def testReadKoFile(koFile):
kPmap = readKOFile(koFile, 'PATHWAY')
assert ('K00397' not in kPmap)
myAssertEq(kPmap['K00399'],
['ko00680 Methane metabolism', 'ko01200 Carbon metabolism'])
kEmap = readKOFile(koFile, 'EC')
myAssertEq(kEmap['K00397'], ['EC:1.8.99.-'])
myAssertEq(kEmap['K00399'], ['EC:2.8.4.1'])
def testReadKoFile(koFile):
kPmap = readKOFile(koFile, 'PATHWAY')
assert('K00397' not in kPmap)
myAssertEq(kPmap['K00399'],
['ko00680 Methane metabolism',
'ko01200 Carbon metabolism'])
kEmap = readKOFile(koFile, 'EC')
myAssertEq(kEmap['K00397'], ['EC:1.8.99.-'])
myAssertEq(kEmap['K00399'], ['EC:2.8.4.1'])
def testReadKeggFile(keggFile):
kDmap = parse_keg_file(keggFile, 'DESCRIPTION')
myAssertEq(kDmap['K01623'],
'ALDO; fructose-bisphosphate aldolase, class I [EC:4.1.2.13]')
kPmap = parse_keg_file(keggFile, 'PATHWAY')
assert('K04519' in kPmap)
assert('K15634' in kPmap)
myAssertEq(kPmap['K03011'],
['00230 Purine metabolism',
'00240 Pyrimidine metabolism',
'03020 RNA polymerase',
"05016 Huntington's disease",
'05169 Epstein-Barr virus infection'])
k2map = parse_keg_file(keggFile, 2)
myAssertEq(k2map['K13810'][0].lower(), 'Carbohydrate Metabolism'.lower())
myAssertEq(k2map['K13810'][1].lower(), 'Overview'.lower())
myAssertEq(k2map['K00399'][0].lower(), 'Energy Metabolism'.lower())
myAssertEq(k2map['K00399'][1].lower(), 'Overview'.lower())
k3map = parse_keg_file(keggFile, 3)
myAssertEq(k3map['K13810'], [
'00010 Glycolysis / Gluconeogenesis [PATH:ko00010]',
'00030 Pentose phosphate pathway [PATH:ko00030]',
'00500 Starch and sucrose metabolism [PATH:ko00500]',
'00520 Amino sugar and nucleotide sugar metabolism [PATH:ko00520]',
'01230 Biosynthesis of amino acids [PATH:ko01230]',
])
myAssertEq(k3map['K00399'], [
'00680 Methane metabolism [PATH:ko00680]',
'01200 Carbon metabolism [PATH:ko01200]',
])
myAssertEq(k3map['K03404'], [
'00860 Porphyrin and chlorophyll metabolism [PATH:ko00860]',
])
k3mapQ = parse_keg_file(keggFile, '3')
for k in k3map.keys():
try:
myAssertEq(k3map[k], k3mapQ[k])
except AssertionError:
raise AssertionError(
"level 3 classes for %s do not match:\n%s\n%s" %
(k, k3map[k], k3mapQ[k]))
def testParseGeneLink(koFile):
gkmap = parseLinkFile(koFile)
myAssertEq(gkmap['ggo:101148121'], ['K16534'])
myAssertEq(gkmap['olu:OSTLU_15108'], ['K11126'])
myAssertEq(gkmap['ebt:EBL_c03070'], ['K02879'])
myAssertEq(gkmap['pec:W5S_4205'], ['K00363'])
myAssertEq(gkmap['buc:BU148'], ['K03101'])
myAssertEq(gkmap['smaf:D781_0330'], ['K06925'])
myAssertEq(gkmap['nkr:NKOR_05565'], ['K03524'])
def test():
import sys
global myAssertEq, myAssertIs
from edl.test import myAssertEq, myAssertIs
if len(sys.argv)>1:
loglevel=logging.DEBUG
else:
loglevel=logging.WARN
logging.basicConfig(stream=sys.stderr, level=loglevel)
m8data=["001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3 gi|91763278|ref|ZP_01265242.1| Peptidase family M48 [Candidatus Pelagibacter ubique HTCC1002] 61.7021276595745 94 282 1 57 150 134 4e-30 0.992957746478873\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3 gi|71083682|ref|YP_266402.1| M48 family peptidase [Candidatus Pelagibacter ubique HTCC1062] 61.7021276595745 94 282 1 40 133 134 4e-30 0.992957746478873\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3 gi|262277211|ref|ZP_06055004.1| peptidase family M48 family [alpha proteobacterium HIMB114] 65.9090909090909 88 264 1 63 150 132 9e-30 0.929577464788732\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3 gi|254456035|ref|ZP_05069464.1| peptidase family M48 [Candidatus Pelagibacter sp. HTCC7211] 66.2790697674419 