def test_longest_overlap():
# This should return the longest possible overlap =
# shortest possible subsequence between sequences.
longest_overlap1 = {"one": "ACCCC", "two": "CCCCG"}
assert find_overlaps(longest_overlap1) == "ACCCCG"
longest_overlap2 = {"three": "GGGGT", "four": "AGGGG"}
assert find_overlaps(longest_overlap2) == "AGGGGT"
def test_rosalind_exercise():
# Make sure that the script produces the right answer as judged by Rosalind
test_file = "data/rosalind_long5.txt"
answer_file = "results/long5.txt"
with open(answer_file, "r") as read_file:
answer = read_file.readline().strip()
sequence_dictionary = read_sequences(test_file)
assert find_overlaps(sequence_dictionary) == answer
def test_simple_sequences_with_duplicates():
# This should return a single instance of the longest supersequence
simple_with_duplicates = {
"one": "AC",
"two": "CG",
"three": "GT",
"one-dup": "AC",
"two-dup": "CG",
"three-dup": "GT",
}
assert find_overlaps(simple_with_duplicates) == "ACGT"
def test_two_simple_sequences():
two_simple_sequences = {"one": "AC", "two": "CG"}
assert find_overlaps(two_simple_sequences) == "ACG"
def test_simple_deduplication():
# This should return on of the two identical sequences
simple_duplicates = {"one": "A", "two": "A"}
assert find_overlaps(simple_duplicates) == "A"
def test_single_sequence():
# This should return the sequence itself
assert find_overlaps({"single_sequence": "ACGT"}) == "ACGT"
def test_find_overlaps():
# Make sure the sample dataset works as intended
assert find_overlaps(sample_dictionary) == "ATTAGACCTGCCGGAATAC"