def test_conv_align2GRmat_bl8_2(self):
currentdir = os.path.dirname(os.path.abspath(__file__))
ali_file = currentdir + os.sep + 'data' + os.sep + 'ex2.bl8'
aliFormat = 2
(U, NU, genomes, reads) = PathoID.conv_align2GRmat(ali_file,self.scoreCutoff,aliFormat)
print U, NU, genomes, reads
score = 7036818.21 #Expected score from the alignment file
expectedU = {}
self.assertEquals(expectedU, U, "Failed bl8 Example 2 Unique Reads Assertion")
expectedNU = {0: [[0, 1], [score, score], [0.5, 0.5], score],
1: [[0, 1], [score, score], [0.5, 0.5], score],
2: [[2, 1], [score, score], [0.5, 0.5], score],
3: [[2, 1], [score, score], [0.5, 0.5], score],
4: [[2, 0, 1], [score, score, score], [0.3333, 0.3333, 0.3333], score],
5: [[2, 0, 1], [score, score, score], [0.3333, 0.3333, 0.3333], score],
6: [[2, 0, 1], [score, score, score], [0.3333, 0.3333, 0.3333], score]}
self.assertEquals(len(expectedNU), len(NU), "Failed bl8 Example 1 Non-Unique Reads length Assertion")
for read in expectedNU:
self.assertEquals(expectedNU[read][0], NU[read][0],
"Failed bl8 Example 2 Non-Unique Read %d genome mapping Assertion" %read)
for j in range(len(expectedNU[read][1])):
self.assertAlmostEquals(expectedNU[read][1][j], NU[read][1][j], 2,
"Failed bl8 Example 2 Non-Unique Read %d score Assertion" %read)
for j in range(len(expectedNU[read][2])):
self.assertAlmostEquals(NU[read][2][j], expectedNU[read][2][j], 4,
"Failed bl8 Example 2 Non-Unique Read %d proportion Assertion" %read)
self.assertAlmostEquals(expectedNU[read][3], NU[read][3], 2,
"Failed bl8 Example 1 Non-Unique Read %d weight Assertion" %read)
expectedGenomes = ['genome2', 'genome1', 'genome3']
self.assertEquals(expectedGenomes, genomes, "Failed bl8 Example 2 Genomes Assertion")
expectedReads = ['read1_12', 'read2_12', 'read3_13', 'read4_13', 'read5_123', 'read6_123', 'read7_123']
self.assertEquals(expectedReads, reads, "Failed bl8 Example 2 Reads Assertion")
def test_pathoscope_em_4(self):
scaledScore = 2.6881171418161356e+43 #Expected Re-scaled score
U = {2: [0, scaledScore]}
NU = {0: [[0, 1], [scaledScore, scaledScore], [0.5, 0.5], scaledScore],
1: [[1, 0], [scaledScore, scaledScore], [0.5, 0.5], scaledScore],
3: [[2, 3], [scaledScore, scaledScore], [0.5, 0.5], scaledScore],
4: [[2, 1], [scaledScore, scaledScore], [0.5, 0.5], scaledScore]}
### Genome hash
genomes = {0:"genome4", 1:"genome3", 2:"genome1", 3:"genome2"}
(initPi, pi, theta, NU) = PathoID.pathoscope_em(U, NU, genomes,
self.maxIter, self.emEpsilon, self.verbose, self.piPrior, self.thetaPrior)
print initPi, pi, theta, NU
expectedInitPi = [0.4, 0.3, 0.2, 0.1]
for j in range(len(expectedInitPi)):
self.assertAlmostEquals(initPi[j], expectedInitPi[j], 4, "Failed EM Example 4 Initial PI Assertion j=%d" %j)
expectedPi = [0.20, 0.57, 0.23, 0.0]
for j in range(len(expectedPi)):