86 258 1 65 150 132 2e-29 0.908450704225352\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3 gi|118581678|ref|YP_902928.1| peptidase M48, Ste24p [Pelobacter propionicus DSM 2379] 51.6129032258064 93 282 4 53 144 108 2e-22 0.982394366197183\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3 gi|255534285|ref|YP_003094656.1| zn-dependent protease with chaperone function [Flavobacteriaceae bacterium 3519-10] 47.3118279569892 93 282 4 55 146 102 1e-20 0.982394366197183\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3 gi|317502588|ref|ZP_07960709.1| M48B family peptidase [Prevotella salivae DSM 15606] 51.6129032258064 93 279 1 85 176 100 7e-20 0.982394366197183\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3 gi|325104752|ref|YP_004274406.1| peptidase M48 Ste24p [Pedobacter saltans DSM 12145] 48.3870967741936 93 279 1 59 150 100 7e-20 0.982394366197183\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3 gi|256425464|ref|YP_003126117.1| peptidase M48 Ste24p [Chitinophaga pinensis DSM 2588] 48.8888888888889 90 273 4 58 146 99.8 9e-20 0.950704225352113\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3 gi|299142895|ref|ZP_07036022.1| peptidase, M48 family [Prevotella oris C735] 50 94 282 1 58 150 99.4 1e-19 0.992957746478873\n"]
#test1 passthrough
logging.info("Starting passthrough test")
m8stream=m8data.__iter__()
params=FilterParams()
outs = filterM8Stream(m8stream,params)
myAssertEq(outs.next(),m8data[0])
myAssertEq(outs.next(),m8data[1])
myAssertEq(outs.next(),m8data[2])
myAssertEq(outs.next(),m8data[3])
myAssertEq(outs.next(),m8data[4])
logging.info("Starting best test")
m8stream=m8data.__iter__()
params=FilterParams(topPct=0.)
outs = filterM8Stream(m8stream,params)
myAssertEq(outs.next(),m8data[0])
myAssertEq(outs.next(),m8data[1])
try:
outs.next()
sys.exit("There should only be 2 elements!")
except StopIteration:
pass
logging.info("Starting n1 test")
m8stream=m8data.__iter__()
params = FilterParams(hitsPerRead=1)
outs = filterM8Stream(m8stream,params)
myAssertEq(outs.next(),m8data[0])
try:
outs.next()
sys.exit("There should only be 1 elements!")
except StopIteration:
pass
def test_gff():
setup_tests()
line = 'KM282-20-02b-5_c283151\tcsearch\ttRNA\t303\t233\t' + \
'40.6\t-\t.\tTarget=RF00005 2 70\n'
hit = Hit(line, 'gff')
myAssertEq(hit.read, 'KM282-20-02b-5_c283151')
myAssertEq(hit.score, 40.6)
myAssertEq(hit.hit, 'RF00005')
line = 'KM282-20-02a-100_c12273\tbarrnap:0.7\trRNA\t9\t772\t' + \
'6.8e-41\t+\t.\tName=12S_rRNA;product=12S ribosomal RNA\n'
hit = Hit(line, 'gff')
myAssertEq(hit.read, 'KM282-20-02a-100_c12273')
myAssertEq(hit.evalue, 6.8e-41)
myAssertEq(hit.hit, '12S_rRNA')
line = 'KM282-20-02a-100_c1\tProdigal_v2.6.2\tCDS\t309\t686\t' + \
'53.3\t-\t0\tID=1_2;partial=00;start_type=ATG;rbs_motif=' + \
'AGGA;rbs_spacer=5-10bp;gc_cont=0.381;conf=100.00;score=' + \
'54.54;cscore=45.68;sscore=8.86;rscore=5.50;uscore=-0.63;' + \
'tscore=2.76;\n'
hit = Hit(line, 'gff')
myAssertEq(hit.read, 'KM282-20-02a-100_c1')
myAssertEq(hit.score, 53.3)
myAssertEq(hit.hit, '1_2')
def test():
setup_tests()
m8data = ["001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3"
" gi|91763278|ref|ZP_01265242.1| Peptidase family"
" M48 [Candidatus Pelagibacter ubique HTCC1002]"
" 61.7021276595745 94 282 1 57 150 134 4e-30"
" 0.992957746478873\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3"
" gi|71083682|ref|YP_266402.1|"
" M48 family peptidase [Candidatus Pelagibacter ubique"
" HTCC1062] 61.7021276595745 94 282 1 40 133 134"
