def test_2_compare_hits_12(self):
# test 20 hits, one function, case 2.5
hit = DiamondHit()
hit.import_hit('NS500496_240_HYN75BGXX:1:11112:25043:18797#CTCTCT/2 kegg|nio:NITINOP_1721 58.5 41 17 311 3 125 271 311 4.2e-05 44.3 RP-L22'.split('\t'))
read = AnnotatedRead('NS500496_240_HYN75BGXX:1:11112:25043:18797#CTCTCT/2')
old_hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11112:25043:18797#CTCTCT/2')
old_hit_list.add_hit(hit)
read.hit_list = old_hit_list
# print ('* test2_10: 17 hits with 1 function, case 2.5*')
new_hits = ['NS500496_240_HYN75BGXX:1:11112:25043:18797#CTCTCT/2|3|125 kegg|nio:NITINOP_1721 58.5 41 17 311 1 123 271 311 1.0e-02 43.9',
'NS500496_240_HYN75BGXX:1:11112:25043:18797#CTCTCT/2|3|125 kegg|mgot:MgSA37_03614 58.5 41 17 128 1 123 88 128 1.4e-02 43.5',
'NS500496_240_HYN75BGXX:1:11112:25043:18797#CTCTCT/2|3|125 kegg|lfc:LFE_0874 58.5 41 17 127 1 123 87 127 1.4e-02 43.5',
'NS500496_240_HYN75BGXX:1:11112:25043:18797#CTCTCT/2|3|125 fig|269799.8.peg.645 53.7 41 19 127 1 123 87 127 1.8e-02 43.1',
'NS500496_240_HYN75BGXX:1:11112:25043:18797#CTCTCT/2|3|125 fig|653733.4.peg.1965 58.5 41 17 126 1 123 86 126 1.8e-02 43.1',
'NS500496_240_HYN75BGXX:1:11112:25043:18797#CTCTCT/2|3|125 kegg|gbe:GbCGDNIH1_0546 56.1 41 18 125 1 123 85 125 1.8e-02 43.1'
]
hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11112:25043:18797#CTCTCT/2|3|125')
for new_hit in new_hits:
hit = DiamondHit()
hit.create_hit(new_hit.split('\t'))
hit.annotate_hit(self.parser.ref_data)
hit_list.add_hit(hit)
compare_hits_erpk_lca(read, 3, 125, hit_list, self.parser.config.get_biscore_range_cutoff(self.parser.collection), 15, 150, self.parser.taxonomy_data, self.parser.ref_data)
# print('Read status:', read.status)
# print('Read function:', read.functions)
self.assertEqual(read.status, STATUS_BAD)
self.assertEqual(len(read.functions), 0)
self.assertEqual(read.taxonomy, None)
def test_2_compare_hits_2(self):
# test 2 hits with 1 function, case 1.2
hit = DiamondHit()
hit.import_hit('NS500496_240_HYN75BGXX:1:11101:10772:2071#CTCTCT/1 fig|485913.3.peg.8591 87.9 33 4 101 100 2 1 33 1.1e-09 58.5 UreA'.split('\t'))
read = AnnotatedRead('NS500496_240_HYN75BGXX:1:11101:10772:2071#CTCTCT/1')
old_hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:10772:2071#CTCTCT/1')
old_hit_list.add_hit(hit)
read.hit_list = old_hit_list
print ('*test_2_compare_hits_2: test 2 hits with 1 function, case 1.2 *')
new_hits = ['NS500496_240_HYN75BGXX:1:11101:10772:2071#CTCTCT/1|100|2 fig|316274.7.peg.2519 87.9 33 4 101 99 1 1 33 2.1e-07 58.9'
]
hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:10772:2071#CTCTCT/1|100|2')
for new_hit in new_hits:
hit = DiamondHit()
hit.create_hit(new_hit.split('\t'))
hit.annotate_hit(self.parser.ref_data)
hit_list.add_hit(hit)
self.assertEqual(read.functions['UreA'], 0.0)
compare_hits_erpk_lca(read, 100, 2, hit_list, self.parser.config.get_biscore_range_cutoff(self.parser.collection), 15, 150, self.parser.taxonomy_data, self.parser.ref_data)
# print('Read status:', read.status)
# print('Read function:', read.functions)
self.assertEqual(read.status, STATUS_GOOD)
self.assertEqual(len(read.functions), 1)
self.assertEqual(read.functions['UreA'], get_erpk_score(101, 150, 15))
self.assertEqual(read.taxonomy, '65')
def test_2_compare_hits_5(self):
# test 7 hits, two functions, case 2.1
hit = DiamondHit()
hit.import_hit('NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1 fig|1121378.3.peg.2960 76.0 50 12 231 150 1 23 72 9.0e-15 75.5 UreA|UreB'.split('\t'))
read = AnnotatedRead('NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1')
old_hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1')
old_hit_list.add_hit(hit)
read.hit_list = old_hit_list
print ('* test_2_compare_hits_5: test 7 hits with 2 functions, case 2.1*')
new_hits = ['NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1121378.3.peg.2960 76.0 50 12 231 150 1 23 72 3.3e-12 75.5',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 kegg|hco:LOKO_03690 72.0 50 14 100 150 1 23 72 4.3e-12 75.1',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1160705.3.peg.7402 72.0 50 14 236 150 1 159 208 4.3e-12 75.1',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1156841.3.peg.6425 74.0 50 13 100 150 1 23 72 4.3e-12 75.1',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 kegg|masw:AM586_12165 74.0 50 13 100 150 1 23 72 5.6e-12 74.7',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1203460.3.peg.2591 72.0 50 14 100 150 1 23 72 5.6e-12 74.7',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1121943.4.peg.3735 72.0 50 14 100 150 1 23 72 5.6e-12 74.7',
]
hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1')
for new_hit in new_hits:
hit = DiamondHit()
hit.create_hit(new_hit.split('\t'))
hit.annotate_hit(self.parser.ref_data)
hit_list.add_hit(hit)
compare_hits_erpk_lca(read, 150, 1, hit_list, self.parser.config.get_biscore_range_cutoff(self.parser.collection), 15, 150, self.parser.taxonomy_data, self.parser.ref_data)