self.assertAlmostEquals(pi[j], expectedPi[j], 2, "Failed EM Example 4 PI Assertion")
expectedTheta = [0.0, 0.72, 0.28, 0.0]
for j in range(len(expectedTheta)):
self.assertAlmostEquals(theta[j], expectedTheta[j], 2, "Failed EM Example 4 Theta Assertion")
expectedNU = {0: [[0, 1], [scaledScore, scaledScore], [0.0, 1.0], scaledScore],
1: [[1, 0], [scaledScore, scaledScore], [1.0, 0.0], scaledScore],
3: [[2, 3], [scaledScore, scaledScore], [1.0, 0.0], scaledScore],
4: [[2, 1], [scaledScore, scaledScore], [0.14, 0.86], scaledScore]}
for read in expectedNU:
self.assertEquals(NU[read][0], expectedNU[read][0],
"Failed EM Example 4 Non-Unique Read %d genome mapping Assertion" %read)
self.assertEquals(NU[read][1], expectedNU[read][1],
"Failed EM Example 4 Non-Unique Read %d score Assertion" %read)
for j in range(len(expectedNU[read][2])):
self.assertAlmostEquals(NU[read][2][j], expectedNU[read][2][j], 2,
"Failed EM Example 4 Non-Unique Read %d proportion Assertion" %read)
def test_conv_align2GRmat_sam_4(self):
currentdir = os.path.dirname(os.path.abspath(__file__))
ali_file = currentdir + os.sep + 'data' + os.sep + 'ex4.sam'
aliFormat = 1
(U, NU, genomes, reads) = PathoID.conv_align2GRmat(ali_file,self.scoreCutoff,aliFormat)
print U, NU, genomes, reads
scaledScore = 2.6881171418161356e+43 #Expected Re-scaled score
expectedU = {2: [0, scaledScore]}
self.assertEquals(len(expectedU), len(U), "Failed sam Example 4 Unique Reads length Assertion")
for read in expectedU:
self.assertEquals(expectedU[read][0], U[read][0],
"Failed sam Example 4 Unique Read %d genome mapping Assertion" %read)
self.assertAlmostEquals(expectedU[read][1], U[read][1], 2,
"Failed sam Example 4 Unique Read %d score Assertion" %read)
expectedNU = {0: [[0, 1], [scaledScore, scaledScore], [0.5, 0.5], scaledScore],
1: [[1, 0], [scaledScore, scaledScore], [0.5, 0.5], scaledScore],
3: [[2, 3], [scaledScore, scaledScore], [0.5, 0.5], scaledScore],
4: [[2, 1], [scaledScore, scaledScore], [0.5, 0.5], scaledScore]}
self.assertEquals(len(expectedNU), len(NU), "Failed sam Example 4 Non-Unique Reads length Assertion")
for read in expectedNU:
self.assertEquals(expectedNU[read][0], NU[read][0],
"Failed sam Example 4 Non-Unique Read %d genome mapping Assertion" %read)
for j in range(len(expectedNU[read][1])):
self.assertAlmostEquals(expectedNU[read][1][j], NU[read][1][j], 2,
"Failed sam Example 4 Non-Unique Read %d score Assertion" %read)
for j in range(len(expectedNU[read][2])):
self.assertAlmostEquals(NU[read][2][j], expectedNU[read][2][j], 4,
"Failed sam Example 4 Non-Unique Read %d proportion Assertion" %read)
self.assertAlmostEquals(expectedNU[read][3], NU[read][3], 2,
"Failed sam Example 4 Non-Unique Read %d weight Assertion" %read)
expectedGenomes = ['genome4', 'genome3', 'genome1', 'genome2']
self.assertEquals(expectedGenomes, genomes, "Failed sam Example 4 Genomes Assertion")