" 4e-30 0.992957746478873\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3"
" gi|262277211|ref|ZP_06055004.1| peptidase family M48 family"
" [alpha proteobacterium HIMB114] 65.9090909090909 88 264"
" 1 63 150 132 9e-30 0.929577464788732\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3"
" gi|254456035|ref|ZP_05069464.1| peptidase family M48"
" [Candidatus Pelagibacter sp. HTCC7211] 66.2790697674419"
" 86 258 1 65 150 132 2e-29 0.908450704225352\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3"
" gi|118581678|ref|YP_902928.1| peptidase M48, Ste24p"
" [Pelobacter propionicus DSM 2379] 51.6129032258064 93"
" 282 4 53 144 108 2e-22 0.982394366197183\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3"
" gi|255534285|ref|YP_003094656.1| zn-dependent protease"
" with chaperone function [Flavobacteriaceae bacterium"
" 3519-10] 47.3118279569892 93 282 4 55 146 102"
" 1e-20 0.982394366197183\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3"
" gi|317502588|ref|ZP_07960709.1| M48B family peptidase"
" [Prevotella salivae DSM 15606] 51.6129032258064 93"
" 279 1 85 176 100 7e-20 0.982394366197183\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3"
" gi|325104752|ref|YP_004274406.1| peptidase M48 Ste24p"
" [Pedobacter saltans DSM 12145] 48.3870967741936 93"
" 279 1 59 150 100 7e-20 0.982394366197183\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3"
" gi|256425464|ref|YP_003126117.1| peptidase M48 Ste24p"
" [Chitinophaga pinensis DSM 2588] 48.8888888888889"
" 90 273 4 58 146 99.8 9e-20 0.950704225352113\n",
"001598_1419_3101 H186x25M length=284 uaccno=E3N7QM101DQXE3"
" gi|299142895|ref|ZP_07036022.1| peptidase, M48 family"
" [Prevotella oris C735] 50 94 282 1 58 150 99.4"
" 1e-19 0.992957746478873\n"]
# test1 passthrough
logging.info("Starting passthrough test")
m8stream = m8data.__iter__()
params = FilterParams()
outs = filterM8Stream(m8stream, params, returnLines=True)
myAssertEq(next(outs), m8data[0])
myAssertEq(next(outs), m8data[1])
myAssertEq(next(outs), m8data[2])
myAssertEq(next(outs), m8data[3])
myAssertEq(next(outs), m8data[4])
logging.info("Starting best test")
m8stream = m8data.__iter__()
params = FilterParams(top_pct=0.)
outs = filterM8Stream(m8stream, params)
myAssertEq(next(outs), m8data[0])
myAssertEq(next(outs), m8data[1])
try:
next(outs)
sys.exit("There should only be 2 elements!")
except StopIteration:
pass
logging.info("Starting n1 test")
m8stream = m8data.__iter__()
params = FilterParams(hits_per_read=1)
outs = filterM8Stream(m8stream, params)
myAssertEq(next(outs), m8data[0])
try:
next(outs)
sys.exit("There should only be 1 elements!")
except StopIteration:
pass
def test_gff():
setup_tests()
line = 'KM282-20-02b-5_c283151\tcsearch\ttRNA\t303\t233\t' + \
'40.6\t-\t.\tTarget=RF00005 2 70\n'
hit = Hit(line, 'gff')
myAssertEq(hit.read, 'KM282-20-02b-5_c283151')
myAssertEq(hit.score, 40.6)
myAssertEq(hit.hit, 'RF00005')
line = 'KM282-20-02a-100_c12273\tbarrnap:0.7\trRNA\t9\t772\t' + \
'6.8e-41\t+\t.\tName=12S_rRNA;product=12S ribosomal RNA\n'
hit = Hit(line, 'gff')
myAssertEq(hit.read, 'KM282-20-02a-100_c12273')
myAssertEq(hit.evalue, 6.8e-41)
myAssertEq(hit.hit, '12S_rRNA')
line = 'KM282-20-02a-100_c1\tProdigal_v2.6.2\tCDS\t309\t686\t' + \
'53.3\t-\t0\tID=1_2;partial=00;start_type=ATG;rbs_motif=' + \
'AGGA;rbs_spacer=5-10bp;gc_cont=0.381;conf=100.00;score=' + \
'54.54;cscore=45.68;sscore=8.86;rscore=5.50;uscore=-0.63;' + \
'tscore=2.76;\n'
hit = Hit(line, 'gff')
myAssertEq(hit.read, 'KM282-20-02a-100_c1')
myAssertEq(hit.score, 53.3)
myAssertEq(hit.hit, '1_2')
