#Recurrence relation is defined as Fn = Fn-1 + Fn-2 where Fn-1 are the rabbits that were alive one month ago and Fn-2
# is not only the number ofrabbits that were alive two months ago, but also happens to be the number of offspring for the
# n month.
# What to do:
#1. function must take n and k, where n is the month we're interested in and k is the number of offspring per pair of raabits.
#2. Get the month and litter size from specified file
#3. write the result from the how_many_bunnies functions into a new file
from helperfunctions import write_to_file, make_output_filename, get_nums
input_filename = "filename.txt"
def how_many_bunnies(month, litter_size):
total_buns = 0
if month == 1 or month == 2:
total_buns += 1
else:
total_buns += how_many_bunnies(
month - 1, litter_size) + how_many_bunnies(
month - 2, litter_size) * litter_size
return total_buns
nums = get_nums(input_filename)
bunnies = how_many_bunnies(nums[0], nums[1])
write_to_file(input_filename, str(bunnies))
#What to do: # 1. get the DNA string from the file # 2. make the string into a Seq object with Biopython and specify RNA alphabet # 3. use translate() from BioPython # 4. write protein sequence to file from helperfunctions import write_to_file, make_output_filename, get_string from Bio.Seq import Seq from Bio.Alphabet import IUPAC input_filename = "filename.txt" rna_string = get_string(input_filename) rna_sequence = Seq(rna_string, IUPAC.unambiguous_rna) protein_sequence = rna_sequence.translate(to_stop=True) write_to_file(input_filename, protein_sequence)
from helperfunctions import write_to_file, make_output_filename, make_iterator
from Bio import SeqIO
from Bio.SeqUtils import GC
input_filename = "filename.txt"
format_type = "fasta"
def max_GC_content(input_file, format_type):
max_GC_content = 0.00
max_GC_content_id = ""
generator = make_iterator(input_filename, format_type)
for sequence in generator:
GC_content = GC(
sequence.seq
) #BioPython has a built in way to calculate the GC content of a sequence
if GC_content > max_GC_content:
max_GC_content = GC_content
max_GC_content_id = sequence.id
winner = max_GC_content_id + "\n" + str(max_GC_content)
return winner
answer = max_GC_content(input_filename)
write_to_file(input_filename, answer)
#this chunk keeps tally of the nucleotides at each position by adding to profile as it tranverses each sequence
iterator = make_iterator(input_filename, "fasta")
for sequence in iterator:
length = len(sequence.seq)
if profile == []:
profile = make_matrix(length, 4)
for i in range(0, length):
nucleotide = sequence.seq[i]
profile[i][nucleotides[nucleotide]] += 1
consensus_sequence = ""
#this chunk finds what nucleotide had the most instances per position and adds it to the consensus sequence
for i in range(0, length):
most_nucleotides = max(profile[i])
nucleotide_index = profile[i].index(most_nucleotides)
for key in nucleotides:
if nucleotides[key] == nucleotide_index:
consensus_sequence += key
#this chunk changes profile to a nice string that includes the consensus sequence and the final profile
final_profile = consensus_sequence + "\n"
for nucleotide in ["A", "C", "G", "T"]:
row = []
for i in range(0, length):
row.append(str(profile[i][nucleotides[nucleotide]]))
final_row = nucleotide + ": " + " ".join(row) + "\n"
final_profile += final_row
write_to_file(input_filename, final_profile)
#What we're going to do
#1. get the DNA string
#2. switch each nucleotide to its complement but in lowercase, so it does not affect the conversion of other nucleotides
#3. make the strand uppercase, and then reverse it
#4. write the reverse complement to a new file
#import the functions from helperfunctions.py
from helperfunctions import get_string, write_to_file, make_output_filename
#setting the filename
input_filename = "filename.txt"
#get the DNA string from the file
DNA_string = get_string(input_filename)
# this is the easiest way but man is it ugly
rc1 = DNA_string.replace("A","t")
rc2 = rc1.replace("C","g")
rc3 = rc2.replace("G","c")
rc4 = rc3.replace("T","a")
reverse_complement = rc4.upper()[::-1] #note that the reversal part of this step comes straight from the stack overflow answer
#here: https://stackoverflow.com/questions/931092/reverse-a-string-in-python I didn't
#know the step part
#write reverse complement to output file
write_to_file(input_filename, reverse_complement)
#What to do:
# 1. Get the strings from file
# 2. use find() on the DNA string until it returns -1, everytime one is found, change the first base to *
# 3. keep track of the indexes
# 4. write indexes to file
from helperfunctions import write_to_file, get_strings, make_output_filename
input_filename = "filename.txt"
dna_strings = get_strings(input_filename)
dna_string = dna_strings[0].strip()
substring = dna_strings[1].strip()
substring_index = dna_string.find(substring)
indexes = []
while (substring_index != -1):
indexes.append(str(substring_index + 1))
dna_string = dna_string[:substring_index] + "*" + dna_string[
substring_index + 1:]
substring_index = dna_string.find(substring)
index_string = " ".join(indexes)
write_to_file(input_filename, index_string)
#this was tricky because the answer was in 1-based numbering and I goofed.
