Coursera_Learn_to_Program/a2.py at master · bugzPDX/Coursera_Learn_to_Program · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
def get_length(dna):
    """ (str) -> int

    Return the length of the DNA sequence dna.

    >>> get_length('ATCGAT')
    6
    >>> get_length('ATCG')
    4
    """
    return len(dna)


def is_longer(dna1, dna2):
    """ (str, str) -> bool

    Return True if and only if DNA sequence dna1 is longer than DNA sequence
    dna2.

    >>> is_longer('ATCG', 'AT')
    True
    >>> is_longer('ATCG', 'ATCGGA')
    False
    """
    return dna1 > dna2


def count_nucleotides(dna, nucleotide):
    """ (str, str) -> int

    Return the number of occurrences of nucleotide in the DNA sequence dna.

    >>> count_nucleotides('ATCGGC', 'G')
    2
    >>> count_nucleotides('ATCTA', 'G')
    0
    """
    return dna.count(nucleotide)


def contains_sequence(dna1, dna2):
    """ (str, str) -> bool

    Return True if and only if DNA sequence dna2 occurs in the DNA sequence
    dna1.

    >>> contains_sequence('ATCGGC', 'GG')
    True
    >>> contains_sequence('ATCGGC', 'GT')
    False

    """
    return dna2 in dna1


def is_valid_sequence(dna):

    """ (str) -> bool

    Return True if and only if the DNA sequence is valid. A string is not a
    valid DNA sequence if it contains lowercase letters.

    >>> is_valid_sequence('ATAGCCGTA')
    True
    >>> is_valid_sequence('ATaGccGTB')
    False

    """

    for char in dna:
        if char not in 'ATCG':
            return False
    return True


def insert_sequence(dna1, dna2, index):

    """ (str, str, int) -> str

    Return the DNA sequence obtained by inserting the second DNA sequence
    into the first DNA sequence at the given index.

    >>> insert_sequence('ATTA', 'CG', 1)
    ACGTTA
    >>> insert_sequence('CGTTAC', 'TCG', 3)
    CGTTCGTAC

    """

    result = dna1[:index] + dna2 + dna1[index:]
    return result


def get_complement(dna):

    """ (str) -> str

    Return the nucleotide's complement.

    >>> get_complement('A')
    T
    >>> get_complement('C')
    G
    >>> get_complement('G')
    C
    >>> get_complement('T')
    A

    """

    if dna == 'A':
        return 'T'
    if dna == 'T':
        return 'A'
    if dna == 'C':
        return 'G'
    if dna == 'G':
        return 'C'
    return 'Invalid nucleotide'

def get_complementary_sequence(sequence):

    """ (str) -> str

    Return the DNA sequence that is complementary to the given DNA sequence.

    >>> get_complementary_sequence('ATTA')
    TAAT
    >>> get_complementary_sequence('CTAG')
    GATC
    >>> get_complementary_sequence('AGTTACGT')
    TCAATGCA

    """

    result = ''

    for char in sequence:
        result += get_complement(char)
    return result