# print('Read status:', read.get_status())
# print('Read function:', read.get_functions())
self.assertEqual(read.status, STATUS_GOOD)
self.assertEqual(len(read.functions), 1)
self.assertEqual(read.functions['UreA'], get_erpk_score(231, 150, 15))
self.assertEqual(read.taxonomy, '2')
def test_3_protein_taxonomy(self):
self.project.import_reads_json(sample, ENDS)
protein = 'D16-4706_contig_11213_7'
print('D16-4706_contig_11213_7 taxonomy')
print(self.project.samples[sample].reads[end][protein].taxonomy)
parser = DiamondParser(config=self.project.config,
options=self.project.options,
taxonomy_data=self.project.taxonomy_data,
ref_data=self.project.ref_data,
sample=self.project.samples[sample],
end=end)
parser.parse_reference_output()
print(str(parser.reads[protein]))
# parse_background_output(parser)
hit_line = 'D16-4706_contig_11213_7|4|257 fig|408672.3.peg.2637 63.0 254 94 256 1 254 2 255 1.1e-97 362.1'
hit = DiamondHit()
hit.create_hit(tabular_output_fields=hit_line.split('\t'))
hit_list = DiamondHitList('D16-4706_contig_11213_7|4|257')
hit_list.add_hit(hit)
hit_list.annotate_hits(self.project.ref_data)
hit_list.filter_list_by_identity(self.project.ref_data)
print('hit_list')
print(hit_list)
compare_protein_hits_lca(parser.reads[protein], 4, 257, hit_list, 0.03, 1.0, 1.0, self.project.taxonomy_data, self.project.ref_data)
print(parser.reads[protein].taxonomy)
self.assertEqual(parser.reads[protein].taxonomy, '408672')
def decode_assembly(obj):
"""Custom JSON decoder for Sample object
Args:
obj (obj): GeneAssembly object to decode
"""
if '__DiamondHitList__' in obj:
diamond_hit_list = DiamondHitList()
diamond_hit_list.__dict__.update(obj['__DiamondHitList__'])
return diamond_hit_list
elif '__DiamondHit__' in obj:
diamond_hit = DiamondHit()
diamond_hit.__dict__.update(obj['__DiamondHit__'])
return diamond_hit
elif '__Contig__' in obj:
contig = Contig()
contig.__dict__.update(obj['__Contig__'])
return contig
elif '__Gene__' in obj:
gene = Gene()
gene.__dict__.update(obj['__Gene__'])
return gene
elif '__GeneAssembly__' in obj:
gene_assembly = GeneAssembly()
gene_assembly.__dict__.update(obj['__GeneAssembly__'])
return gene_assembly
return obj
def import_hit_list(self):
"""Imports tab-separated table of DAIMOND hits. Use for resuming
analysis after Fama restart
Returns:
:obj:dict[str, :obj:AnnotatedRead]
"""
infile = os.path.join(os.path.join(self.sample.work_directory,
self.sample.sample_id + '_'
+ self.end + '_'
+ self.options.ref_hits_list_name))
ret_val = {}
hit_list = None
current_read_id = None
with open(infile, 'r', newline='') as infile:
tsvin = csv.reader(infile, delimiter='\t')
for row in tsvin:
if current_read_id is None:
# initialize
current_read_id = row[0]
hit_list = DiamondHitList(current_read_id)
elif current_read_id != row[0]:
ret_val[current_read_id] = AnnotatedRead(current_read_id)
ret_val[current_read_id].hit_list = hit_list
current_read_id = row[0]
hit_list = DiamondHitList(current_read_id)
hit = DiamondHit()
hit.import_hit(row)
hit_list.add_hit(hit)
ret_val[current_read_id] = AnnotatedRead(current_read_id)
ret_val[current_read_id].hit_list = hit_list
return ret_val
def test_2_compare_hits_4(self):
# test hit with two functions
hit = DiamondHit()
hit.import_hit('NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1 fig|1121378.3.peg.2960 76.0 50 12 231 150 1 23 72 9.0e-15 75.5 UreA|UreB'.split('\t'))
read = AnnotatedRead('NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1')
old_hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1')
old_hit_list.add_hit(hit)
read.hit_list = old_hit_list
# test 20 hits, one function
print ('*test_2_compare_hits_4: test 20 hits with 2 functions, case 2.1*')
new_hits = ['NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1121378.3.peg.2960 76.0 50 12 231 150 1 23 72 3.3e-12 75.5',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 kegg|hco:LOKO_03690 72.0 50 14 100 150 1 23 72 4.3e-12 75.1',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1160705.3.peg.7402 72.0 50 14 236 150 1 159 208 4.3e-12 75.1',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1156841.3.peg.6425 74.0 50 13 100 150 1 23 72 4.3e-12 75.1',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 kegg|masw:AM586_12165 74.0 50 13 100 150 1 23 72 5.6e-12 74.7',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1203460.3.peg.2591 72.0 50 14 100 150 1 23 72 5.6e-12 74.7',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1121943.4.peg.3735 72.0 50 14 100 150 1 23 72 5.6e-12 74.7',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 kegg|samb:SAM23877_1321 72.0 50 14 100 150 1 23 72 7.3e-12 74.3',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|100226.15.peg.1235 72.0 50 14 100 150 1 23 72 7.3e-12 74.3',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|290398.11.peg.2325 72.0 50 14 100 150 1 23 72 7.3e-12 