def test_order_of_annotation_fields_is_taken_from_annotations_orddict_order(
self, fasta_seq, index_df):
# first seq_context, then triplet_seq
annotations = OrderedDict()
annotations['seq_context'] = 2
annotations['triplet_seq'] = True
computed_lines = list(
bed_lines_generator(fasta_seq=fasta_seq,
motifs=['CG', 'CHH', 'CHG'],
annotations=annotations,
chr_name='chr1'))
expected_cols = '#chrom start end motif score strand seq_context triplet_seq'.split(
)
expected_lines = self.get_expected_lines(index_df, expected_cols)
assert computed_lines[0:3] == expected_lines[0:3]
# first triplet_seq, then seq_context
annotations = OrderedDict()
annotations['triplet_seq'] = True
annotations['seq_context'] = 2
computed_lines = list(
bed_lines_generator(fasta_seq=fasta_seq,
motifs=['CG', 'CHH', 'CHG'],
annotations=annotations,
chr_name='chr1'))
expected_cols = '#chrom start end motif score strand triplet_seq seq_context'.split(
)
expected_lines = self.get_expected_lines(index_df, expected_cols)
assert computed_lines[0:3] == expected_lines[0:3]
def test_optionally_annotates_motif_triplet_sequence(
self, fasta_seq, index_df, annotations_orddict):
annotations_orddict['seq_context'] = 0
computed_lines = list(
bed_lines_generator(fasta_seq=fasta_seq,
motifs=['CG', 'CHH', 'CHG'],
annotations=annotations_orddict,
chr_name='chr1'))
expected_cols = '#chrom start end motif score strand triplet_seq'.split(
)
expected_lines = self.get_expected_lines(index_df, expected_cols)
assert computed_lines == expected_lines
def test_finds_cytosines_and_classifies_motifs_correctly_even_at_boundaries_and_next_to_Ns(
self, fasta_seq, index_df, annotations_orddict):
for k in annotations_orddict.keys():
annotations_orddict[k] = False
computed_lines = list(
bed_lines_generator(fasta_seq=fasta_seq,
motifs=['CG', 'CHH', 'CHG'],
annotations=annotations_orddict,
chr_name='chr1'))
expected_cols = '#chrom start end motif score strand'.split()
expected_lines = self.get_expected_lines(index_df, expected_cols)
assert computed_lines == expected_lines
def test_discards_cytosines_which_are_not_in_the_specified_motifs(
self, index_df, fasta_seq):
computed_lines = list(
bed_lines_generator(fasta_seq=fasta_seq,
motifs=['CG'],
annotations={},
chr_name='chr1'))
expected_cols = '#chrom start end motif score strand'.split()
is_cg = index_df['motif'] == 'CG'
cg_index_df = index_df.loc[is_cg, :]
expected_lines = self.get_expected_lines(cg_index_df, expected_cols)
assert computed_lines == expected_lines