#What to do:
#1. make a little hammy distance function to compare two DNA sequences
#2. Extract both sequences from a single file
#3. write total point mutations to file
from helperfunctions import get_strings, write_to_file, make_output_filename
input_filename = "filename.txt"
def hamming_distance(DNA_seq1, DNA_seq2):
Dh = 0
for i in range(0, len(DNA_seq1)):
if DNA_seq1[i] != DNA_seq2[i]:
Dh += 1
return Dh
sequences = get_strings(input_filename)
point_mutations = hamming_distance(sequences[0], sequences[1])
write_to_file(input_filename, str(point_mutations))
# heterozygote
# What to do:
# make a function for this
# 1. get the total number of organisms, and the total - 1 for the second organism
# 2. calcultate the probability it will be dominant homozygote or heterozygote
# 3. write this probability into a file
from helperfunctions import write_to_file, get_nums, make_output_file
input_filename = "filename.txt"
def prob_dominant_allele(k, m, n):
#k homozygous dominant, m heterozygous, n homozygous recessive
total_organisms = k + m + n
prob_kk = (k / total_organisms * (k - 1) / (total_organisms - 1))
prob_km = (k / total_organisms * m / (total_organisms - 1)) * 2
prob_kn = (k / total_organisms * n / (total_organisms - 1)) * 2
prob_mm = (m / total_organisms * (m - 1) / (total_organisms - 1) * .75)
prob_mn = (m / total_organisms * n / (total_organisms - 1) * .5) * 2
total_prob = prob_kk + prob_km + prob_kn + prob_mm + prob_mn
return total_prob
organism_nums = get_nums(input_filename)
probability = prob_dominant_allele(organism_nums[0], organism_nums[1],
organism_nums[2])
write_to_file(input_filename, str(probability))
#What I have to do
#1. Open file and read DNA string
#2. Replace every T nucleotide with a U
#3. write new RNA string into a file
from helperfunctions import get_string, write_to_file, make_output_filename
#setting filenames
input_filename = "filename.txt"
#open file and prepare DNA string
DNA_string = get_string(input_filename)
#replace every 'T' with 'U'
RNA_string = DNA_string.replace("T", "U")
#open output file and write RNA string to it
write_to_file(input_filename, RNA_string)
#What I have to do
#1. Open the file with the DNA string
#2. Read from the file
#3. Keep tally of nucleotides
#4. Create a new file and write the tally in the order A C G and T
from helperfunctions import get_string, write_to_file, make_output_filename
#setting file names
input_filename = "filename.txt"
#opening file and setting up DNA string for counting
DNA_string = get_string(input_filename)
#make a tally of nucleotides
nucleotide_tally = (str(DNA_string.count("A")) + " " +
str(DNA_string.count("C")) + " " +
str(DNA_string.count("G")) + " " +
str(DNA_string.count("T")))
#write tally to new file
write_to_file(input_filename, nucleotide_tally)