expectedReads = ['read1_34', 'read2_34', 'read3_4', 'read4_12', 'read5_13']
self.assertEquals(expectedReads, reads, "Failed sam Example 4 Reads Assertion")
def test_conv_align2GRmat_gsam_3(self):
currentdir = os.path.dirname(os.path.abspath(__file__))
ali_file = currentdir + os.sep + 'data' + os.sep + 'ex3.g.sam'
aliFormat = 0
(U, NU, genomes, reads) = PathoID.conv_align2GRmat(ali_file,self.scoreCutoff,aliFormat)
print U, NU, genomes, reads
expectedU = {0: [0, 1.0], 1: [0, 1.0], 2: [0, 1.0], 3: [1, 1.0], 4: [1, 1.0]}
self.assertEquals(len(expectedU), len(U), "Failed gnusam Example 3 Unique Reads length Assertion")
for read in expectedU:
self.assertEquals(expectedU[read][0], U[read][0],
"Failed gnusam Example 3 Unique Read %d genome mapping Assertion" %read)
self.assertAlmostEquals(expectedU[read][1], U[read][1], 2,
"Failed gnusam Example 3 Unique Read %d score Assertion" %read)
expectedNU = {5: [[0, 1, 2], [0.33, 0.33, 0.33], [0.3333, 0.3333, 0.3333], 0.33],
6: [[0, 1, 2], [0.33, 0.33, 0.33], [0.3333, 0.3333, 0.3333], 0.33],
7: [[0, 1, 2], [0.33, 0.33, 0.33], [0.3333, 0.3333, 0.3333], 0.33]}
self.assertEquals(len(expectedNU), len(NU), "Failed gnusam Example 3 Non-Unique Reads length Assertion")
for read in expectedNU:
self.assertEquals(expectedNU[read][0], NU[read][0],
"Failed gnusam Example 3 Non-Unique Read %d genome mapping Assertion" %read)
for j in range(len(expectedNU[read][1])):
self.assertAlmostEquals(expectedNU[read][1][j], NU[read][1][j], 2,
"Failed gnusam Example 3 Non-Unique Read %d score Assertion" %read)
for j in range(len(expectedNU[read][2])):
self.assertAlmostEquals(NU[read][2][j], expectedNU[read][2][j], 4,
"Failed gnusam Example 3 Non-Unique Read %d proportion Assertion" %read)
self.assertAlmostEquals(expectedNU[read][3], NU[read][3], 2,
"Failed gnusam Example 3 Non-Unique Read %d weight Assertion" %read)
expectedGenomes = ['genome1', 'genome2', 'genome3']
self.assertEquals(expectedGenomes, genomes, "Failed gnusam Example 3 Genomes Assertion")
expectedReads = ['read1_1', 'read2_1', 'read3_1', 'read4_3', 'read5_2', 'read6_123', 'read7_123', 'read8_123']
self.assertEquals(expectedReads, reads, "Failed gnusam Example 3 Reads Assertion")
def test_pathoscope_em_2(self):
### 3 unique reads: 2 reads to genome1 and 1 read to genome4
U = {}
### non-unique reads: 3 total reads 1:[[genomes],[qij],[xij]]
NU = {
0: [[0, 3], [0.5, 0.5], [0.5, 0.5], 0.5],
1: [[0, 3], [0.5, 0.5], [0.5, 0.5], 0.5],
2: [[0, 2, 3], [0.4, 0.2, 0.4], [0.33, 0.33, 0.33], 0.4],
3: [[0, 2, 3], [0.4, 0.4, 0.2], [0.33, 0.33, 0.33], 0.4],
4: [[0, 2, 3], [0.4, 0.4, 0.2], [0.33, 0.33, 0.33], 0.4]
}
### Genome hash
genomes = {0: "ecoli", 1: "strep", 2: "anthrax", 3: "plague"}
(initPi, pi, theta,
NU) = PathoID.pathoscope_em(U, NU, genomes, self.maxIter,
self.emEpsilon, self.verbose,
self.piPrior, self.thetaPrior)
