Fizzizist/rosalind-solutions
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update PROB

Browse Source
This commit is contained in:
Fizzizist 2025-02-18 21:12:09 -05:00
parent 222e3ee447
commit 389773d411
1 changed files with 16 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
python/PROB.py
View File

@ -4,39 +4,44 @@ Solutions to the PROB Rosalind Problem - Introduction to Random Strings
Author: Peter Vlasveld Author: Peter Vlasveld
Date: 20190222 Date: 20190222
""" """
import math import math
#Read in file content into list # Read in file content into list
f1 = open("rosalind_prob.txt") f1 = open("rosalind_prob.txt")
content = f1.readlines() content = f1.readlines()
f1.close() f1.close()
""" """
Function to calculate the probability of the exact sequence given the GC-content Function to calculate the probability of the exact sequence given the
GC-content
@param gc - the GC-content given @param gc - the GC-content given
@param seq - the sequence being studied @param seq - the sequence being studied
@return - the raw probability value @return - the raw probability value
""" """
def calcProb(gc, seq): def calcProb(gc, seq):
# get probability for just one nucleotide # get probability for just one nucleotide
gchalf = gc/2.0 gchalf = gc / 2.0
athalf = (1.0-gc)/2.0 athalf = (1.0 - gc) / 2.0
# multiply all of the probability values for each letter in the sequence # multiply all of the probability values for each letter in the sequence
prob = 1.0 prob = 1.0
for i in range(0, len(seq)): for i in range(0, len(seq)):
if seq[i] == 'A' or seq[i] == 'T': if seq[i] == "A" or seq[i] == "T":
prob *= athalf prob *= athalf
elif seq[i] == 'G' or seq[i] == 'C': elif seq[i] == "G" or seq[i] == "C":
prob *= gchalf prob *= gchalf
# return the probability value # return the probability value
return prob return prob
# take the log of the probabilities returned by calcProb # take the log of the probabilities returned by calcProb
# format them to 3 decimal places # format them to 3 decimal places
gcCons = content[1].split( ) gcCons = content[1].split()
finalProbs = [] finalProbs = []
for i in gcCons: for i in gcCons:
rawProb = calcProb(float(i), content[0]) rawProb = calcProb(float(i), content[0])
@ -44,3 +49,4 @@ for i in gcCons:
# print the probabilities with spaces in between # print the probabilities with spaces in between
print(" ".join(finalProbs)) print(" ".join(finalProbs))