Lesson 6: Iteration notebook - Introduction to Python For Bioinformatics

# The sequence we want to analyze
seq = 'GACAGACUCCAUGNNNNNNNCACGUGGGUAUCUGUC'

# Initialize GC counter
n_gc = 0

# Initialize sequence length
len_seq = 0

# Loop through sequence and count G's and C's
for base in seq:
# all three of these mean the same thing
#    if base != 'N' and base != 'n':
#        len_seq += 1
#    if not (base == 'N' or base == 'n'):
#        len_seq += 1
    if base not in 'Nn':
        len_seq += 1
    if base in 'GCgc':
        n_gc += 1
        
# Divide to get GC content
n_gc / len_seq

0.5517241379310345

# length of a sequence
print("length:", len(seq))

length: 36

my_list = [1, 'a', ['a', 'fine', 'day']]
print("length:", len(my_list))

length: 3

# We'll do one through 5
my_integers = [1, 2, 3, 4, 5]

# Double each one
for n in my_integers:
    n *= 2
    
# Check out the result
my_integers

[1, 2, 3, 4, 5]

# Don't do things this way
my_integers[0] *= 2
my_integers[1] *= 2
my_integers[2] *= 2
my_integers[3] *= 2
my_integers[4] *= 2

my_integers

[2, 4, 6, 8, 10]

range(10)

range(0, 10)

type(range(10))

range

my_range = range(10)
print(type(my_range))
range_iterator = iter(my_range)
print(type(range_iterator))
print(next(range_iterator))
print(next(range_iterator))

<class 'range'>
<class 'range_iterator'>
0
1

seq = 'GACAGACUCCAUGNNNNNNNCACGUGGGUAUCUGUC'
seq_iter = iter(seq)
print(type(seq_iter))
print(next(seq_iter))
print(next(seq_iter))

<class 'str_ascii_iterator'>
G
A

for i in range(10):
    print(i, end='  ')

0  1  2  3  4  5  6  7  8  9

print('hello', 'world', sep='|')

hello|world

print('hello', 'world')

hello world

print(sep='|', 'hello', 'world')

  Cell In[13], line 1
    print(sep='|', 'hello', 'world')
                                   ^
SyntaxError: positional argument follows keyword argument

help(print)

Help on built-in function print in module builtins:

print(*args, sep=' ', end='\n', file=None, flush=False)
    Prints the values to a stream, or to sys.stdout by default.

    sep
      string inserted between values, default a space.
    end
      string appended after the last value, default a newline.
    file
      a file-like object (stream); defaults to the current sys.stdout.
    flush
      whether to forcibly flush the stream.

for i in range(10):
    print(i, end='  ')

0  1  2  3  4  5  6  7  8  9

help(range)

Help on class range in module builtins:

class range(object)
 |  range(stop) -> range object
 |  range(start, stop[, step]) -> range object
 |
 |  Return an object that produces a sequence of integers from start (inclusive)
 |  to stop (exclusive) by step.  range(i, j) produces i, i+1, i+2, ..., j-1.
 |  start defaults to 0, and stop is omitted!  range(4) produces 0, 1, 2, 3.
 |  These are exactly the valid indices for a list of 4 elements.
 |  When step is given, it specifies the increment (or decrement).
 |
 |  Methods defined here:
 |
 |  __bool__(self, /)
 |      True if self else False
 |
 |  __contains__(self, key, /)
 |      Return bool(key in self).
 |
 |  __eq__(self, value, /)
 |      Return self==value.
 |
 |  __ge__(self, value, /)
 |      Return self>=value.
 |
 |  __getitem__(self, key, /)
 |      Return self[key].
 |
 |  __gt__(self, value, /)
 |      Return self>value.
 |
 |  __hash__(self, /)
 |      Return hash(self).
 |
 |  __iter__(self, /)
 |      Implement iter(self).
 |
 |  __le__(self, value, /)
 |      Return self<=value.
 |
 |  __len__(self, /)
 |      Return len(self).
 |
 |  __lt__(self, value, /)
 |      Return self<value.
 |
 |  __ne__(self, value, /)
 |      Return self!=value.
 |
 |  __reduce__(self, /)
 |      Helper for pickle.
 |
 |  __repr__(self, /)
 |      Return repr(self).
 |
 |  __reversed__(self, /)
 |      Return a reverse iterator.
 |
 |  count(self, object, /)
 |      rangeobject.count(value) -> integer -- return number of occurrences of value
 |
 |  index(self, object, /)
 |      rangeobject.index(value) -> integer -- return index of value.
 |      Raise ValueError if the value is not present.
 |
 |  ----------------------------------------------------------------------
 |  Static methods defined here:
 |
 |  __new__(*args, **kwargs)
 |      Create and return a new object.  See help(type) for accurate signature.
 |
 |  ----------------------------------------------------------------------
 |  Data descriptors defined here:
 |
 |  start
 |
 |  step
 |
 |  stop