74.3',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1000565.3.peg.3274 72.0 50 14 100 150 1 23 72 9.6e-12 73.9',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 kegg|hhu:AR456_08480 68.0 50 16 100 150 1 23 72 1.3e-11 73.6',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1126229.3.peg.323 70.0 50 15 100 150 1 23 72 1.3e-11 73.6',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1155714.3.peg.3022 70.0 50 15 100 150 1 23 72 1.3e-11 73.6',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1155716.3.peg.3618 72.0 50 14 100 150 1 23 72 1.3e-11 73.6',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1155718.3.peg.3182 68.0 50 16 100 150 1 23 72 1.3e-11 73.6',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|591167.6.peg.5739 70.0 50 15 100 150 1 23 72 1.3e-11 73.6',
'NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1 fig|1054862.3.peg.1097 72.0 50 14 103 150 1 26 75 1.3e-11 73.6'
]
hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9189:2106#CTCTCT/1|150|1')
for new_hit in new_hits:
hit = DiamondHit()
hit.create_hit(new_hit.split('\t'))
hit.annotate_hit(self.parser.ref_data)
hit_list.add_hit(hit)
compare_hits_erpk_lca(read, 150, 1, hit_list, self.parser.config.get_biscore_range_cutoff(self.parser.collection), 15, 150, self.parser.taxonomy_data, self.parser.ref_data)
# print('268 Read status:', read.get_status())
# print('269 Read function:', read.get_functions())
self.assertEqual(read.status, STATUS_GOOD)
self.assertEqual(len(read.functions), 1)
self.assertEqual(read.functions['UreA'], get_erpk_score(231, 150, 15))
self.assertEqual(read.taxonomy, '2')
def test_2_compare_hits_7(self):
# test hit with one function and many close homologs, case 2.2
hit = DiamondHit()
hit.import_hit('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1 fig|363754.4.peg.84 88.0 50 6 570 1 150 270 319 7.6e-22 99.0 UreC'.split('\t'))
read = AnnotatedRead('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1')
old_hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1')
old_hit_list.add_hit(hit)
read.hit_list = old_hit_list
# test 20 hits, one function
print ('* test 17 hits with 1 function, case 2.2*')
new_hits = ['NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|266835.9.peg.3902 88.0 50 6 570 1 150 270 319 2.8e-19 99.0',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|363754.4.peg.84 90.0 50 5 590 1 150 290 339 4.7e-19 98.2',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|411684.3.peg.2730 88.0 50 6 570 1 150 270 319 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|176299.10.peg.2410 90.0 50 5 569 1 150 269 318 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|maad:AZF01_14085 86.0 50 7 570 1 150 270 319 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|266834.11.peg.3959 88.0 50 6 570 1 150 270 319 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|six:BSY16_122 88.0 50 6 568 1 150 269 318 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1144306.3.peg.717 86.0 50 7 569 1 150 269 318 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|meso:BSQ44_05880 88.0 50 6 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|118163.3.peg.2804 90.0 50 5 565 1 150 266 315 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|244592.3.peg.2201 90.0 50 5 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1150469.3.peg.1765 90.0 50 5 583 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|don:BSK21_03675 90.0 50 5 566 1 150 269 318 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1048680.4.peg.3848 86.0 50 7 569 1 150 269 318 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|311402.9.peg.5014 86.0 50 7 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|hoe:IMCC20628_02897 88.0 50 6 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|744979.4.peg.2070 88.0 50 6 570 1 150 270 319 8.1e-19 97.4'
]
hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150')
for new_hit in new_hits:
hit = DiamondHit()
hit.create_hit(new_hit.split('\t'))
hit.annotate_hit(self.parser.ref_data)
hit_list.add_hit(hit)
compare_hits_erpk_lca(read, 1, 150, hit_list, self.parser.config.get_biscore_range_cutoff(self.parser.collection), 15, 150, self.parser.taxonomy_data, self.parser.ref_data)
# print('Read status:', read.get_status())
# print('Read function:', read.get_functions())
self.assertEqual(read.status, STATUS_GOOD)
self.assertEqual(len(read.functions), 1)
self.assertEqual(read.functions['UreC'], get_erpk_score(570, 150, 15))
self.assertEqual(read.taxonomy, '28211')
def test_2_compare_hits_8(self):
# test hit with one function and many close homologs, case 2.4
hit = DiamondHit()
hit.import_hit('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1 fig|363754.4.peg.84 88.0 50 6 570 1 150 270 319 7.6e-22 99.0 UreC'.split('\t'))
read = AnnotatedRead('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1')
old_hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1')
old_hit_list.add_hit(hit)