print initPi, pi, theta, NU
expectedInitPi = [0.44, 0.0, 0.2, 0.36]
expectedPi = [1.0, 0.0, 0.0, 0.0]
expectedTheta = [1.0, 0.0, 0.0, 0.0]
expectedNU0 = [1.0, 0.0]
expectedNU1 = [1.0, 0.0]
expectedNU2 = [1.0, 0.0, 0.0]
expectedNU3 = [1.0, 0.0, 0.0]
expectedNU4 = [1.0, 0.0, 0.0]
diffInitPi = [abs(a - b) for a, b in zip(initPi, expectedInitPi)]
diffPi = [abs(a - b) for a, b in zip(pi, expectedPi)]
diffTheta = [abs(a - b) for a, b in zip(theta, expectedTheta)]
diffNU0 = [abs(a - b) for a, b in zip(NU[2][2], expectedNU0)]
diffNU1 = [abs(a - b) for a, b in zip(NU[3][2], expectedNU1)]
diffNU2 = [abs(a - b) for a, b in zip(NU[2][2], expectedNU2)]
diffNU3 = [abs(a - b) for a, b in zip(NU[3][2], expectedNU3)]
diffNU4 = [abs(a - b) for a, b in zip(NU[4][2], expectedNU4)]
delta = [0.01] * 4
self.assertTrue(diffInitPi < delta, "Failed initPi Assertion")
self.assertTrue(diffPi < delta, "Failed Pi Assertion")
self.assertTrue(diffTheta < delta, "Failed Theta Assertion")
delta = [0.0001] * 2
self.assertTrue(diffNU0 < delta, "Failed Non-Unique Read 3 Assertion")
self.assertTrue(diffNU1 < delta, "Failed Non-Unique Read 4 Assertion")
delta = [0.0001] * 3
self.assertTrue(diffNU2 < delta, "Failed Non-Unique Read 2 Assertion")
self.assertTrue(diffNU3 < delta, "Failed Non-Unique Read 2 Assertion")
self.assertTrue(diffNU4 < delta, "Failed Non-Unique Read 2 Assertion")
def test_pathoscope_em_x1(self):
### 2 unique reads: 2 reads to genome1
U = {0: [0, 0.5], 1: [0, 0.5]}
### 0 non-unique reads: 0 total reads readnum:[[genomes],[qij],[xij]]
NU = {}
### Genome hash
genomes = {0:"genome1", 1:"genome2", 2:"genome3", 3:"genome4"}
(initPi, pi, theta, NU) = PathoID.pathoscope_em(U, NU, genomes,
self.maxIter, self.emEpsilon, self.verbose, self.piPrior, self.thetaPrior)
print initPi, pi, theta, NU
expectedInitPi = [1.0, 0.0, 0.0, 0.0]
expectedPi = [1.0, 0.0, 0.0, 0.0]
expectedTheta = [0.0, 0.0, 0.0, 0.0]
diffInitPi = [abs(a - b) for a, b in zip(initPi, expectedInitPi)]
diffPi = [abs(a - b) for a, b in zip(pi, expectedPi)]
diffTheta = [abs(a - b) for a, b in zip(theta, expectedTheta)]
delta = [0.0001]*4
self.assertTrue(diffInitPi < delta, "Failed initPi Assertion")
self.assertTrue(diffPi < delta, "Failed Pi Assertion")
self.assertTrue(diffTheta < delta, "Failed Theta Assertion")
def main():
# parse some argument lists
inputArgs = parser.parse_args()
#### PathoID modules ####
start = time();
if (inputArgs.subcommand=='LIB'):
################################################$
#append taxon id in the front of sequence header
################################################$
NAs = 'X'
if inputArgs.lib_dbuser!=NAs and inputArgs.lib_dbpasswd==NAs:
print 'if you want to use mysql, make sure that you install pathoDB and '
'also specify the corresponding mysql password correctly '
'(Ask your mysql admin to access the database).'
