Code implements the dynamic programming solution for global pairwise alignment of two sequences. Trying to perform a semi-global alignment between the SARS-CoV-2 reference genome and the first read in the Nanopore sample. The length of the reference genome is 29903 base pairs and the length of the first Nanopore read is 1246 base pairs. When I run the following code, I get this message in my terminal:
import sys
import numpy as np
GAP = -2
MATCH = 5
MISMATCH = -3
MAXLENGTH_A = 29904
MAXLENGTH_B = 1247
# insert sequence files
A = open("SARS-CoV-2 reference genome.txt", "r")
B = open("Nanopore.txt", "r")
def max(A, B, C):
if (A >= B and A >= C):
return A
elif (B >= A and B >= C):
return B
else:
return C
def Tmax(A, B, C):
if (A > B and A > C):
return 'D'
elif (B > A and B > C):
return 'L'
else:
return 'U'
def m(p, q):
if (p == q):
return MATCH
else:
return MISMATCH
def append(st, c):
return c + "".join(i for i in st)
if __name__ == "__main__":
if (len(sys.argv) != 2):
print("Usage: align <input file>")
sys.exit()
if (not os.path.isfile(sys.argv[1])):
print("input file not found.")
sys.exit()
S = np.empty([MAXLENGTH_A, MAXLENGTH_B], dtype = int)
T = np.empty([MAXLENGTH_A, MAXLENGTH_B], dtype = str)
with open(sys.argv[1], "r") as file:
A = str(A.readline())[:-1]
B = str(B.readline())[:-1]
print("Sequence A:",A)
print("Sequence B:",B)
N = len(A)
M = len(B)
S[0][0] = 0
T[0][0] = 'D'
for i in range(0, N + 1):
S[i][0] = GAP * i
T[i][0] = 'U'
for i in range(0, M + 1):
S[0][i] = GAP * i
T[0][i] = 'L'
for i in range(1, N + 1):
for j in range(1, M + 1):
S[i][j] = max(S[i-1][j-1]+m(A[i-1],B[j-1]),S[i][j-1]+GAP,S[i-1][j]+GAP)
T[i][j] = Tmax(S[i-1][j-1]+m(A[i-1],B[j-1]),S[i][j-1]+GAP,S[i-1][j]+GAP)
print("The score of the alignment is :",S[N][M])
i, j = N, M
RA = RB = RM = ""
while (i != 0 or j != 0):
if (T[i][j]=='D'):
RA = append(RA,A[i-1])
RB = append(RB,B[j-1])
if (A[i-1] == B[j-1]):
RM = append(RM,'|')
else:
RM = append(RM,'*')
i -= 1
j -= 1
elif (T[i][j]=='L'):
RA = append(RA,'-')
RB = append(RB,B[j-1])
RM = append(RM,' ')
j -= 1
elif (T[i][j]=='U'):
RA = append(RA,A[i-1])
RB = append(RB,'-')
RM = append(RM,' ')
i -= 1
print(RA)
print(RM)
print(RB)
This has nothing to do with python. The error message comes this line:
if (len(sys.argv) != 2):
print("Usage: align <input file>")
The code expects to be called with exactly one argument, the input file:
align path/to/input/file
You provided a different number of arguments, probably zero.
Related
I'm trying to write png reader using python and zlib. I do not understand what to do after I've decompressed IDAT content. My code now (imagine that we have only one IDAT chunk):
...
def IDAT(self, chunk_size):
data = self.f.read(chunk_size)
raw_colors = zlib.decompress(data)
self.raw_color_values.extend(raw_colors)
self.f.read(4)
self.processIDAT()
def processIDAT(self):
Recon = []
i = 0
bytesPerPixel = self.bit_depth // 8
if self.color_type == 2:
bytesPerPixel = (self.bit_depth // 8) * 3
for y in range(self.file_height): # for each scanline
processRow = [0] * self.file_width
filter_type = self.raw_color_values[y * (self.file_width * bytesPerPixel + 1)]
i += 1
for x in range(self.file_width): # for each byte in scanline
color_index = self.raw_color_values[y * (self.file_width * bytesPerPixel + 1) + 1 + x]
i += 1
if filter_type == 0: # None
Recon_x = color_index
elif filter_type == 1: # Sub
# ??????
elif filter_type == 2: # Up
# ??????
elif filter_type == 3: # Average
# ??????
elif filter_type == 4: # Paeth
Recon_x = color_index + self.PaethPredictor() # what are params here?
