reverse_complement.py

# See tests for a more comprehensive complementary table
SIMPLE_COMPLEMENTS_STR = """#Reduced table with bases A, G, C, T
 Base	Complementary Base
 A	T
 T	A
 G	C
 C	G
"""


# Recommended helper function
def _clean_sequence(sequence, str_table):
    """
    Receives a DNA sequence and a str_table that defines valid (and
    complementary) bases
    Returns all sequences converted to upper case and remove invalid
    characters
    t!t%ttttAACCG --> TTTTTTAACCG
    """
    filter_list = [s[1] for s in str_table.splitlines()[2:]]
    return "".join(filter(lambda c: c in filter_list, sequence.upper()))


def reverse(sequence, str_table=SIMPLE_COMPLEMENTS_STR):
    """
    Receives a DNA sequence and a str_table that defines valid (and
    complementary) bases
    Returns a reversed string of sequence while removing all characters
    not found in str_table characters
    e.g. t!t%ttttAACCG --> GCCAATTTTTT
    """
    return _clean_sequence(sequence, str_table)[::-1]


def complement(sequence, str_table=SIMPLE_COMPLEMENTS_STR):
    """
    Receives a DNA sequence and a str_table that defines valid (and
    complementary) bases
    Returns a string containing complementary bases as defined in
    str_table while removing non input_sequence characters
    e.g. t!t%ttttAACCG --> AAAAAATTGGC
    """
    clean_seq = _clean_sequence(sequence, str_table)
    replace_dict = {s[1]: s[-1] for s in str_table.splitlines(keepends=False)[2:]}
    return "".join(map(lambda c: replace_dict[c], clean_seq))


def reverse_complement(sequence, str_table=SIMPLE_COMPLEMENTS_STR):
    """
    Receives a DNA sequence and a str_table that defines valid (and
    complementary) bases
    Returns a string containing complementary bases as defined in str_table
    while removing non input_sequence characters
    e.g. t!t%ttttAACCG --> CGGTTAAAAAA
    """
    return complement(sequence, str_table)[::-1]