read.hit_list = old_hit_list
# test 20 hits, one function, case 2.4
print ('* test2_8: 17 hits with 1 function, case 2.4*')
new_hits = ['NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id1 88.0 50 6 570 1 150 270 319 2.8e-19 99.0',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id2 90.0 50 5 590 1 150 290 339 4.7e-19 98.2',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id3 88.0 50 6 570 1 150 270 319 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id4 90.0 50 5 569 1 150 269 318 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id5 86.0 50 7 570 1 150 270 319 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id6 88.0 50 6 570 1 150 270 319 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id7 88.0 50 6 568 1 150 269 318 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id8 86.0 50 7 569 1 150 269 318 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id9 88.0 50 6 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id10 90.0 50 5 565 1 150 266 315 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id11 90.0 50 5 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id12 90.0 50 5 583 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id13 90.0 50 5 566 1 150 269 318 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id14 86.0 50 7 569 1 150 269 318 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id15 86.0 50 7 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id16 88.0 50 6 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fake_id17 88.0 50 6 570 1 150 270 319 8.1e-19 97.4'
]
hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150')
for new_hit in new_hits:
hit = DiamondHit()
hit.create_hit(new_hit.split('\t'))
hit.annotate_hit(self.parser.ref_data)
hit_list.add_hit(hit)
compare_hits_erpk_lca(read, 1, 150, hit_list, self.parser.config.get_biscore_range_cutoff(self.parser.collection), 15, 150, self.parser.taxonomy_data, self.parser.ref_data)
# print('Read status:', read.get_status())
# print('Read function:', read.get_functions())
self.assertEqual(read.status, STATUS_BAD)
self.assertEqual(len(read.functions), 0)
self.assertEqual(read.taxonomy, None)
def decode_reads(obj):
"""Custom JSON decoder for AnnotatedRead object
Args:
obj (obj): AnnotatedRead object to decode
"""
if '__AnnotatedRead__' in obj:
annotated_read = AnnotatedRead()
annotated_read.__dict__.update(obj['__AnnotatedRead__'])
return annotated_read
elif '__DiamondHitList__' in obj:
diamond_hit_list = DiamondHitList()
diamond_hit_list.__dict__.update(obj['__DiamondHitList__'])
return diamond_hit_list
elif '__DiamondHit__' in obj:
diamond_hit = DiamondHit()
diamond_hit.__dict__.update(obj['__DiamondHit__'])
return diamond_hit
return obj
def test_2_compare_hits_3(self):
# test 3 hits with 1 function, case 1.3
hit = DiamondHit()
hit.import_hit('NS500496_240_HYN75BGXX:1:11101:10772:2071#CTCTCT/1 fig|485913.3.peg.8591 87.9 33 4 101 100 2 1 33 1.1e-09 58.5 UreA'.split('\t'))
read = AnnotatedRead('NS500496_240_HYN75BGXX:1:11101:10772:2071#CTCTCT/1')
old_hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:10772:2071#CTCTCT/1')
old_hit_list.add_hit(hit)
read.hit_list = old_hit_list
print ('* test 1 hit with 1 function, case 1.3 *')
new_hits = ['NS500496_240_HYN75BGXX:1:11101:10772:2071#CTCTCT/1|100|2 fake_id 87.9 33 4 101 99 1 1 33 2.1e-07 58.9'
]
hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:10772:2071#CTCTCT/1|100|2')
for new_hit in new_hits:
hit = DiamondHit()
hit.create_hit(new_hit.split('\t'))
hit.annotate_hit(self.parser.ref_data)
hit_list.add_hit(hit)
compare_hits_erpk_lca(read, 100, 2, hit_list, self.parser.config.get_biscore_range_cutoff(self.parser.collection), 15, 150, self.parser.taxonomy_data, self.parser.ref_data)
# print('Read status:', read.get_status())
# print('Read function:', read.get_functions())
self.assertEqual(read.status, STATUS_BAD)
self.assertEqual(len(read.functions), 0)
self.assertEqual(read.taxonomy, None)
def decode_sample(obj):
"""Custom JSON decoder for Sample object
Args:
obj (obj): Sample object to decode
"""
if '__Sample__' in obj:
sample = Sample()
sample.__dict__.update(obj['__Sample__'])
return sample
elif '__AnnotatedRead__' in obj:
annotated_read = AnnotatedRead()
annotated_read.__dict__.update(obj['__AnnotatedRead__'])
return annotated_read
elif '__DiamondHitList__' in obj:
diamond_hit_list = DiamondHitList()
diamond_hit_list.__dict__.update(obj['__DiamondHitList__'])
return diamond_hit_list
elif '__DiamondHit__' in obj:
diamond_hit = DiamondHit()
diamond_hit.__dict__.update(obj['__DiamondHit__'])
return diamond_hit
return obj
def parse_background_output(self):
"""Reads and processes DIAMOND tabular output of the classification
DIAMOND search.
Note: this function takes existing list of hits and compares each
of them with results of new similarity serach (against classification DB).
For the comparison, it calls compare_hits_lca function.
