from immuno.ensembl import transcript_variant
def test_dbnsfp_validation_set():
validation_set = pd.read_csv("dbnsfp_validation_set.csv")
for idx, row in validation_set.iterrows():
yield (validate_transcript_mutation, row)
def validate_transcript_mutation(row):
transcript_id = row["ensembl_transcript"]
print row
peptide, start, stop, annot = transcript_variant.peptide_from_transcript_variant(
transcript_id, row["position"], ref=row["ref"], alt=row["alt"], padding=None, max_length=None
)
assert peptide is not None
aa_index = row["aapos"] - 1
assert peptide[row["aapos"] - 1] == row["aaalt"], "Expected %s at amino acid pos %d but found %s" % (
row["aaalt"],
aa_index,
peptide[aa_index],
)
if __name__ == "__main__":
from dsltools import testing_helpers
testing_helpers.run_local_tests()
# Copyright (c) 2014. Mount Sinai School of Medicine
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from immuno import vcf
def test_vcf_to_dataframe():
vcf_file = 'data/example.vcf'
df = vcf.load_vcf(vcf_file)
assert df is not None
assert(len(df) == 3)
assert(len(df.columns) == 8)
if __name__ == '__main__':
from dsltools import testing_helpers
testing_helpers.run_local_tests()