def main(args_list=None):
if not args_list:
args_list = sys.argv[1:]
args = parse_args(parser, args_list)
print(args)
if args.hits_txt and len(args.hits_txt) > 0:
dataset = Dataset.from_peptides_text_files(args.hits_txt)
dataset = dataset.assemble_contigs()
else:
dataset = Dataset.from_csv(args.dataset_csv)
dataframes = []
for allele, allele_dataset in dataset.groupby_allele():
print("-- %s" % allele)
df = allele_dataset.to_dataframe()
netmhciipan = NetMHCIIpan([allele])
# pad peptides with alanines in case they're shorter than 9mer
peptides = ensure_peptide_lengths(df.peptide)
n_peptides = len(peptides)
binding_predictions = netmhciipan.predict_peptides(peptides)
ic50_pred = np.array([x.affinity for x in binding_predictions])
percentile_rank_pred = np.array(
[x.percentile_rank for x in binding_predictions])
assert len(ic50_pred) == n_peptides
assert len(percentile_rank_pred) == n_peptides
df["netmhciipan_ic50"] = ic50_pred
df["netmhciipan_percentile_rank"] = percentile_rank_pred
dataframes.append(df)
combined_df = pd.concat(dataframes)
combined_df.to_csv(args.output_csv, index=False)
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_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-DRA1*01:01-DRB1*01:01")
]
ii_pan_predictor = NetMHCIIpan(alleles=alleles)
fasta_dictionary = {"TP53-001": "SQAMDDLMLSPDDIEQWFTED"}
binding_predictions = ii_pan_predictor.predict_subsequences(
sequence_dict=fasta_dictionary, peptide_lengths=[15, 16])
unique_lengths = {x.length for x in binding_predictions}
eq_(unique_lengths, {15, 16})
unique_alleles = {x.allele for x in binding_predictions}
eq_(
unique_alleles, {
"HLA-DPA1*01:05-DPB1*100:01", "HLA-DQA1*05:11-DQB1*03:02",
"HLA-DRA1*01:01-DRB1*01:01"
})
# length of "SQAMDDLMLSPDDIEQWFTED" is 21
# Expect 3 * ((21-15+1) + (21-16+1)) = 39 entries
assert len(binding_predictions) == 39, \
"Expected 39 epitopes from %s" % (binding_predictions,)
def test_netmhcii_pan_mouse():
alleles = [normalize_allele_name("H2-IAb")]
ii_pan_predictor = NetMHCIIpan(alleles=alleles)
fasta_dictionary = {
"SMAD4-001": "PAPAPSWPLSSSVPSQKTYQGSYGFRLGFLHSGT",
"TP53-001": "SQAMDDLMLSPDDIEQWFTED"
}
binding_predictions = ii_pan_predictor.predict_subsequences(
sequence_dict=fasta_dictionary, peptide_lengths=[15, 16])
unique_lengths = {x.length for x in binding_predictions}
eq_(unique_lengths, {15, 16})
unique_alleles = {x.allele for x in binding_predictions}
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(binding_predictions) == 52, \
"Expected 52 epitopes from %s" % (binding_predictions,)
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,)
start=100018900,
ref='C',
alt='T',
ensembl=ensembl_grch37),
Variant(contig=11,
start=32861682,
ref='G',
alt='A',
ensembl=ensembl_grch37)
])
alleles = ["HLA-DPA1*01:05/DPB1*100:01", "DRB10102"]
epitope_lengths = [15, 16]
mhc_model = NetMHCIIpan(alleles=alleles, epitope_lengths=epitope_lengths)
def test_netmhcii_pan_epitopes():
epitope_predictions = predict_epitopes_from_variants(
mhc_model=mhc_model,
variants=variants,
transcript_expression_dict=None,
only_novel_epitopes=True)
# expect (15 + 16 mutant peptides) * (2 alleles) * 2 variants =
# 124 total epitope predictions
eq_(len(epitope_predictions), 124)
unique_alleles = {
epitope_prediction.allele
for epitope_prediction in epitope_predictions
alt='T',
ensembl=ensembl_grch37),
Variant(
contig=11,
start=32861682,
ref='G',
alt='A',
ensembl=ensembl_grch37)])
alleles = [
"HLA-DPA1*01:05/DPB1*100:01",
"DRB10102"
]
mhc_model = NetMHCIIpan(
alleles=alleles,
default_peptide_lengths=[15, 16])
def test_netmhcii_pan_epitopes():
epitope_predictions = TopiaryPredictor(
mhc_model=mhc_model,
only_novel_epitopes=True).predict_from_variants(variants=variants)
# expect (15 + 16 mutant peptides) * (2 alleles) * 2 variants =
# 124 total epitope predictions
eq_(len(epitope_predictions), 124)
unique_alleles = set(epitope_predictions.allele)
assert len(unique_alleles) == 2, \
"Expected 2 unique alleles, got %s" % (unique_alleles,)
unique_lengths = set(epitope_predictions.peptide_length)
assert unique_lengths == {15, 16}, \
def test_class2_8mer_fails():
ii_pan_predictor = NetMHCIIpan(alleles=["HLA-DRB1*01:01"])
with assert_raises(ValueError):
ii_pan_predictor.predict_peptides(["A" * 8])
def test_class2_9mer_success():
ii_pan_predictor = NetMHCIIpan(alleles=["HLA-DRB1*01:01"])
predictions = ii_pan_predictor.predict_peptides(["A" * 9])
eq_(len(predictions), 1)