def test_gc_blocks_invalid_amino_acid():
with pytest.raises(RuntimeError) as excinfo:
gc_blocks.gc_blocks('B', 1)
excinfo.match("B is not a valid nucleotide.")
with pytest.raises(RuntimeError) as excinfo:
gc_blocks.gc_blocks('ATGACTBCGT', 4)
excinfo.match("B is not a valid nucleotide.")
def test_gc_blocks_for_empty_seq():
"""Perform unit tests on gc_blocks for empty seq"""
with pytest.raises(RuntimeError) as excinfo:
gc_blocks.gc_blocks('', 1) == ()
excinfo.match("Block size is longer than sequence.")
with pytest.raises(RuntimeError) as excinfo:
gc_blocks.gc_blocks('', 50) == ()
excinfo.match("Block size is longer than sequence.")
def gc_map(seq, block_size, gc_thresh):
"""Divides a sequence into blocks and capitalizes blocks with GC content greater than or equal to the threshold."""
blocks = gc_blocks.make_blocks(seq, block_size)
block_gc_content = gc_blocks.gc_blocks(seq, block_size)
# Initialize final sequence
seq_analyzed = ''
for i, val in enumerate(block_gc_content):
if val >= gc_thresh:
seq_analyzed += blocks[i].upper()
else:
seq_analyzed += blocks[i].lower()
return seq_analyzed
def test_gc_blocks_lowercase():
"""Perform unit tests on number_negative for lowercase"""
assert gc_blocks.gc_blocks('atgactacgt', 4) == (
0.25, 0.5) # We want the function to be agnostic to case
def test_gc_blocks_for_long_block():
"""Perform unit tests on gc_blocks for when the block size is longer than the sequence"""
with pytest.raises(RuntimeError) as excinfo:
gc_blocks.gc_blocks('ATGACTAGCTAGC', 20)
excinfo.match("Block size is longer than sequence.")
def test_gc_blocks_short_sequences():
"""Perform unit tests on gc_blocks for short sequence"""
assert gc_blocks.gc_blocks('ATGACTACGT', 4) == (0.25, 0.5)
def test_gc_blocks_single_nucleotide():
"""Perform unit tests on gc_blocks for single nucleotide"""
assert gc_blocks.gc_blocks('C', 1) == (1 / 1, )
assert gc_blocks.gc_blocks('G', 1) == (1 / 1, )
assert gc_blocks.gc_blocks('A', 1) == (0, )
assert gc_blocks.gc_blocks('T', 1) == (0, )