def test_netmhcii_pan_multiple_alleles():
alleles = [
normalize_allele_name("HLA-DPA1*01:05-DPB1*100:01"),
normalize_allele_name("HLA-DQA1*05:11-DQB1*03:02"),
normalize_allele_name("HLA-DRB1*01:01")
]
ii_pan_predictor = NetMHCIIpan(
alleles=alleles,
epitope_lengths=[15, 16])
fasta_dictionary = {
"TP53-001": "SQAMDDLMLSPDDIEQWFTED"
}
epitope_collection = ii_pan_predictor.predict(
fasta_dictionary=fasta_dictionary)
unique_lengths = {x.length for x in epitope_collection}
eq_(unique_lengths, {15, 16})
unique_alleles = {x.allele for x in epitope_collection}
eq_(unique_alleles, {
"HLA-DPA1*01:05-DPB1*100:01",
"HLA-DQA1*05:11-DQB1*03:02",
"HLA-DRB1*01:01"
})
# length of "SQAMDDLMLSPDDIEQWFTED" is 21
# Expect 3 * ((21-15+1) + (21-16+1)) = 39 entries
assert len(epitope_collection) == 39, \
"Expected 39 epitopes from %s" % (epitope_collection,)
def test_macaque_alleles():
allele_name = "Mamu-B*082:02"
eq_(normalize_allele_name(allele_name), "Mamu-B*82:02")
eq_(compact_allele_name(allele_name), "B8202")
# expect 3rd zero in the family "007" to be trimmed in the normalized form
# of this allele
allele_name = "Mamu-B*007:02"
eq_(normalize_allele_name(allele_name), "Mamu-B*07:02")
eq_(compact_allele_name(allele_name), "B0702")
def test_mouse_class1_alleles_H2_Db():
# H2-Db
eq_(parse_allele_name("H2-Db"),
AlleleName("H-2", "D", "", "b"))
eq_(normalize_allele_name("H2-Db"), "H-2-Db")
eq_(compact_allele_name("H2-Db"), "Db")
# with hyphen in "H-2"
eq_(parse_allele_name("H-2-Db"),
AlleleName("H-2", "D", "", "b"))
eq_(normalize_allele_name("H-2-Db"), "H-2-Db")
eq_(compact_allele_name("H-2-Db"), "Db")
def test_mouse_class1_alleles_H2_Kk():
# H2-Kk
eq_(parse_allele_name("H2-Kk"),
AlleleName("H-2", "K", "", "k"))
eq_(normalize_allele_name("H2-Kk"), "H-2-Kk")
eq_(compact_allele_name("H-2-Kk"), "Kk")
# with a hyphen in "H-2"
eq_(parse_allele_name("H-2-Kk"),
AlleleName("H-2", "K", "", "k"))
eq_(normalize_allele_name("H-2-Kk"), "H-2-Kk")
eq_(compact_allele_name("H-2-Kk"), "Kk")
def test_mouse_class2_alleles():
# H2-IAb
eq_(parse_allele_name("H2-IAb"),
AlleleName("H-2", "IA", "", "b"))
eq_(normalize_allele_name("H2-IAb"), "H-2-IAb")
eq_(compact_allele_name("H2-IAb"), "IAb")
# with hyphen in "H-2"
eq_(parse_allele_name("H-2-IAb"),
AlleleName("H-2", "IA", "", "b"))
eq_(normalize_allele_name("H-2-IAb"), "H-2-IAb")
eq_(compact_allele_name("H-2-IAb"), "IAb")
def mhc_alleles_from_args(args):
alleles = [
normalize_allele_name(allele.strip())
for allele in args.mhc_alleles.split(",")
if allele.strip()
]
if args.mhc_alleles_file:
with open(args.mhc_alleles_file, 'r') as f:
for line in f:
line = line.strip()
if line:
alleles.append(normalize_allele_name(line))
if len(alleles) == 0:
raise ValueError(
"MHC alleles required (use --mhc-alleles or --mhc-alleles-file)")
return alleles
def test_netmhc_cons_chunking():
alleles = [normalize_allele_name(DEFAULT_ALLELE)]
fasta_dictionary = {
"SMAD4-001": "ASIINFKELA",
"TP53-001": "ASILLLVFYW",
"SMAD4-002": "ASIINFKELS",
"TP53-002": "ASILLLVFYS",
"TP53-003": "ASILLLVFYT",
"TP53-004": "ASILLLVFYG",
"TP53-005": "ASILLLVFYG"
}
for max_file_records in [1, 5, 20]:
for process_limit in [1, 2, 10]:
cons_predictor = NetMHCcons(
alleles=alleles,
epitope_lengths=[9],
max_file_records=max_file_records,
process_limit=process_limit