else:
print('unknown filter type: ' + str(filter_type))
Recon.append(Recon_x & 0xff) # truncation to byte
return Recon
def PaethPredictor(self, a, b, c):
p = a + b - c
pa = abs(p - a)
pb = abs(p - b)
pc = abs(p - c)
if pa <= pb and pa <= pc:
Pr = a
elif pb <= pc:
Pr = b
else:
Pr = c
return Pr
According to official documentation I have to implement Recon function. What this function does? Are there any implementation references?
The formulas for Recon are right there in the document you linked:
I am stuck in rewriting Python code to compile it in PyPy. My task is to calculate number of inversions in a list using modification of merge sort. Input data brings from input.txt, the result of the code is written in output.txt. My last attempt to do this looks like:
import sys
def merge(a, b, inverse_num):
n, m = len(a), len(b)
i = 0
j = 0
c = []
while i < n or j < m:
if j == m:
c.append(a[i])
i += 1
# inverse_num += 1
elif i < n and a[i] <= b[j]:
c.append(a[i])
i += 1
elif i < n and a[i] > b[j]:
c.append(b[j])
j += 1
inverse_num += n - i
if j == m and i == n - 1:
c.append(a[i])
i += 1
else:
c.append(b[j])
j += 1
return c, inverse_num
def merge_sort(arr, inverse_num=0):
n = len(arr)
if n == 1:
return arr, inverse_num
l = arr[:(n//2)]
r = arr[(n//2):n]
l, inverse_num_l = merge_sort(l, inverse_num)
r, inverse_num_r = merge_sort(r, inverse_num)
inverse_num = inverse_num_l + inverse_num_r
return merge(l, r, inverse_num)
def main():
with open('input.txt') as f:
n = int(f.readline().split()[0])
in_list = list(map(int, f.readline().split()))
output_file = open('output.txt', 'w')
sorted_arr, inverse_num = merge_sort(in_list, inverse_num=0)
output_file.write(str(inverse_num))
output_file.close()
return 0
def target(*args):
return entry_point, None
def entry_point(argv):
main()
return 0
if __name__ == "__main__":
entry_point(sys.argv)
After compilation it with command pypy "C:/pypy_compile/pypy-src/translate.py" Task2.py
error appears:
[translation:ERROR] TypeError: method_split() takes at least 2 arguments (1 given)
Processing block:
block#27[v4...] is a <class 'rpython.flowspace.flowcontext.SpamBlock'>
in (Task2:44)main
containing the following operations:
v6 = getattr(v5, ('split'))
v7 = simple_call(v6)
--end--
Thanks in advance for helping.
just a small labyrinth solver. try it to on python but dont even understand why it doesnt print anything. Im just started with python and trying to actually translate my teachers code from cpp just for interest.