# Print numbers 2 through 9
for i in range(2, 10):
    print(i, end='  ')

# Print a newline
print()
    
# Print even numbers, 2 through 9
for i in range(2, 10, 2):
    print(i, end='     ')

2  3  4  5  6  7  8  9  
2     4     6     8

for i in range(10, 2 , -2):
    print(i, end='     ')

10     8     6     4

range(1000)

range(0, 1000)

list(range(10))

[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]

list(range(1000))

my_integers = [1, 2, 3, 4, 5]
# indices      0  1  2  3  4
# Since len(my_integers) = 5, this takes i from 0 to 4, 
# exactly the indices of my_integers
for i in range(len(my_integers)):
    my_integers[i] *= 2
    
my_integers

[2, 4, 6, 8, 10]

my_integers = [1, 2, 3, 4, 5]
double_integers = []

for n in my_integers:
    double_integers += [n*2]
    # double_integers = double_integers + [n*2]

print("my integers:", my_integers)
print("double integers:", double_integers)

my integers: [1, 2, 3, 4, 5]
double integers: [2, 4, 6, 8, 10]

[1, 2, 3, 4, 5] + 6

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[24], line 1
----> 1 [1, 2, 3, 4, 5] + 6 

TypeError: can only concatenate list (not "int") to list

[1, 2, 3, 4, 5] + [6]

[1, 2, 3, 4, 5, 6]

[1, 2, 3, 4, 5] + ['six']

[1, 2, 3, 4, 5, 'six']

[1, 2, 3, 4, 5] + 'six'

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[27], line 1
----> 1 [1, 2, 3, 4, 5] + 'six'

TypeError: can only concatenate list (not "str") to list

my_integers = [1, 2, 3, 4, 5]

for n in my_integers:
    double_integers += [n*2]
    # double_integers = double_integers + [n*2]

this_num += 1

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[29], line 1
----> 1 this_num += 1

NameError: name 'this_num' is not defined

my_integers = (1, 2, 3, 4, 5)
double_integers = ()

for n in my_integers:
    double_integers += (n*2,)
    # double_integers = double_integers + [n*2]

print("my integers:", my_integers)
print("double integers:", double_integers)

my integers: (1, 2, 3, 4, 5)
double integers: (2, 4, 6, 8, 10)

my_numbers = (1,2,3,4,5)

for i in range(len(my_numbers)):
    my_numbers[i] *= 2

my_numbers

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[31], line 4
      1 my_numbers = (1,2,3,4,5)
      3 for i in range(len(my_numbers)):
----> 4     my_numbers[i] *= 2
      6 my_numbers

TypeError: 'tuple' object does not support item assignment

seq = 'GACAGACUCCAUGNNNNNNNCACGUGGGUAUCUGUC'

# Initialized sequence length
len_seq = 0

# Loop through sequence and print index of G's
for base in seq:
    if base in 'Gg':
        print(len_seq, end='  ')
    len_seq += 1

0  4  12  23  25  26  27  33

seq = 'GACAGACUCCAUGNNNNNNNCACGUGGGUAUCUGUC'

# Loop through sequence and print index of G's
for i, base in enumerate(seq):
    if base in 'Gg':
        print(i, end='  ')

0  4  12  23  25  26  27  33

my_tuple = (3, 2, 1)
a, b, c = my_tuple
print(a, b, c)

3 2 1

list(enumerate(seq))

[(0, 'G'),
 (1, 'A'),
 (2, 'C'),
 (3, 'A'),
 (4, 'G'),
 (5, 'A'),
 (6, 'C'),
 (7, 'U'),
 (8, 'C'),
 (9, 'C'),
 (10, 'A'),
 (11, 'U'),
 (12, 'G'),
 (13, 'N'),
 (14, 'N'),
 (15, 'N'),
 (16, 'N'),
 (17, 'N'),
 (18, 'N'),
 (19, 'N'),
 (20, 'C'),
 (21, 'A'),
 (22, 'C'),
 (23, 'G'),
 (24, 'U'),
 (25, 'G'),
 (26, 'G'),
 (27, 'G'),
 (28, 'U'),
 (29, 'A'),
 (30, 'U'),
 (31, 'C'),
 (32, 'U'),
 (33, 'G'),
 (34, 'U'),
 (35, 'C')]

my_integers = [1, 2, 3, 4, 5]

# Double each one
for i, _ in enumerate(my_integers):
    my_integers[i] *= 2
    
# Check out the result
my_integers

[2, 4, 6, 8, 10]

my_integers = [1, 2, 3, 4, 5]

# Double each one
for i, num in enumerate(my_integers):
    my_integers[i] = num * 2
    
# Check out the result
my_integers

[2, 4, 6, 8, 10]

seq = 'GACAGACUCCAUGNNNNNNNCACGUGGGUAUCUGUC'

