Newer
Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
import logging
logging.getLogger('matplotlib').disabled = True
logging.getLogger('tensorflow').disabled = True
import tempfile
import os
import pandas
from numpy.testing import assert_equal, assert_array_less, assert_array_equal
from mhcflurry import predict_scan_command
from mhcflurry.testing_utils import cleanup, startup
teardown = cleanup
setup = startup
from . import data_path
def test_fasta():
args = [
data_path("example.fasta"),
"--alleles",
"HLA-A*02:01,HLA-A*03:01,HLA-B*57:01,HLA-B*45:01,HLA-C*02:02,HLA-C*07:02",
]
deletes = []
try:
fd_out = tempfile.NamedTemporaryFile(delete=False, suffix=".csv")
deletes.append(fd_out.name)
full_args = args + ["--out", fd_out.name]
print("Running with args: %s" % full_args)
predict_scan_command.run(full_args)
result = pandas.read_csv(fd_out.name)
print(result)
assert not result.isnull().any().any()
finally:
for delete in deletes:
os.unlink(delete)
assert_equal(result.best_allele.nunique(), 6)
assert_equal(result.sequence_name.nunique(), 3)
assert_array_less(result.affinity_percentile, 2.0)
def test_fasta_50nm():
args = [
data_path("example.fasta"),
"--alleles",
"HLA-A*02:01,HLA-A*03:01,HLA-B*57:01,HLA-B*45:01,HLA-C*02:02,HLA-C*07:02",
"--results-filtered", "affinity",
"--threshold-affinity", "50",
]
deletes = []
try:
fd_out = tempfile.NamedTemporaryFile(delete=False, suffix=".csv")
deletes.append(fd_out.name)
full_args = args + ["--out", fd_out.name]
print("Running with args: %s" % full_args)
predict_scan_command.run(full_args)
result = pandas.read_csv(fd_out.name)
print(result)
assert not result.isnull().any().any()
finally:
for delete in deletes:
os.unlink(delete)
assert len(result) > 0
assert_array_less(result.affinity, 50)
def test_fasta_best():
args = [
data_path("example.fasta"),
"--alleles",
"HLA-A*02:01,HLA-A*03:01,HLA-B*57:01,HLA-B*45:01,HLA-C*02:02,HLA-C*07:02",
"--results-best", "affinity_percentile",
]
deletes = []
try:
fd_out = tempfile.NamedTemporaryFile(delete=False, suffix=".csv")
deletes.append(fd_out.name)
full_args = args + ["--out", fd_out.name]
print("Running with args: %s" % full_args)
predict_scan_command.run(full_args)
result = pandas.read_csv(fd_out.name)
print(result)
assert not result.isnull().any().any()
finally:
for delete in deletes:
os.unlink(delete)
assert len(result) > 0
assert_array_equal(
result.groupby(["sequence_name"]).peptide.count().values, 1)
def test_commandline_sequences():
args = [
"--sequences", "ASDFGHKL", "QWERTYIPCVNM",
"--alleles", "HLA-A0201,HLA-A0301", "H-2-Kb",
"--peptide-lengths", "8",
"--results-all",
]
deletes = []
try:
fd_out = tempfile.NamedTemporaryFile(delete=False, suffix=".csv")
deletes.append(fd_out.name)
full_args = args + ["--out", fd_out.name]
print("Running with args: %s" % full_args)
predict_scan_command.run(full_args)
result = pandas.read_csv(fd_out.name)
print(result)
finally:
for delete in deletes:
os.unlink(delete)
print(result)
assert_equal(result.sequence_name.nunique(), 2)
assert_equal(result.best_allele.nunique(), 3)
assert_equal(result.experiment_name.nunique(), 2)
assert_equal((result.peptide == "ASDFGHKL").sum(), 2)
assert_equal((result.peptide != "ASDFGHKL").sum(), 10)