def test_create_kmers_from_sequence(self):
kmers = KmerHelper.create_kmers_from_sequence(ReceptorSequence(amino_acid_sequence="ABCDEFG"), 3, sequence_type=SequenceType.AMINO_ACID)
self.assertTrue("ABC" in kmers and "BCD" in kmers and "CDE" in kmers and "DEF" in kmers and "EFG" in kmers)
self.assertEqual(5, len(kmers))
kmers = KmerHelper.create_kmers_from_sequence(ReceptorSequence(amino_acid_sequence="AB"), 3, sequence_type=SequenceType.AMINO_ACID)
self.assertTrue(len(kmers) == 0)
def encode_sequence(sequence: ReceptorSequence, params: EncoderParams):
"""
Encodes a receptor sequence into a sequence of k-mers
Args:
sequence: ReceptorSequence object
params: EncoderParams object with information on k-mer length
Returns:
"""
k = params.model["k"]
sequence_type = params.model.get('sequence_type', None)
length = len(sequence.get_sequence(sequence_type))
if length < k:
logging.warning(
f'KmerSequenceEncoder: Sequence length {length} is less than {k}. Ignoring sequence...'
)
return None
kmers = KmerHelper.create_kmers_from_sequence(
sequence=sequence, k=k, sequence_type=sequence_type)
return kmers
def _encode_repertoire(self, repertoire, vectors):
repertoire_vector = np.zeros(vectors.vector_size)
for (index2, sequence) in enumerate(repertoire.sequences):
kmers = KmerHelper.create_kmers_from_sequence(sequence=sequence,
k=self.k)
sequence_vector = np.zeros(vectors.vector_size)
for kmer in kmers:
try:
word_vector = vectors.get_vector(kmer)
sequence_vector = np.add(sequence_vector, word_vector)
except KeyError:
pass
repertoire_vector = np.add(repertoire_vector, sequence_vector)
return repertoire_vector
def encode_sequence(sequence: ReceptorSequence, params: EncoderParams):
"""
creates overlapping continuous k-mers and IMGT position pairs from a sequence as features for use in
KmerFrequencyEncoder object of type EncoderParams, same object as passed into KmerFrequencyEncoder.
:param sequence: ReceptorSequence
:param params: EncoderParams (where params["model"]["k"] is used)
:return: SequenceEncodingResult
"""
k = params.model["k"]
length = len(sequence.get_sequence())
if length < k:
logging.warning('KmerSequenceEncoder: Sequence length is less than k. Ignoring sequence...')
return None
kmers = KmerHelper.create_kmers_from_sequence(sequence, k)
return kmers