# Define start codon
start_codon = 'AUG'

# Initialize sequence index
i = 0

# Scan sequence until we hit the start codon
while seq[i:i+3] != start_codon:
    i += 1
    
# Show the result
print('The start codon starts at index', i)

The start codon starts at index 10

seq = 'GACAGACUCCAUGNNNNNNNCACGUGGGUAUCUGUC'

# Define start codon
start_codon = 'AZG'

# Initialize sequence index
i = 0

# Scan sequence until we hit the start codon
# There is an error in this code. The loop
# will never complete. Uncomment the next lines
# and run them to see, but you will need to
# stop the notebook yourself (the stop button
# has a square)
# while seq[i:i+3] != start_codon:
#     i += 1
    
# Show the result
print('The start codon starts at index', i)

The start codon starts at index 0

seq[1000]

---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
Cell In[40], line 1
----> 1 seq[1000]

IndexError: string index out of range

seq[1000:1003]

''

seq = 'GACAGACUCCAUGNNNNNNNCACGUGGGUAUCUGUC'

# Define start codon
start_codon = 'AZG'

# Initialize sequence index
i = 0

# Scan sequence until we hit the start codon
while seq[i:i+3] != start_codon and i < len(seq):
    i += 1
    
# Show the result
if i < len(seq):
    print('The start codon starts at index', i)
else:
    print('Start codon not found')

Start codon not found

len(seq)

36

lines = [
    "FINDHOM v 1.2:\n",
    "Search results:\n",
    "Query\tMatch fraction\tScore\tSubject\n",
    "SMPL001\t0.7\t12331\tAQ10213 Phlebotomus perniciosus\n",
    "SMPL003\t0.5\t6032\tBZ102363 Phlebotomus papatasi\n",
    "SMPL004\t0.8\t13123\tRD178237 Sergentomyia dubia\n",
    "SMPL007\t0.6\t10610\tBQ187981 Phlebotomus papatasi\n"
]

for line in lines:
    print(line, end='')

FINDHOM v 1.2:
Search results:
Query	Match fraction	Score	Subject
SMPL001	0.7	12331	AQ10213 Phlebotomus perniciosus
SMPL003	0.5	6032	BZ102363 Phlebotomus papatasi
SMPL004	0.8	13123	RD178237 Sergentomyia dubia
SMPL007	0.6	10610	BQ187981 Phlebotomus papatasi

lines = [
    "FINDHOM v 1.2:\n",
    "Search results:\n",
    "Query\tMatch fraction\tScore\tSubject\n",
    "SMPL001\t0.7\t12331\tAQ10213 Phlebotomus perniciosus\n",
    "SMPL003\t0.5\t6032\tBZ102363 Phlebotomus papatasi\n",
    "SMPL004\t0.8\t13123\tRD178237 Sergentomyia dubia\n",
    "SMPL007\t0.6\t10610\tBQ187981 Phlebotomus papatasi\n"
]

# Search term
search_term = "Sergentomyia"
# Scan sequence until we hit the start codon
for i, line in enumerate(lines):
    if search_term in line:
        print(search_term, 'found on line', i+1)
        break
else:
    print(search_term, 'not found in output.')

Sergentomyia found on line 6

lines = [
    "FINDHOM v 1.2:\n",
    "Search results:\n",
    "Query\tMatch fraction\tScore\tSubject\n",
    "SMPL001\t0.7\t12331\tAQ10213 Phlebotomus perniciosus\n",
    "SMPL003\t0.5\t6032\tBZ102363 Phlebotomus papatasi\n",
    "SMPL004\t0.8\t13123\tRD178237 Sergentomyia dubia\n",
    "SMPL007\t0.6\t10610\tBQ187981 Phlebotomus papatasi\n"
]

# Search term
search_term = "Sergentomydia"
# Scan sequence until we hit the start codon
for i, line in enumerate(lines):
    if search_term in line:
        print(search_term, 'found on line', i+1)
        break
print(search_term, 'not found in output.')

Sergentomydia not found in output.

lines = [
    "FINDHOM v 1.2:\n",
    "Search results:\n",
    "Query\tMatch fraction\tScore\tSubject\n",
    "SMPL001\t0.7\t12331\tAQ10213 Phlebotomus perniciosus\n",
    "SMPL003\t0.5\t6032\tBZ102363 Phlebotomus papatasi\n",
    "SMPL004\t0.8\t13123\tRD178237 Sergentomyia dubia\n",
    "SMPL007\t0.6\t10610\tBQ187981 Phlebotomus papatasi\n"
]

# Search term
search_term = "Sergentomyia"
# Scan sequence until we hit the start codon
for i, line in enumerate(lines):
    if search_term in line:
        print(search_term, 'found on line', i+1)
        break
print(search_term, 'not found in output.')

Sergentomyia found on line 6
Sergentomyia not found in output.