MysqlConf=(inputArgs.lib_dbhost,inputArgs.lib_dbport,inputArgs.lib_dbuser,inputArgs.lib_dbpasswd,inputArgs.lib_db)
taxon_ids=pathoLib.parse_input_app_build_nt_tgt(inputArgs.lib_taxon_ids)
exclude_taxon_ids=pathoLib.parse_input_app_build_nt_tgt(inputArgs.lib_exclude_taxon_ids)
(ncbiNt_ti,ncbiNt_invalid) = pathoLib.append_ti_into_fasta_app(inputArgs.lib_reference,
taxon_ids, exclude_taxon_ids, inputArgs.lib_subtax,MysqlConf,
not(inputArgs.lib_nodesc), inputArgs.lib_online_search, inputArgs.lib_outprefix,
inputArgs.lib_outdir)
if (inputArgs.subcommand=='MAP'):
pathoMapOptions = PathoMapA.PathoMapOptions()
pathoMapOptions.verbose = inputArgs.verbose
pathoMapOptions.outDir = inputArgs.map_outdir
pathoMapOptions.indexDir = inputArgs.map_indexdir
pathoMapOptions.outAlignFile = inputArgs.map_outalign
pathoMapOptions.inReadFile = inputArgs.map_inputread
pathoMapOptions.inReadFilePair1 = inputArgs.map_inputread1
pathoMapOptions.inReadFilePair2 = inputArgs.map_inputread2
pathoMapOptions.targetAlignParameters = inputArgs.map_targetalignparams
pathoMapOptions.filterAlignParameters = inputArgs.map_filteralignparams
if (len(inputArgs.map_targetref)>0):
pathoMapOptions.targetRefFiles = inputArgs.map_targetref.split(",")
if (len(inputArgs.map_filterref)>0):
pathoMapOptions.filterRefFiles = inputArgs.map_filterref.split(",")
if (len(inputArgs.map_targetindex)>0):
pathoMapOptions.targetIndexPrefixes = inputArgs.map_targetindex.split(",")
if (len(inputArgs.map_filterindex)>0):
pathoMapOptions.filterIndexPrefixes = inputArgs.map_filterindex.split(",")
if (len(inputArgs.map_targetalign)>0):
pathoMapOptions.targetAlignFiles = inputArgs.map_targetalign.split(",")
if (len(inputArgs.map_filteralign)>0):
pathoMapOptions.filterAlignFiles = inputArgs.map_filteralign.split(",")
pathoMapOptions.btHome = inputArgs.map_bthome
pathoMapOptions.numThreads = inputArgs.map_numthreads
pathoMapOptions.exp_tag = inputArgs.map_exp_tag + "-"
PathoMapA.processPathoMap(pathoMapOptions)
if (inputArgs.subcommand=='ID'):
pathoIdOptions = PathoID.PathoIdOptions(inputArgs.id_ali_file)
pathoIdOptions.ali_format = inputArgs.id_ali_format
pathoIdOptions.verbose = inputArgs.verbose
pathoIdOptions.out_matrix_flag = inputArgs.id_out_matrix
pathoIdOptions.score_cutoff = inputArgs.id_score_cutoff
pathoIdOptions.exp_tag = inputArgs.id_exp_tag
pathoIdOptions.outdir = inputArgs.id_outdir
pathoIdOptions.emEpsilon = inputArgs.id_emEpsilon
pathoIdOptions.maxIter = inputArgs.id_maxIter
pathoIdOptions.piPrior = inputArgs.id_piPrior
pathoIdOptions.thetaPrior = inputArgs.id_thetaPrior
pathoIdOptions.noalign = inputArgs.id_noalign
pathoIdOptions.noCutOff = inputArgs.id_nocutoff
PathoID.pathoscope_reassign(pathoIdOptions)
if (inputArgs.subcommand=='REP'):
pathoReportOptions = PathoReportA.PathoReportOptions(inputArgs.rep_ali_file)
pathoReportOptions.verbose = inputArgs.verbose
pathoReportOptions.contigFlag = inputArgs.rep_contig_flag
pathoReportOptions.outDir = inputArgs.rep_outdir
pathoReportOptions.samtoolsHome = inputArgs.rep_samtoolshome
pathoReportOptions.noCutOff = inputArgs.rep_nocutoff
mysqlConf=(inputArgs.rep_dbhost,inputArgs.rep_dbport,inputArgs.rep_dbuser,
inputArgs.rep_dbpasswd,inputArgs.rep_db)
pathoReportOptions.mysqlConf = mysqlConf
PathoReportA.processPathoReport(pathoReportOptions)
if (inputArgs.subcommand=='QC'):
qcargs = sys.argv[2:]
pathoqcdir = pathoscopedir + os.path.sep + 'pathoscope' + os.path.sep + 'pathoqc'
pathoqcfile = pathoqcdir + os.path.sep + 'pathoqc.py'
if os.path.exists(pathoqcfile):
cmd = sys.executable
cmd += " " + pathoqcfile + " "
cmd += " ".join(qcargs)
print(cmd)
os.system(cmd)
else:
print("PathoQC (" + pathoqcfile + ") not found. Please download pathoqc_vXXX.tar.gz and "
"install it ("+pathoqcdir+") from http://sourceforge.net/projects/pathoscope/")
elapsed = time() - start;
if inputArgs.verbose:
print "Total Elapsed Time: %d" % (elapsed)
def main():
# parse some argument lists
inputArgs = parser.parse_args()
#### PathoID modules ####
start = time()
if (inputArgs.subcommand == 'LIB'):
################################################$
#append taxon id in the front of sequence header
################################################$
NAs = 'X'
if inputArgs.lib_dbuser != NAs and inputArgs.lib_dbpasswd == NAs:
print 'if you want to use mysql, make sure that you install pathoDB and '
'also specify the corresponding mysql password correctly '
'(Ask your mysql admin to access the database).'