need to reach to the destination after visiting each cell
m = [
[2,0,0,0,0,0],
[0,0,0,0,0,0],
[0,0,0,0,0,0],
[0,0,0,0,0,0],
[0,0,0,2,0,0],
[0,0,0,0,0,0]
]
STOP = 34
r = 0
c = 0
def init( r_: int = 0, c_: int = 0) -> None:
r = 0
c = 0
def step(r,c,level):
if level==STOP-1:
if r == 3 and c == 5:
for i in range(0,level):
print("("+init(int(r),int(c))+"," + init(int(r),int(c)) + ") - ")
print("(3,5)\n")
return True
else:
return False
m[r][c]=1
if c > 0 and m[r][c - 1] == 0:
if step(r, c - 1, level + 1):
return True
if c < 5 and m[r][c + 1] == 0:
if (step(r, c + 1, level + 1)):
return True
if r > 0 and m[r - 1][c] == 0:
if (step(r - 1, c, level + 1)):
return True
if r < 5 and m[r + 1][c] == 0:
if (step(r + 1, c, level + 1)):
return True
m[r][c] = 0
return False
def main(argc, argv):
step(0, 1, 0)
Python doesn't automatically call main like c does, nor does it require a main function. Your code can just live in the top level (e.g. print('hello world') is a valid, complete program)
Change this line:
def main(argc, argv):
to this:
if __name__ == '__main__':
got it
import matplotlib.pyplot as plt
S, F, W, X = 1, 2, 0, None
FIELD = [[X,S,W,W,W,W],
[W,W,W,W,W,W],
[W,W,W,W,W,W],
[W,W,W,W,W,F],
[W,W,W,X,W,W],
[W,W,W,W,W,W]]
ROWS = len(FIELD)
COLS = len(FIELD[0])
START_POS = [(i, line.index(S)) for i, line in enumerate(FIELD) if S in line][0]
FINISH_POS = [(i, line.index(F)) for i, line in enumerate(FIELD) if F in line][0]
STEPS = sum(line.count(W) for line in FIELD) + 1
print("Start:", START_POS, "\nFinish:", FINISH_POS, "\nTotal steps:", STEPS)
def do_step(level, path, points):
global FIELD
r, c = points[-1]
if r<0 or c<0 or r>=ROWS or c>=COLS or FIELD[r][c] == X:
return
if level == STEPS and (r, c) == FINISH_POS:
print("Found path:", path)
yy, xx = zip(*points)
plt.plot(xx, yy, "-ok")
plt.gca().invert_yaxis()
plt.show()
exit()
current = FIELD[r][c]
FIELD[r][c] = X
for dr, dc, dir in ((-1,0,'^'), (0,1,'>'), (1,0,'v'), (0,-1,'<')):
do_step(level+1, path+dir, points+[(r+dr,c+dc)])
FIELD[r][c] = current
do_step(0, "", [START_POS])
print("No path's found.")
I'm trying to make a factoring program, but it doesn't seem to work with negative number a-, b- and c-inputs.
from fractions import gcd
factor = -1
opp = 0
number = 1
success = 0
a = int(input("a-value: "))
b = int(input("b-value: "))
c = int(input("c-value: "))
factors = []
d = 0
e = 0
while number <= abs(a*c):
#Checking for multiples
if abs(a*c) % number == 0:
factor += 1
factors.append(number)
number += 1
while (factor-opp) >= 0:
#Checking for actual factors
d = int(factors[factor])
e = int(factors[opp])
if (abs(d+e) or abs(d-e)) == abs(b):
success += 1
break
else:
factor -= 1
opp += 1
if success > 0:
if (d+e) == b:
e = e
elif (d-e) == b:
e -= 2*e
elif (e-d) == b:
d -= 2*d
elif (-d-e) == b:
d -= 2*d
e -= 2*e
#Figuring out the equation
if d % a == 0:
d /= a
f = 1
else:
f = a/gcd(d,a)
d /= gcd(d,a)
if e % a == 0:
e /= a
g = 1
else:
g = a/gcd(e,a)
e /= gcd(e,a)
#Displaying the answer
if d >= 0:
d = str("+" + str(int(d)))
if e >= 0:
e = str("+" + str(int(e)))
elif e < 0:
e = str(int(e))
else:
d = str(int(d))
if e >= 0:
e = str("+" + str(int(e)))
elif e < 0:
e = str(int(e))
if f == 1:
if g == 1:
print ("(x" + d + ")(x" + e + ")")
else:
g = str(int(g))
print ("(x" + d + ")(" + g + "x" + e + ")")
elif g == 1:
f = str(int(f))
print ("(" + f + "x" + d + ")(x" + e + ")")
else:
f = str(int(f))
g = str(int(g))
print ("(" + f + "x" + d + ")(" + g + "x" + e + ")")
else:
print("This equation cannot be factored into integers.")
More specifically, the problem is somewhere within this block, I think. I've tested it out with print statements:
while (factor-opp) >= 0:
#Checking for actual factors
d = int(factors[factor])
e = int(factors[opp])
if (abs(d+e) or abs(d-e)) == abs(b):
success += 1
break
else:
factor -= 1
opp += 1
I've searched everywhere: my programming textbook, online searches about inputting negatives, everything. What am I doing wrong here?
Ok I am able to reproduce your issue for a simple testcase like - a=1 , b=0, c=-4 .