"""
tsvfile = os.path.join(self.assembly_dir,
'all_contigs_' + self.project.options.background_output_name)
current_query_id = None
hit_list = None
length_cutoff = self.project.config.get_length_cutoff(
self.project.options.get_collection())
biscore_range_cutoff = self.project.config.get_biscore_range_cutoff(
self.project.options.get_collection())
print('Relative bit-score cutoff: ', biscore_range_cutoff,
', Length cutoff: ', length_cutoff)
average_coverage = self.assembly.calculate_average_coverage()
with open(tsvfile, 'r', newline='') as infile:
tsvin = csv.reader(infile, delimiter='\t')
function_id = ''
contig_id = ''
gene_id = ''
coverage = ''
for row in tsvin:
if current_query_id is None:
current_query_id = row[0]
hit_list = DiamondHitList(current_query_id)
hit = DiamondHit()
hit.create_hit(row)
# filtering by identity and length
if hit.length < length_cutoff:
continue # skip this hit
if hit.query_id != current_query_id:
hit_list.annotate_hits(self.project.ref_data)
hit_list.filter_list_by_identity(self.project.ref_data)
# compare list of hits from search in background DB with existing
# hit from search in reference DB
current_query_id_tokens = current_query_id.split('|')
function_id = current_query_id_tokens[0]
contig_id = '_'.join(current_query_id_tokens[1].split('_')[:-1])
gene_id = '|'.join(current_query_id_tokens[:-2])
coverage = self.assembly.contigs[function_id][contig_id].get_coverage()
try:
compare_protein_hits_lca(
self.assembly.contigs[function_id][contig_id].genes[gene_id],
int(current_query_id_tokens[-2]), # hit_start
int(current_query_id_tokens[-1]), # hit_end
hit_list,
biscore_range_cutoff,
coverage,
average_coverage,
self.project.taxonomy_data,
self.project.ref_data
)
except KeyError:
print(' '.join(['Gene not found:', gene_id, 'in', function_id, contig_id]))
current_query_id = hit.query_id
hit_list = DiamondHitList(current_query_id)
hit_list.add_hit(hit)
hit_list.annotate_hits(self.project.ref_data)
hit_list.filter_list_by_identity(self.project.ref_data)
current_query_id_tokens = current_query_id.split('|')
function_id = current_query_id_tokens[0]
contig_id = '_'.join(current_query_id_tokens[1].split('_')[:-1])
gene_id = '|'.join(current_query_id_tokens[:-2])
coverage = self.assembly.contigs[function_id][contig_id].get_coverage()
try:
compare_protein_hits_lca(
self.assembly.contigs[function_id][contig_id].genes[gene_id],
int(current_query_id_tokens[-2]), # hit_start
int(current_query_id_tokens[-1]), # hit_end
hit_list,
biscore_range_cutoff,
coverage,
average_coverage,
self.project.taxonomy_data,
self.project.ref_data
)
except KeyError:
print(' '.join(['Gene not found:', gene_id, 'in', function_id, contig_id]))
def parse_reference_output(self):
"""Reads and processes DIAMOND tabular output of the preselection
DIAMOND search.
Note: this function finds query sequences similar to reference
proteins. Since a query sequence may have more than one areas of
similarity (for instance, in fusion proteins of two subunits or
in multi-domain proteins), it will try to find as many such areas
as possible.
DIAMOND hits are filtered by two parameters: length of alignment
and amino acid identity %, which are defined in program config ini.
"""
tsvfile = os.path.join(self.assembly_dir,
'all_contigs_' + self.project.options.ref_output_name)
current_id = ''
hit_list = DiamondHitList(current_id)
identity_cutoff = self.project.config.get_identity_cutoff(
self.project.options.get_collection())
length_cutoff = self.project.config.get_length_cutoff(
self.project.options.get_collection())
print('Parse reference output: Identity cutoff: ',
identity_cutoff,
', Length cutoff: ',
length_cutoff)
with open(tsvfile, 'r', newline='') as infile:
tsvin = csv.reader(infile, delimiter='\t')
for row in tsvin:
hit = DiamondHit()
hit.create_hit(row)
# filtering by identity and length
if hit.identity < identity_cutoff:
continue # skip this line
if hit.length < length_cutoff:
continue # skip this line
if hit.query_id != current_id:
# filter list for overlapping hits
hit_list.filter_list(self.project.config.get_overlap_cutoff(
self.project.options.get_collection()))
if hit_list.hits_number != 0:
# annotate_hits
hit_list.annotate_hits(self.project.ref_data)
function_id, contig_id, _ = parse_gene_id(current_id)
self.assembly.contigs[function_id][contig_id].\
genes[current_id].hit_list = hit_list
current_id = hit.query_id
hit_list = DiamondHitList(current_id)
hit_list.add_hit(hit)
hit_list.filter_list(
self.project.config.get_overlap_cutoff(self.project.options.get_collection()))
if hit_list.hits_number != 0:
# annotate_hits
hit_list.annotate_hits(self.project.ref_data)
function_id, contig_id, _ = parse_gene_id(current_id)
self.assembly.contigs[function_id][contig_id].genes[current_id].hit_list = \
hit_list
def test_2_compare_hits_6(self):
# test hit with one function and many close homologs, case 2.1
hit = DiamondHit()
hit.import_hit('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1 fig|363754.4.peg.84 88.0 50 6 570 1 150 270 319 7.6e-22 99.0 UreC'.split('\t'))
read = AnnotatedRead('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1')
old_hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1')
old_hit_list.add_hit(hit)
read.hit_list = old_hit_list
# test 20 hits, one function
print ('* test_2_compare_hits_6: test 40 hits with 1 function, case 2.1*')