MysqlConf = (inputArgs.lib_dbhost, inputArgs.lib_dbport,
inputArgs.lib_dbuser, inputArgs.lib_dbpasswd,
inputArgs.lib_db)
taxon_ids = pathoLib.parse_input_app_build_nt_tgt(
inputArgs.lib_taxon_ids)
exclude_taxon_ids = pathoLib.parse_input_app_build_nt_tgt(
inputArgs.lib_exclude_taxon_ids)
(ncbiNt_ti, ncbiNt_invalid) = pathoLib.append_ti_into_fasta_app(
inputArgs.lib_reference, taxon_ids, exclude_taxon_ids,
inputArgs.lib_subtax, MysqlConf, not (inputArgs.lib_nodesc),
inputArgs.lib_online_search, inputArgs.lib_outprefix,
inputArgs.lib_outdir)
if (inputArgs.subcommand == 'MAP'):
pathoMapOptions = PathoMapA.PathoMapOptions()
pathoMapOptions.verbose = inputArgs.verbose
pathoMapOptions.outDir = inputArgs.map_outdir
pathoMapOptions.indexDir = inputArgs.map_indexdir
pathoMapOptions.outAlignFile = inputArgs.map_outalign
pathoMapOptions.inReadFile = inputArgs.map_inputread
pathoMapOptions.inReadFilePair1 = inputArgs.map_inputread1
pathoMapOptions.inReadFilePair2 = inputArgs.map_inputread2
pathoMapOptions.targetAlignParameters = inputArgs.map_targetalignparams
pathoMapOptions.filterAlignParameters = inputArgs.map_filteralignparams
if (len(inputArgs.map_targetref) > 0):
pathoMapOptions.targetRefFiles = inputArgs.map_targetref.split(",")
if (len(inputArgs.map_filterref) > 0):
pathoMapOptions.filterRefFiles = inputArgs.map_filterref.split(",")
if (len(inputArgs.map_targetindex) > 0):
pathoMapOptions.targetIndexPrefixes = inputArgs.map_targetindex.split(
",")
if (len(inputArgs.map_filterindex) > 0):
pathoMapOptions.filterIndexPrefixes = inputArgs.map_filterindex.split(
",")
if (len(inputArgs.map_targetalign) > 0):
pathoMapOptions.targetAlignFiles = inputArgs.map_targetalign.split(
",")
if (len(inputArgs.map_filteralign) > 0):
pathoMapOptions.filterAlignFiles = inputArgs.map_filteralign.split(
",")
pathoMapOptions.btHome = inputArgs.map_bthome
pathoMapOptions.numThreads = inputArgs.map_numthreads
pathoMapOptions.exp_tag = inputArgs.map_exp_tag + "-"
PathoMapA.processPathoMap(pathoMapOptions)
if (inputArgs.subcommand == 'ID'):
pathoIdOptions = PathoID.PathoIdOptions(inputArgs.id_ali_file)
pathoIdOptions.ali_format = inputArgs.id_ali_format
pathoIdOptions.verbose = inputArgs.verbose
pathoIdOptions.out_matrix_flag = inputArgs.id_out_matrix
pathoIdOptions.score_cutoff = inputArgs.id_score_cutoff
pathoIdOptions.exp_tag = inputArgs.id_exp_tag
pathoIdOptions.outdir = inputArgs.id_outdir
pathoIdOptions.emEpsilon = inputArgs.id_emEpsilon
pathoIdOptions.maxIter = inputArgs.id_maxIter
pathoIdOptions.piPrior = inputArgs.id_piPrior
pathoIdOptions.thetaPrior = inputArgs.id_thetaPrior
pathoIdOptions.noalign = inputArgs.id_noalign
pathoIdOptions.noCutOff = inputArgs.id_nocutoff
PathoID.pathoscope_reassign(pathoIdOptions)
if (inputArgs.subcommand == 'REP'):
pathoReportOptions = PathoReportA.PathoReportOptions(
inputArgs.rep_ali_file)
pathoReportOptions.verbose = inputArgs.verbose
pathoReportOptions.contigFlag = inputArgs.rep_contig_flag
pathoReportOptions.outDir = inputArgs.rep_outdir
