def test_create_kmers_from_string(self):
kmers = KmerHelper.create_kmers_from_string("ABCDEFG", 3)
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_string("AB", 3)
self.assertTrue(len(kmers) == 0)
def compute_tcrb_relative_abundance(sequences: np.ndarray, counts: np.ndarray, k: int) -> dict:
"""
Computes the relative abundance of k-mers in the repertoire per following equations where C is the template count for the given receptor
sequence, T is the total count across all receptor sequences. The relative abundance per receptor sequence is then computed and only the
maximum sequence abudance was used for the k-mer so that the k-mer's relative abundance is equal to the abundance of the most frequent
receptor sequence in which the receptor appears:
.. math::
T^{TCR \\beta} = \\sum_{TCR\\beta} C^{TCR\\beta}
RA^{TCR\\beta} = \\frac{C^{TCR\\beta}}{T^{TCR\\beta}}
RA = \\max_{\\underset{with \\, kmer}{TCR\\beta}} {RA^{TCR \\beta}}
For more details, please see the original publication: Ostmeyer J, Christley S, Toby IT, Cowell LG. Biophysicochemical motifs in T cell
receptor sequences distinguish repertoires from tumor-infiltrating lymphocytes and adjacent healthy tissue. Cancer Res. Published online
January 1, 2019:canres.2292.2018. `doi:10.1158/0008-5472.CAN-18-2292 <https://cancerres.aacrjournals.org/content/canres/79/7/1671.full.pdf>`_
Arguments:
sequences: an array of (amino acid) sequences (corresponding to a repertoire)
counts: an array of counts for each of the sequences
k: the length of the k-mer (in the publication referenced above, k is 4)
Returns:
a dictionary where keys are k-mers and values are their relative abundances in the given list of sequences
"""
relative_abundance = {}
total_count = np.sum(counts)
relative_abundance_per_sequence = counts / total_count
for index, sequence in enumerate(sequences):
kmers = KmerHelper.create_kmers_from_string(sequence, k)
for kmer in kmers:
if kmer not in relative_abundance or relative_abundance[kmer] < relative_abundance_per_sequence[index]:
relative_abundance[kmer] = relative_abundance_per_sequence[index]
return relative_abundance
def compute_relative_abundance(sequences: np.ndarray, counts: np.ndarray, k: int) -> dict:
"""
Computes the relative abundance of k-mers in the repertoire per following equations where C is the template count, T is the total count and
RA is relative abundance (the output of the function for each k-mer separately):
.. math::
C^{kmer}=\\sum_{\\underset{with kmer}{TCR \\beta}} C^{TCR \\beta}
T^{kmer} = \\sum_{kmer} C^{kmer}
RA = \\frac{C^{kmer}}{T^{kmer}}
For more details, please see the original publication: Ostmeyer J, Christley S, Toby IT, Cowell LG. Biophysicochemical motifs in T cell
receptor sequences distinguish repertoires from tumor-infiltrating lymphocytes and adjacent healthy tissue. Cancer Res. Published online
January 1, 2019:canres.2292.2018. `doi:10.1158/0008-5472.CAN-18-2292 <https://cancerres.aacrjournals.org/content/canres/79/7/1671.full.pdf>`_
Arguments:
sequences: an array of (amino acid) sequences (corresponding to a repertoire)
counts: an array of counts for each of the sequences
k: the length of the k-mer (in the publication referenced above, k is 4)
Returns:
a dictionary where keys are k-mers and values are their relative abundances in the given list of sequences
"""
c_kmers = Counter()
for index, sequence in enumerate(sequences):
kmers = KmerHelper.create_kmers_from_string(sequence, k)
c_kmers += {kmer: counts[index] for kmer in kmers}
t_kmers = sum(c_kmers.values())
return {kmer: c_kmers[kmer] / t_kmers for kmer in c_kmers.keys()}