The issue is in the line -
if (abs(d+e) or abs(d-e)) == abs(b):
This does not check whether abs(b) is equal to abs(d+e) or abs(d-e) , instead it first evaluates the result of (abs(d+e) or abs(d-e)) , which would return the first non-zero result , and then compare that against abs(b) , so for negative numbers this does not evaluate the result correctly. Change that condition to -
if abs(d+e) == abs(b) or abs(d-e) == abs(b):
or you can also use a set -
if abs(b) in {abs(d+e), abs(d-e)}: #Though I doubt if using set would give any performance improvement because of the overhead of creating a set.
Demo after changes -
a-value: 1
b-value: 0
c-value: -4
(x+2)(x-2)
a-value: 1
b-value: -1
c-value: -6
(x-3)(x+2)
One more thing, there is something you have not considered , when a=-1 , b=-4 , c=-4 , the result should come to -(x+2)(x+2) , but the current program results in (x+2)(x+2) .
If I have 2 numbers in binary form as a string, and I want to add them I will do it digit by digit, from the right most end. So 001 + 010 = 011
But suppose I have to do 001+001, how should I create a code to figure out how to take carry over responses?
bin and int are very useful here:
a = '001'
b = '011'
c = bin(int(a,2) + int(b,2))
# 0b100
int allows you to specify what base the first argument is in when converting from a string (in this case two), and bin converts a number back to a binary string.
This accepts an arbitrary number or arguments:
>>> def bin_add(*bin_nums: str) -> str:
... return bin(sum(int(x, 2) for x in bin_nums))[2:]
...
>>> x = bin_add('1', '10', '100')
>>> x
'111'
>>> int(x, base = 2)
7
Here's an easy to understand version
def binAdd(s1, s2):
if not s1 or not s2:
return ''
maxlen = max(len(s1), len(s2))
s1 = s1.zfill(maxlen)
s2 = s2.zfill(maxlen)
result = ''
carry = 0
i = maxlen - 1
while(i >= 0):
s = int(s1[i]) + int(s2[i])
if s == 2: #1+1
if carry == 0:
carry = 1
result = "%s%s" % (result, '0')
else:
result = "%s%s" % (result, '1')
elif s == 1: # 1+0
if carry == 1:
result = "%s%s" % (result, '0')
else:
result = "%s%s" % (result, '1')
else: # 0+0
if carry == 1:
result = "%s%s" % (result, '1')
carry = 0
else:
result = "%s%s" % (result, '0')
i = i - 1;
if carry>0:
result = "%s%s" % (result, '1')
return result[::-1]
Can be simple if you parse the strings by int (shown in the other answer). Here is a kindergarten-school-math way:
>>> def add(x,y):
maxlen = max(len(x), len(y))
#Normalize lengths
x = x.zfill(maxlen)
y = y.zfill(maxlen)
result = ''
carry = 0
for i in range(maxlen-1, -1, -1):
r = carry
r += 1 if x[i] == '1' else 0
r += 1 if y[i] == '1' else 0
# r can be 0,1,2,3 (carry + x[i] + y[i])
# and among these, for r==1 and r==3 you will have result bit = 1
# for r==2 and r==3 you will have carry = 1
result = ('1' if r % 2 == 1 else '0') + result
carry = 0 if r < 2 else 1
if carry !=0 : result = '1' + result
return result.zfill(maxlen)
>>> add('1','111')
'1000'
>>> add('111','111')
'1110'
>>> add('111','1000')
'1111'
It works both ways
# as strings
a = "0b001"
b = "0b010"
c = bin(int(a, 2) + int(b, 2))
# as binary numbers
a = 0b001
b = 0b010
c = bin(a + b)
you can use this function I did:
def addBinary(self, a, b):
"""
:type a: str
:type b: str
:rtype: str
"""
#a = int('10110', 2) #(0*2** 0)+(1*2**1)+(1*2**2)+(0*2**3)+(1*2**4) = 22