pathoReportOptions.samtoolsHome = inputArgs.rep_samtoolshome
pathoReportOptions.noCutOff = inputArgs.rep_nocutoff
mysqlConf = (inputArgs.rep_dbhost, inputArgs.rep_dbport,
inputArgs.rep_dbuser, inputArgs.rep_dbpasswd,
inputArgs.rep_db)
pathoReportOptions.mysqlConf = mysqlConf
PathoReportA.processPathoReport(pathoReportOptions)
if (inputArgs.subcommand == 'QC'):
qcargs = sys.argv[2:]
pathoqcdir = pathoscopedir + os.path.sep + 'pathoscope' + os.path.sep + 'pathoqc'
pathoqcfile = pathoqcdir + os.path.sep + 'pathoqc.py'
if os.path.exists(pathoqcfile):
cmd = sys.executable
cmd += " " + pathoqcfile + " "
cmd += " ".join(qcargs)
print(cmd)
os.system(cmd)
else:
print(
"PathoQC (" + pathoqcfile +
") not found. Please download pathoqc_vXXX.tar.gz and "
"install it (" + pathoqcdir +
") from http://sourceforge.net/projects/pathoscope/")
elapsed = time() - start
if inputArgs.verbose:
print "Total Elapsed Time: %d" % (elapsed)
pathoMapOptions.targetIndexPrefixes = inputArgs.map_targetindex.split(
",")
if (len(inputArgs.map_filterindex) > 0):
pathoMapOptions.filterIndexPrefixes = inputArgs.map_filterindex.split(
",")
if (len(inputArgs.map_targetalign) > 0):
pathoMapOptions.targetAlignFiles = inputArgs.map_targetalign.split(",")
if (len(inputArgs.map_filteralign) > 0):
pathoMapOptions.filterAlignFiles = inputArgs.map_filteralign.split(",")
pathoMapOptions.btHome = inputArgs.map_bthome
pathoMapOptions.numThreads = inputArgs.map_numthreads
pathoMapOptions.exp_tag = inputArgs.map_exp_tag + "-"
PathoMapA.processPathoMap(pathoMapOptions)
if (inputArgs.subcommand == 'ID'):
pathoIdOptions = PathoID.PathoIdOptions(inputArgs.id_ali_file)
pathoIdOptions.ali_format = inputArgs.id_ali_format
pathoIdOptions.verbose = inputArgs.verbose
pathoIdOptions.out_matrix_flag = inputArgs.id_out_matrix
pathoIdOptions.score_cutoff = inputArgs.id_score_cutoff
pathoIdOptions.exp_tag = inputArgs.id_exp_tag
pathoIdOptions.outdir = inputArgs.id_outdir
pathoIdOptions.emEpsilon = inputArgs.id_emEpsilon
pathoIdOptions.maxIter = inputArgs.id_maxIter
pathoIdOptions.piPrior = inputArgs.id_piPrior
pathoIdOptions.thetaPrior = inputArgs.id_thetaPrior
pathoIdOptions.noalign = inputArgs.id_noalign
PathoID.pathoscope_reassign(pathoIdOptions)
if (inputArgs.subcommand == 'REP'):
pathoReportOptions = PathoReportA.PathoReportOptions(
default='testset',
dest='exp_tag',
help='Experiment tag')
parser.add_argument('-outdir',
action='store',
default='.',
dest='outdir',
help='Output Directory')
parser.add_argument('--version', action='version', version='%(prog)s 1.0')
parser.add_argument('-t',
action='store',
default='sam',
dest='ali_format',
help='Alignment Format: sam/bl8/gnu-sam')
parser.add_argument('-f',
action='store',
dest='ali_file',
required=True,
help='Alignment file path')
inputArgs = parser.parse_args()
start = time()
PathoID.pathoscope_reassign(inputArgs.out_matrix, inputArgs.verbose,
inputArgs.score_cutoff, inputArgs.exp_tag,
inputArgs.ali_format, inputArgs.ali_file,
inputArgs.outdir, inputArgs.emEpsilon,
inputArgs.maxIter, not (inputArgs.noalign))
