:\n%s\n%s" % (cigA2.lin, cigB2.lin))
ctr = ctr + 1
if not isOK and isEOF:
isOK = True
return isOK, ctr
if __name__ == '__main__':
from testdata import DataFiles, areFilesIdentical
df = DataFiles()
refnam = df.joinData(DATA[0])
readfilnamA = df.joinData(DATA[1])
readfilnamB = df.joinData(DATA[2])
n_pairs_expected = DATA[3]
indexnam = df.addIndex(TMPFIL_PREFIX)
oufilnam_ref = df.addTMP(TMPFIL_PREFIX + ".n0.cig")
oufilnam_thread = df.addTMP(TMPFIL_PREFIX + ".n%i.cig" % NTHREADS)
smalt_index(df, indexnam, refnam, KMER, NSKIP)
smalt_map(df, oufilnam_ref, indexnam, readfilnamA, readfilnamB)
smalt_map(df, oufilnam_thread, indexnam, readfilnamA, readfilnamB,
["-n", "%i" % NTHREADS, "-O"])
from subprocess import call
tup = [PROGNAM, 'map']
if len(flags) > 0:
tup.extend(flags)
tup.extend([
'-f', typ,
'-o', oufilnam,
indexnam,
readfil, matefil])
df.call(tup, "when mapping")
if __name__ == '__main__':
from testdata import DataFiles
df = DataFiles()
refnam = df.joinData(FNAM_REF)
readnamA = df.joinData(FNAM_READ1)
readnamB = df.joinData(FNAM_READ2)
indexnam = df.addIndex(TMPFIL_PREFIX)
oufilnam = df.addTMP(TMPFIL_PREFIX + ".sam")
smalt_index(df,indexnam, refnam, KMER, NSKIP)
smalt_map(df,oufilnam, indexnam, readnamA, readnamB, "sam", ["-x"])
#print "Test ok."
df.cleanup()
exit()
exit("Unexpected result for read '%s'" % cig.qnam)
infil.close()
def prep_fasta(filnam):
from testdata import openFile
infil = openFile(filnam, 'w')
for seq in READSEQS:
for i in range(len(seq)):
infil.write("%c" % seq[i])
infil.close()
if __name__ == '__main__':
from testdata import DataFiles
df = DataFiles()
#refnam = df.unpack(REFSEQ)
#refnam = df.addTMP(REFSEQ)
refnam = df.joinData(REFSEQ)
indexnam = df.addIndex(TMPFIL_PREFIX)
readfilnam = df.addTMP(TMPFIL_PREFIX + ".fq")
oufilnam = df.addTMP(TMPFIL_PREFIX + ".cig")
prep_fasta(readfilnam)
smalt_index(df, indexnam, refnam, KMER, NSKIP)
smalt_map(df, oufilnam, indexnam, readfilnam)
compare_result(oufilnam)
df.cleanup()
from sys import exit
from subprocess import call
tup = (PROGNAM, 'map',
'-r', '-1',
'-F', typ,
'-o', oufilnam,
indexnam,
readfil, matefil)
df.call(tup, "when mapping")
if __name__ == '__main__':
from testdata import DataFiles, areFilesIdentical
df = DataFiles()
refnam = df.joinData(REF_FASTA_NAME)
readnamA = df.joinData(READ_PREFIX + "_nonam_1.fq.gz")
readnamB = df.joinData(READ_PREFIX + "_nonam_2.fq.gz")
bamnam = df.joinData(READ_PREFIX + ".bam")
samnam = df.unpack(READ_PREFIX + ".sam")
indexnam = df.addIndex(TMPFIL_PREFIX)
oufilnam_fastq = df.addTMP(TMPFIL_PREFIX + "fastq.sam")
oufilnam_bam = df.addTMP(TMPFIL_PREFIX + "bam.sam")
oufilnam_sam = df.addTMP(TMPFIL_PREFIX + "sam.sam")
oufilnam2_sam = df.addTMP(TMPFIL_PREFIX + "sam2.sam")
smalt_index(df,indexnam, refnam, KMER, NSKIP)