def testReadKeggFile(keggFile):
kDmap = readKeggFile(keggFile, 'DESCRIPTION')
myAssertEq(kDmap['K09630'], ['PRSS36; protease, serine, 36 [EC:3.4.21.-]'])
kPmap = readKeggFile(keggFile, 'PATHWAY')
assert('K00397' in kPmap)
myAssertEq(kPmap['K00399'], ['01200 Carbon metabolism',
'00680 Methane metabolism', '01000 Enzymes'])
k2map = readKeggFile(keggFile, 2)
myAssertEq(k2map['K13810'][1].lower(), 'Carbohydrate Metabolism'.lower())
myAssertEq(k2map['K13810'][0].lower(), 'Overview'.lower())
myAssertEq(k2map['K00399'][1].lower(), 'Energy Metabolism'.lower())
myAssertEq(k2map['K00399'][0].lower(), 'Overview'.lower())
k3map = readKeggFile(keggFile, 3)
myAssertEq(k3map['K13810'],
['01230 Biosynthesis of amino acids',
'00010 Glycolysis / Gluconeogenesis',
'00030 Pentose phosphate pathway',
'00500 Starch and sucrose metabolism',
'00520 Amino sugar and nucleotide sugar metabolism',
'01000 Enzymes',
'01000 Enzymes'])
myAssertEq(k3map['K00399'], ['01200 Carbon metabolism',
'00680 Methane metabolism', '01000 Enzymes'])
myAssertEq(
k3map['K03404'], [
'00860 Porphyrin and chlorophyll metabolism', '01000 Enzymes'])
myAssertEq(k3map['K01976'], ['01000 Enzymes'])
myAssertEq(k3map['K07347'],
['02000 Transporters',
'02044 Secretion system',
'02035 Bacterial motility proteins',
'05133 Pertussis'])
myAssertEq(k3map['K09630'], ['01000 Enzymes', '01002 Peptidases'])
k3mapQ = readKeggFile(keggFile, '3')
for k in k3map.keys():
try:
myAssertEq(k3map[k], k3mapQ[k])
except AssertionError:
raise AssertionError(
"level 3 classes for %s do not match:\n%s\n%s" %
(k, k3map[k], k3mapQ[k]))
def testParseGeneLink(koFile):
gkmap = parseLinkFile(koFile)
myAssertEq(gkmap['ggo:101148121'], ['K16534'])
myAssertEq(gkmap['olu:OSTLU_15108'], ['K11126'])
myAssertEq(gkmap['ebt:EBL_c03070'], ['K02879'])
myAssertEq(gkmap['pec:W5S_4205'], ['K00363'])
myAssertEq(gkmap['buc:BU148'], ['K03101'])
myAssertEq(gkmap['smaf:D781_0330'], ['K06925'])
myAssertEq(gkmap['nkr:NKOR_05565'], ['K03524'])
def testReadKeggFile(keggFile):
kDmap = readKeggFile(keggFile, 'DESCRIPTION')
myAssertEq(kDmap['K09630'], ['PRSS36; protease, serine, 36 [EC:3.4.21.-]'])
kPmap = readKeggFile(keggFile, 'PATHWAY')
assert ('K00397' in kPmap)
myAssertEq(kPmap['K00399'], [
'01200 Carbon metabolism', '00680 Methane metabolism', '01000 Enzymes'
])
k2map = readKeggFile(keggFile, 2)
myAssertEq(k2map['K13810'][1].lower(), 'Carbohydrate Metabolism'.lower())
myAssertEq(k2map['K13810'][0].lower(), 'Overview'.lower())
myAssertEq(k2map['K00399'][1].lower(), 'Energy Metabolism'.lower())
myAssertEq(k2map['K00399'][0].lower(), 'Overview'.lower())
k3map = readKeggFile(keggFile, 3)
myAssertEq(k3map['K13810'], [
'01230 Biosynthesis of amino acids',
'00010 Glycolysis / Gluconeogenesis',
'00030 Pentose phosphate pathway',
'00500 Starch and sucrose metabolism',
'00520 Amino sugar and nucleotide sugar metabolism', '01000 Enzymes',
'01000 Enzymes'
])
myAssertEq(k3map['K00399'], [
'01200 Carbon metabolism', '00680 Methane metabolism', '01000 Enzymes'
])
myAssertEq(k3map['K03404'],
['00860 Porphyrin and chlorophyll metabolism', '01000 Enzymes'])
myAssertEq(k3map['K01976'], ['01000 Enzymes'])
myAssertEq(k3map['K07347'], [
'02000 Transporters', '02044 Secretion system',
'02035 Bacterial motility proteins', '05133 Pertussis'
])
myAssertEq(k3map['K09630'], ['01000 Enzymes', '01002 Peptidases'])
k3mapQ = readKeggFile(keggFile, '3')
for k in k3map.keys():
try:
myAssertEq(k3map[k], k3mapQ[k])
except AssertionError:
raise AssertionError(
"level 3 classes for %s do not match:\n%s\n%s" %
(k, k3map[k], k3mapQ[k]))