)
epitope_collection = cons_predictor.predict(
fasta_dictionary=fasta_dictionary)
assert len(epitope_collection) == 14, \
"Expected 14 epitopes from %s" % (epitope_collection,)
source_keys = []
for epitope in epitope_collection:
source_keys.append(epitope.source_sequence_key)
for fasta_key in fasta_dictionary.keys():
fasta_count = source_keys.count(fasta_key)
assert fasta_count == 2, \
("Expected each fasta key to appear twice, once for "
"each length, but saw %s %d time(s)" % (
fasta_key, fasta_count))
def test_human_class2_alpha_beta():
expected = "HLA-DPA1*01:05-DPB1*100:01"
expected_compact = "DPA10105-DPB110001"
for name in ["DPA10105-DPB110001",
"HLA-DPA1*01:05-DPB1*100:01",
"hla-dpa1*0105-dpb1*10001",
"dpa1*0105-dpb1*10001",
"HLA-DPA1*01:05/DPB1*100:01"]:
eq_(normalize_allele_name(name), expected)
eq_(compact_allele_name(name), expected_compact)
def test_wrapper_function():
alleles = [normalize_allele_name("HLA-A*02:01")]
wrapped_4 = NetMHC(alleles=alleles,
epitope_lengths=[9],
program_name="netMHC")
eq_(type(wrapped_4), NetMHC4)
wrapped_3 = NetMHC(alleles=alleles,
epitope_lengths=[9],
program_name="netMHC-3.4")
eq_(type(wrapped_3), NetMHC3)
def test_human_class2():
expected = "HLA-DRB1*01:02"
expected_compact = "DRB10102"
for name in ["DRB1_0102",
"DRB101:02",
"HLA-DRB1_0102",
"DRB10102",
"DRB1*0102",
"HLA-DRB1*0102",
"HLA-DRB1*01:02"]:
eq_(normalize_allele_name(name), expected)
eq_(compact_allele_name(name), expected_compact)
def run_class_with_executable(mhc_class, mhc_executable):
alleles = [normalize_allele_name("HLA-A*02:01")]
predictor = mhc_class(
alleles=alleles,
epitope_lengths=[9],
program_name=mhc_executable)
fasta_dictionary = {
"SMAD4-001": "ASIINFKELA",
"TP53-001": "ASILLLVFYW"
}
epitope_collection = predictor.predict(
fasta_dictionary=fasta_dictionary)
def test_netmhc_pan():
alleles = [normalize_allele_name(DEFAULT_ALLELE)]
pan_predictor = NetMHCpan(
alleles=alleles,
epitope_lengths=[9])
fasta_dictionary = {
"SMAD4-001": "ASIINFKELA",
"TP53-001": "ASILLLVFYW"
}
epitope_collection = pan_predictor.predict(
fasta_dictionary=fasta_dictionary)
assert len(epitope_collection) == 4, \
"Expected 4 epitopes from %s" % (epitope_collection,)
def test_netmhcii_pan_mouse():
alleles = [normalize_allele_name("H2-IAb")]
ii_pan_predictor = NetMHCIIpan(
alleles=alleles,
epitope_lengths=[15, 16])
fasta_dictionary = {
"SMAD4-001": "PAPAPSWPLSSSVPSQKTYQGSYGFRLGFLHSGT",
"TP53-001": "SQAMDDLMLSPDDIEQWFTED"
}
epitope_collection = ii_pan_predictor.predict(
fasta_dictionary=fasta_dictionary)
unique_lengths = {x.length for x in epitope_collection}
eq_(unique_lengths, {15, 16})
unique_alleles = {x.allele for x in epitope_collection}
eq_(unique_alleles, {"H-2-IAb"})
# length of "PAPAPSWPLSSSVPSQKTYQGSYGFRLGFLHSGT" is 34
# length of "SQAMDDLMLSPDDIEQWFTED" is 21
# Expect (34-15+1) + (34-16+1) + (21-15+1) + (21-16+1) = 52 entries
assert len(epitope_collection) == 52, \
"Expected 52 epitopes from %s" % (epitope_collection,)
def test_hla_long_names():
expected = "HLA-A*02:01"
for name in hla_02_01_names:
result = normalize_allele_name(name)
eq_(result, expected)
def test_wrapper_failure():
alleles = [normalize_allele_name("HLA-A*02:01")]
NetMHC(alleles=alleles,
epitope_lengths=[9],
program_name="netMHC-none")