smalt_map(df,oufilnam_fastq, indexnam, readnamA, "fastq", readnamB)
smalt_map(df,oufilnam_bam, indexnam, bamnam, "bam")
def process(df,
indexnam,
oufilnam,
readnamA,
readnamB,
option_label_pairs,
mateno_check=True):
for (option, label_pairs) in option_label_pairs:
smalt_map(df, oufilnam, indexnam, readnamA, readnamB, option)
checkLabels(oufilnam, label_pairs, mateno_check)
if __name__ == '__main__':
from testdata import DataFiles
df = DataFiles()
refnam = df.joinData(REF_FASTA_NAME)
readnamA = df.joinData(READ_PREFIX + "_1.fq")
readnamB = df.joinData(READ_PREFIX + "_2.fq")
indexnam = df.addIndex(TMPFIL_PREFIX)
oufilnam = df.addTMP(TMPFIL_PREFIX + ".cig")
readnamRCA = df.addTMP(TMPFIL_PREFIX + "rc_1.fq")
readnamRCB = df.addTMP(TMPFIL_PREFIX + "rc_2.fq")
smalt_index(df, indexnam, refnam, KMER, NSKIP)
process(df, indexnam, oufilnam, readnamA, readnamB,
OPTION_LABEL_PAIRS_ORIG)
#print "reverse complement 2nd read ..."
if sam.cigar != res[2]:
df.exitErr("ERROR: wrong CIGAR string '%s' (target:'%s')" % (sam.cigar, res[2]))
(typ, fld) = sam.tags["NM"]
edist = int(fld)
if edist != res[3]:
df.exitErr("ERROR: wrong edit distance %i (target: %i)" % (edist, res[3]))
infil.close()
return
if __name__ == '__main__':
from testdata import DataFiles
df = DataFiles()
indexnam = df.addIndex(TMPFIL_PREFIX)
reffilnam = makeFASTAfile(df, "REF", REFSEQ)
readfilnam = makeFASTAfile(df, "READ", READS)
rc_readfilnam = df.addTMP(TMPFIL_PREFIX + "RC.fa")
samfilnam = df.addTMP(TMPFIL_PREFIX + ".sam")
rc_samfilnam = df.addTMP(TMPFIL_PREFIX + "RC.sam")
smalt_index(df, indexnam, reffilnam, KMER, NSKIP)
smalt_map(df, samfilnam, indexnam, readfilnam)
checkSAM(df, samfilnam, RESULTS)
reverseComplement(df, readfilnam, rc_readfilnam)
smalt_map(df, rc_samfilnam, indexnam, rc_readfilnam)
checkSAM(df, samfilnam, RESULTS)
['-f', 'cigar',
'-o', oufilnam,
indexnam,
readfil, matefil]
)
df.call(tup, "when mapping")
def process(df, indexnam, oufilnam, readnamA, readnamB, option_label_pairs, mateno_check=True):
for (option, label_pairs) in option_label_pairs:
smalt_map(df,oufilnam, indexnam, readnamA, readnamB, option)
checkLabels(oufilnam, label_pairs, mateno_check)
if __name__ == '__main__':
from testdata import DataFiles
df = DataFiles()
refnam = df.joinData(REF_FASTA_NAME)
readnamA = df.joinData(READ_PREFIX + "_1.fq")
readnamB = df.joinData(READ_PREFIX + "_2.fq")
indexnam = df.addIndex(TMPFIL_PREFIX)
oufilnam = df.addTMP(TMPFIL_PREFIX + ".cig")
readnamRCA = df.addTMP(TMPFIL_PREFIX + "rc_1.fq")
readnamRCB = df.addTMP(TMPFIL_PREFIX + "rc_2.fq")
smalt_index(df,indexnam, refnam, KMER, NSKIP)
process(df,indexnam, oufilnam, readnamA, readnamB, OPTION_LABEL_PAIRS_ORIG)
#print "reverse complement 2nd read ..."
reverseComplement(df,readnamB, readnamRCB)