#b = int('1011', 2) #(1*2** 0)+(1*2**1)+(0*2**2)+(1*2**3) = 11
sum = int(a, 2) + int(b, 2)
if sum == 0: return "0"
out = []
while sum > 0:
res = int(sum) % 2
out.insert(0, str(res))
sum = sum/2
return ''.join(out)
def addBinary(self, A, B):
min_len, res, carry, i, j = min(len(A), len(B)), '', 0, len(A) - 1, len(B) - 1
while i>=0 and j>=0:
r = carry
r += 1 if A[i] == '1' else 0
r += 1 if B[j] == '1' else 0
res = ('1' if r % 2 == 1 else '0') + res
carry = 0 if r < 2 else 1
i -= 1
j -= 1
while i>=0:
r = carry
r += 1 if A[i] == '1' else 0
res = ('1' if r % 2 == 1 else '0') + res
carry = 0 if r < 2 else 1
i -= 1
while j>=0:
r = carry
r += 1 if B[j] == '1' else 0
res = ('1' if r % 2 == 1 else '0') + res
carry = 0 if r < 2 else 1
j -= 1
if carry == 1:
return '1' + res
return res
#addition of two binary string without using 'bin' inbuilt function
numb1 = input('enter the 1st binary number')
numb2 = input("enter the 2nd binary number")
list1 = []
carry = '0'
maxlen = max(len(numb1), len(numb2))
x = numb1.zfill(maxlen)
y = numb2.zfill(maxlen)
for j in range(maxlen-1,-1,-1):
d1 = x[j]
d2 = y[j]
if d1 == '0' and d2 =='0' and carry =='0':
list1.append('0')
carry = '0'
elif d1 == '1' and d2 =='1' and carry =='1':
list1.append('1')
carry = '1'
elif (d1 == '1' and d2 =='0' and carry =='0') or (d1 == '0' and d2 =='1' and
carry =='0') or (d1 == '0' and d2 =='0' and carry =='1'):
list1.append('1')
carry = '0'
elif d1 == '1' and d2 =='1' and carry =='0':
list1.append('0')
carry = '1'
else:
list1.append('0')
if carry == '1':
list1.append('1')
addition = ''.join(list1[::-1])
print(addition)
Not an optimal solution but a working one without use of any inbuilt functions.
# two approaches
# first - binary to decimal conversion, add and then decimal to binary conversion
# second - binary addition normally
# binary addition - optimal approach
# rules
# 1 + 0 = 1
# 1 + 1 = 0 (carry - 1)
# 1 + 1 + 1(carry) = 1 (carry -1)
aa = a
bb = b
len_a = len(aa)
len_b = len(bb)
min_len = min(len_a, len_b)
carry = 0
arr = []
while min_len > 0:
last_digit_aa = int(aa[len(aa)-1])
last_digit_bb = int(bb[len(bb)-1])
add_digits = last_digit_aa + last_digit_bb + carry
carry = 0
if add_digits == 2:
add_digits = 0
carry = 1
if add_digits == 3:
add_digits = 1
carry = 1
arr.append(add_digits) # will rev this at the very end for output
aa = aa[:-1]
bb = bb[:-1]
min_len -= 1
a_len_after = len(aa)
b_len_after = len(bb)
if a_len_after > 0:
while a_len_after > 0:
while carry == 1:
if len(aa) > 0:
sum_digit = int(aa[len(aa) - 1]) + carry
if sum_digit == 2:
sum_digit = 0
carry = 1
arr.append(sum_digit)
aa = aa[:-1]
else:
carry = 0
arr.append(sum_digit)
aa = aa[:-1]
else:
arr.append(carry)
carry = 0
if carry == 0 and len(aa) > 0:
arr.append(aa[len(aa) - 1])
aa = aa[:-1]
a_len_after -= 1
if b_len_after > 0:
while b_len_after > 0:
while carry == 1:
if len(bb) > 0:
sum_digit = int(bb[len(bb) - 1]) + carry
if sum_digit == 2:
sum_digit = 0
carry = 1
arr.append(sum_digit)
bb = bb[:-1]
else:
carry = 0
arr.append(sum_digit)
bb = bb[:-1]
else:
arr.append(carry)
carry = 0
if carry == 0 and len(bb) > 0:
arr.append(bb[len(bb) - 1])
bb = bb[:-1]
b_len_after -= 1
if carry == 1:
arr.append(carry)
out_arr = reversed(arr)
out_str = "".join(str(x) for x in out_arr)
return out_str