new_hits = ['NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|363754.4.peg.84 88.0 50 6 570 1 150 270 319 2.8e-19 99.0',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|266835.9.peg.3902 90.0 50 5 590 1 150 290 339 4.7e-19 98.2',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|411684.3.peg.2730 88.0 50 6 570 1 150 270 319 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|176299.10.peg.2410 90.0 50 5 569 1 150 269 318 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|maad:AZF01_14085 86.0 50 7 570 1 150 270 319 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|266834.11.peg.3959 88.0 50 6 570 1 150 270 319 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|six:BSY16_122 88.0 50 6 568 1 150 269 318 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1144306.3.peg.717 86.0 50 7 569 1 150 269 318 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|meso:BSQ44_05880 88.0 50 6 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|118163.3.peg.2804 90.0 50 5 565 1 150 266 315 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|244592.3.peg.2201 90.0 50 5 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1150469.3.peg.1765 90.0 50 5 583 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|don:BSK21_03675 90.0 50 5 566 1 150 269 318 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1048680.4.peg.3848 86.0 50 7 569 1 150 269 318 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|311402.9.peg.5014 86.0 50 7 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|hoe:IMCC20628_02897 88.0 50 6 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|744979.4.peg.2070 88.0 50 6 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1123256.3.peg.2564 90.0 50 5 570 1 150 270 319 1.1e-18 97.1',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|labr:CHH27_19355 90.0 50 5 570 1 150 270 319 1.1e-18 97.1',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1156935.5.peg.1846 86.0 50 7 570 1 150 270 319 1.1e-18 97.1',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|314231.3.peg.911 90.0 50 5 570 1 150 270 319 1.1e-18 97.1',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|216596.11.peg.5042 86.0 50 7 570 1 150 270 319 1.1e-18 97.1',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|292564.3.peg.2428 88.0 50 6 574 1 150 270 319 1.1e-18 97.1',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1122218.3.peg.2653 88.0 50 6 570 1 150 270 319 1.4e-18 96.7',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|633131.3.peg.1456 88.0 50 6 586 1 150 287 336 1.4e-18 96.7',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|375451.14.peg.3633 88.0 50 6 569 1 150 270 319 1.4e-18 96.7',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|391593.3.peg.1570 88.0 50 6 569 1 150 270 319 1.4e-18 96.7',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1120961.3.peg.1492 86.0 50 7 570 1 150 270 319 1.8e-18 96.3',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|756067.3.peg.5652 88.0 50 6 581 1 150 266 315 1.8e-18 96.3',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|640510.4.peg.718 88.0 50 6 568 1 150 269 318 1.8e-18 96.3',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|272129.4.peg.175 88.0 50 6 452 1 150 266 315 1.8e-18 96.3',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|197221.4.peg.4 88.0 50 6 572 1 150 270 319 1.8e-18 96.3',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|314256.5.peg.1029 88.0 50 6 569 1 150 270 319 1.8e-18 96.3',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|313624.3.peg.4907 88.0 50 6 568 1 150 270 319 1.8e-18 96.3',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|402777.3.peg.1444 88.0 50 6 601 1 150 270 319 1.8e-18 96.3',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|179408.3.peg.7446 88.0 50 6 603 1 150 266 315 1.8e-18 96.3',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|643473.3.peg.1780 88.0 50 6 564 1 150 266 315 1.8e-18 96.3',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1173263.3.peg.2622 86.0 50 7 565 1 150 266 315 2.4e-18 95.9',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|391038.7.peg.2407 88.0 50 6 568 1 150 269 318 2.4e-18 95.9',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|103690.10.peg.4352 88.0 50 6 568 1 150 270 319 2.4e-18 95.9'
]
hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150')
for new_hit in new_hits:
hit = DiamondHit()
hit.create_hit(new_hit.split('\t'))
hit.annotate_hit(self.parser.ref_data)
hit_list.add_hit(hit)
compare_hits_erpk_lca(read, 1, 150, hit_list, self.parser.config.get_biscore_range_cutoff(self.parser.collection), 15, 150, self.parser.taxonomy_data, self.parser.ref_data)
# print('Read status:', read.get_status())
# print('Read function:', read.get_functions())
self.assertEqual(read.status, STATUS_GOOD)
self.assertEqual(len(read.functions), 1)
self.assertEqual(read.functions['UreC'], get_erpk_score(570, 150, 15))
self.assertEqual(read.taxonomy, '2')
def test_2_compare_hits_11(self):
# read with two hits
hit1 = DiamondHit()
hit1.import_hit('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1 fig|363754.4.peg.84 88.0 50 6 570 1 150 270 319 7.6e-22 99.0 UreC'.split('\t'))
hit2 = DiamondHit()
hit2.import_hit('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1 fig|485913.3.peg.8591 87.9 33 4 101 100 2 1 33 1.1e-09 58.5 UreA'.split('\t'))
read = AnnotatedRead('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1')
old_hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1')
old_hit_list.add_hit(hit1)
old_hit_list.add_hit(hit2)
read.hit_list = old_hit_list
print ('* test read with 2 hits *')
new_hits = ['NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|100|2 fig|485913.3.peg.8591 87.9 33 4 101 99 1 1 33 2.1e-07 58.9',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|100|2 kegg|cap:CLDAP_03170 81.8 33 6 100 99 1 1 33 1.4e-06 56.2',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|100|2 fig|316274.7.peg.2519 78.8 33 7 100 99 1 1 33 6.8e-06 53.9'
]
hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|100|2')
for new_hit in new_hits:
hit = DiamondHit()
hit.create_hit(new_hit.split('\t'))
hit.annotate_hit(self.parser.ref_data)
hit_list.add_hit(hit)