elapsed = time() - start
if inputArgs.verbose:
print "EM Elapsed Time: %d" % (elapsed)
parser.add_argument('-o', action='store_true', default=False, dest='out_matrix',
help='Output alignment matrix')
parser.add_argument('-noUpdatedAlignFile', action='store_true', default=False, dest='noalign',
help='Do not generate an updated alignment file')
parser.add_argument('-verbose', action='store_true', default=False, dest='verbose',
help='Prints verbose text while running')
parser.add_argument('-s', action='store', default=0.01, type=float,
dest='score_cutoff', help='Score Cutoff')
parser.add_argument('-emEpsilon', action='store', default=1e-7, type=float,
dest='emEpsilon', help='EM Algorithm Epsilon cutoff')
parser.add_argument('-maxIter', action='store', default=50, type=int,
dest='maxIter', help='EM Algorithm maximum iterations')
parser.add_argument('-e', action='store', default='testset', dest='exp_tag',
help='Experiment tag')
parser.add_argument('-outdir', action='store', default='.', dest='outdir',
help='Output Directory')
parser.add_argument('--version', action='version', version=VERSION)
parser.add_argument('-t', action='store', default='sam', dest='ali_format',
help='Alignment Format: sam/bl8/gnu-sam')
parser.add_argument('-f', action='store', dest='ali_file', required=True,
help='Alignment file path')
inputArgs = parser.parse_args()
start = time();
PathoID.pathoscope_reassign(inputArgs.out_matrix, inputArgs.verbose,
inputArgs.score_cutoff, inputArgs.exp_tag, inputArgs.ali_format, inputArgs.ali_file,
inputArgs.outdir, inputArgs.emEpsilon, inputArgs.maxIter, not(inputArgs.noalign))
elapsed = time() - start;
if inputArgs.verbose:
print "EM Elapsed Time: %d" % (elapsed)
PathoMapA.processPathoMap(pathoMapOptions) if (inputArgs.subcommand=='ID'): pathoIdOptions = PathoID.PathoIdOptions(inputArgs.id_ali_file) pathoIdOptions.ali_format = inputArgs.id_ali_format pathoIdOptions.verbose = inputArgs.verbose pathoIdOptions.out_matrix_flag = inputArgs.id_out_matrix pathoIdOptions.score_cutoff = inputArgs.id_score_cutoff pathoIdOptions.exp_tag = inputArgs.id_exp_tag pathoIdOptions.outdir = inputArgs.id_outdir pathoIdOptions.emEpsilon = inputArgs.id_emEpsilon pathoIdOptions.maxIter = inputArgs.id_maxIter pathoIdOptions.piPrior = inputArgs.id_piPrior pathoIdOptions.thetaPrior = inputArgs.id_thetaPrior pathoIdOptions.noalign = inputArgs.id_noalign PathoID.pathoscope_reassign(pathoIdOptions) if (inputArgs.subcommand=='REP'): pathoReportOptions = PathoReportA.PathoReportOptions(inputArgs.rep_ali_file) pathoReportOptions.verbose = inputArgs.verbose pathoReportOptions.contigFlag = inputArgs.rep_contig_flag pathoReportOptions.outDir = inputArgs.rep_outdir pathoReportOptions.samtoolsHome = inputArgs.rep_samtoolshome mysqlConf=(inputArgs.rep_dbhost,inputArgs.rep_dbport,inputArgs.rep_dbuser, inputArgs.rep_dbpasswd,inputArgs.rep_db) pathoReportOptions.mysqlConf = mysqlConf PathoReportA.processPathoReport(pathoReportOptions) elapsed = time() - start; if inputArgs.verbose: print "Total Elapsed Time: %d" % (elapsed)