compare_hits_erpk_lca(read, 100, 2, hit_list, self.parser.config.get_biscore_range_cutoff(self.parser.collection), 15, 150, self.parser.taxonomy_data, self.parser.ref_data)
new_hits = ['NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|266835.9.peg.3902 88.0 50 6 570 1 150 270 319 2.8e-19 99.0',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|363754.4.peg.84 90.0 50 5 590 1 150 290 339 4.7e-19 98.2',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|411684.3.peg.2730 88.0 50 6 570 1 150 270 319 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|176299.10.peg.2410 90.0 50 5 569 1 150 269 318 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|maad:AZF01_14085 86.0 50 7 570 1 150 270 319 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|266834.11.peg.3959 88.0 50 6 570 1 150 270 319 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|six:BSY16_122 88.0 50 6 568 1 150 269 318 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1144306.3.peg.717 86.0 50 7 569 1 150 269 318 6.2e-19 97.8',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|meso:BSQ44_05880 88.0 50 6 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|244592.3.peg.2201 90.0 50 5 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1150469.3.peg.1765 90.0 50 5 583 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|don:BSK21_03675 90.0 50 5 566 1 150 269 318 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|1048680.4.peg.3848 86.0 50 7 569 1 150 269 318 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|311402.9.peg.5014 86.0 50 7 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 kegg|hoe:IMCC20628_02897 88.0 50 6 570 1 150 270 319 8.1e-19 97.4',
'NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150 fig|744979.4.peg.2070 88.0 50 6 570 1 150 270 319 8.1e-19 97.4'
]
hit_list = DiamondHitList('NS500496_240_HYN75BGXX:1:11101:9460:3085#CTCTCT/1|1|150')
for new_hit in new_hits:
hit = DiamondHit()
hit.create_hit(new_hit.split('\t'))
hit.annotate_hit(self.parser.ref_data)
hit_list.add_hit(hit)
compare_hits_erpk_lca(read, 1, 150, hit_list, self.parser.config.get_biscore_range_cutoff(self.parser.collection), 15, 150, self.parser.taxonomy_data, self.parser.ref_data)
# print('Read status:', read.status)
# print('Read function:', read.functions)
# print('Read hits:', read.show_hits())
self.assertEqual(read.status, STATUS_GOOD)
self.assertEqual(len(read.functions), 2)
self.assertEqual(read.functions['UreA'], get_erpk_score(101, 150, 15))
self.assertEqual(read.taxonomy, '28211')
def parse_background_output(parser):
"""Reads and processes DIAMOND tabular output of the second DIAMOND
search.
Args:
parser (:obj:DiamondParser): parser object
Note: this function takes existing list of hits and compares each
of them with results of other similarity serach (against larger DB).
For the comparison, it calls compare_hits_lca function, which
in turn updates entries in the 'reads' dictionary.
Raises:
KeyError if read identifier not found in the 'reads' dictionary
"""
tsvfile = os.path.join(
parser.sample.work_directory, parser.sample.sample_id + '_' +
parser.end + '_' + parser.options.background_output_name)
coverage_data = load_coverage_data(parser)
total_coverage = 0.0
if coverage_data:
for contig_id in coverage_data.keys():
total_coverage += coverage_data[contig_id]
average_coverage = total_coverage / len(coverage_data)
else:
average_coverage = 1.0
current_query_id = None
_hit_list = None
length_cutoff = parser.config.get_length_cutoff(parser.collection)
biscore_range_cutoff = parser.config.get_biscore_range_cutoff(
parser.collection)
print('Relative bitscore cutoff: ', biscore_range_cutoff,
', Length cutoff: ', length_cutoff)
with open(tsvfile, 'r', newline='') as infile:
tsvin = csv.reader(infile, delimiter='\t')
for row in tsvin:
if current_query_id is None:
current_query_id = row[0]
_hit_list = DiamondHitList(current_query_id)
hit = DiamondHit()
hit.create_hit(row)
# filtering by length
if hit.length < length_cutoff:
continue
if hit.query_id != current_query_id:
_hit_list.annotate_hits(parser.ref_data)
_hit_list.filter_list_by_identity(parser.ref_data)
current_query_id_tokens = current_query_id.split('|')
protein_id = '|'.join(current_query_id_tokens[:-2])
hit_start = int(current_query_id_tokens[-2])
hit_end = int(current_query_id_tokens[-1])
# Coverage data can be used only if protein ID contains contig ID
contig_id = '_'.join(
protein_id.split(' # ')[0].split('_')[:-1])[1:]
coverage = 1.0
if coverage_data is not None and contig_id in coverage_data:
coverage = coverage_data[contig_id]
try:
compare_protein_hits_lca(parser.reads[protein_id],
hit_start, hit_end, _hit_list,
biscore_range_cutoff, coverage,
average_coverage,
parser.taxonomy_data,
parser.ref_data)
except KeyError:
print('Protein not found: ', protein_id)
current_query_id = hit.query_id
_hit_list = DiamondHitList(current_query_id)
_hit_list.add_hit(hit)
_hit_list.annotate_hits(parser.ref_data)
_hit_list.filter_list_by_identity(parser.ref_data)
current_query_id_tokens = current_query_id.split('|')
protein_id = '|'.join(current_query_id_tokens[:-2])
hit_start = int(current_query_id_tokens[-2])
hit_end = int(current_query_id_tokens[-1])
try:
# Coverage data can be used only if protein ID contains contig ID
contig_id = '_'.join(
protein_id.split(' # ')[0].split('_')[:-1])[1:]
coverage = 1.0
if coverage_data is not None and contig_id in coverage_data:
coverage = coverage_data[contig_id]
compare_protein_hits_lca(parser.reads[protein_id], hit_start,
hit_end, _hit_list, biscore_range_cutoff,
coverage, average_coverage,
parser.taxonomy_data, parser.ref_data)
except KeyError:
print('Protein not found: ', protein_id)
def parse_background_output(self):
"""Reads and processes DIAMOND tabular output of the second DIAMOND
search.
Note: this function takes existing list of hits and compares each
of them with results of other similarity serach (against larger DB).
For the comparison, it calls compare_hits_erpk_lca function, which
in turn updates entries in the 'reads' dictionary.
Raises:
KeyError if read identifier not found in the 'reads' dictionary
"""
if not self.reads:
# Something went wrong and 'reads' dictionary is empty.
# Let's try to import list of reads from file.
self.reads = self.import_hit_list()
tsvfile = os.path.join(
self.sample.work_directory,
self.sample.sample_id + '_' + self.end + '_' + self.options.background_output_name
)
average_read_length = self.sample.get_avg_read_length(self.end)
current_query_id = None
hit_list = None
length_cutoff = self.config.get_length_cutoff(self.collection)
bitscore_range_cutoff = self.config.get_biscore_range_cutoff(self.collection)
print('Relative bit-score cutoff:', bitscore_range_cutoff,
', Length cutoff:', length_cutoff
)
with open(tsvfile, 'r', newline='') as infile:
tsvin = csv.reader(infile, delimiter='\t')
for row in tsvin:
if current_query_id is None:
current_query_id = row[0]
hit_list = DiamondHitList(current_query_id)
hit = DiamondHit()
hit.create_hit(row)
# filtering by length
if hit.length < length_cutoff:
continue # skip this line
# when new query ID reached, process collected hits,
# then start over with new query identifier
if hit.query_id != current_query_id:
# assign functions to selected hits
hit_list.annotate_hits(self.ref_data)
hit_list.filter_list_by_identity(self.ref_data)
# extract initial read identifier from identifier of the hit
current_query_id_tokens = current_query_id.split('|')
read_id = '|'.join(current_query_id_tokens[:-2])
# compare list of hits from search in background DB
# with existing hit from the first similarity search
try:
compare_hits_erpk_lca(
self.reads[read_id],
int(current_query_id_tokens[-2]), # hit_start
int(current_query_id_tokens[-1]), # hit_end
hit_list, bitscore_range_cutoff, length_cutoff,
average_read_length, self.taxonomy_data, self.ref_data
)
except KeyError:
print('Read not found: ', read_id)
# starting over
current_query_id = hit.query_id
hit_list = DiamondHitList(current_query_id)
hit_list.add_hit(hit)
# when EOF reached, process collected hits
# assign functions to selected hits
hit_list.annotate_hits(self.ref_data)
hit_list.filter_list_by_identity(self.ref_data)
# extract initial read identifier from identifier of the hit
current_query_id_tokens = current_query_id.split('|')
read_id = '|'.join(current_query_id_tokens[:-2])
# compare list of hits from search in background DB with
# existing hit from the first similarity search
try:
compare_hits_erpk_lca(
self.reads[read_id],
int(current_query_id_tokens[-2]), # hit_start
int(current_query_id_tokens[-1]), # hit_end
hit_list, bitscore_range_cutoff, length_cutoff,
average_read_length, self.taxonomy_data, self.ref_data
)
except KeyError:
print('Read not found: ', read_id)
def parse_reference_output(self):
"""Reads and processes DIAMOND tabular output of the first DIAMOND
search.
Note: this function finds query sequences similar to reference
proteins. Since a query sequence may have more than one areas of
similarity (for instance, in fusion proteins of two subunits or
in multi-domain proteins), it will try to find as many such areas
as possible.
DIAMOND hits are filtered by two parameters: length of alignment
and amino acid identity %.
This function does not return anything. Instead, it populates
'reads' dictionary with AnnotatedRead objects.
"""
tsvfile = os.path.join(
self.options.get_project_dir(self.sample.sample_id),
self.sample.sample_id + '_' + self.end + '_' + self.options.ref_output_name
)
current_sequence_read_id = ''
hit_list = DiamondHitList(current_sequence_read_id)
# TODO: cleanup identity_cutoff = self.config.get_identity_cutoff(self.collection)
length_cutoff = self.config.get_length_cutoff(self.collection)
print('Length cutoff:', length_cutoff)
with open(tsvfile, 'r', newline='') as infile:
tsvin = csv.reader(infile, delimiter='\t')
for row in tsvin:
hit = DiamondHit()
(row[0], _) = parse_fastq_seqid(row[0])
hit.create_hit(row)
# filtering by length
if hit.length < length_cutoff:
continue # go to next hit
if hit.query_id != current_sequence_read_id:
# when new query ID reached, process collected hits,
# then start over with new query identifier
# filtering: remove overlapping hits
hit_list.filter_list(self.config.get_overlap_cutoff(self.collection))
# if any hits left, assign function to hits and populate reads dictionary
hit_list.annotate_hits(self.ref_data)
hit_list.filter_list_by_identity(self.ref_data)
if hit_list.hits_number != 0:
read = AnnotatedRead(current_sequence_read_id)
read.hit_list = hit_list
self.reads[current_sequence_read_id] = read
# start over
current_sequence_read_id = hit.query_id
hit_list = DiamondHitList(current_sequence_read_id)
hit_list.add_hit(hit)
# when EOF reached, process collected hits
hit_list.filter_list(self.config.get_overlap_cutoff(self.collection))
hit_list.annotate_hits(self.ref_data)
hit_list.filter_list_by_identity(self.ref_data)
if hit_list.hits_number != 0:
read = AnnotatedRead(current_sequence_read_id)
read.hit_list = hit_list
self.reads[current_sequence_read_id] = read
