## do not remove the extra print statements
print('Question 1')
#################################################################
# QUESTION 1                                                    #
#   
# What is the most frequently occuring 6-mer in the fruit fly 
# genome? Below is a path to the Drosophila melanogaster genome.
# this is the same file we used in Week 7. Go through the entire 
# genome and count each k-mer. Then print out the most frequently
# occuring k-mer. You should use overlapping k-mers because we want 
# to consider all of them! Your answer should just contain one line
# that contains only 6 letters, the nucleotides of the most
# frequent 6-mer.
#
#################################################################


genome_fasta = '/autograder/source/dm6.fa'
##add code for question 1 here



## do not remove the extra print statements
print('Question 2')
#################################################################
# QUESTION 2                                                    #
#                                                               #
# For the provided sequences, concatenate them into one sequence
# with no delimiter. Then search through and find the 5th 
# non-overlapping 7-mer in the concatenated sequence. This should 
# be the 5th in order of the sequence, not fifth most abundant.
# The first 7-mer starting at position 0 will be number 1, and so on.
# Your answer should just be one 7-mer on one line, the 5th 
# non-overlapping 7-mer.
#
#################################################################

DNA = ['GCTGATCGTACTACG','GCTACGTACTACTAC','GCGCGTACGCTAC','GCATCTGACGCGCGTAACG']
##add code for question 2 here


## do not remove the extra print statements
print('Question 3')
#################################################################
# QUESTION 3                                                    #
#                                                               #
# Given the following string, write code that will do the 
# following tasks:
# 
# 1. split the string on the newline character ('\n') and assign
#  the resulting elements to a list.
#
# 2. join the elements of the list together using join() and using 
# the empty string as a delimiter.
#
# 3. print out a list of all 2-mers (dinucleotides) in alphabetical
# order. You should not print duplicates. Each distinct k-mer in the 
# resulting sequence should be printed only once. Dont' print the counts,
# just a list of dinucleotides that occur in the concatenated sequence
# in alpabetical order, one dinucleotide per line. Don't print 
# additional content beyond that. 
#
#################################################################

sequences = "ATCGTAGCT\nAATCAGCTCGCTA\nTCTCAGAGATT"
##add code for question 3 here



## do not remove the extra print statements
print('Question 4')
#################################################################
# QUESTION 4                                                    #
#                                                               #
# let's say you have a sequence of length L = 123,456,789 bp.
# How many non-overlapping k-mers of length k=27bp would their be? 
# Print the numerical value of the number of non-overlapping k-mers 
# only. You answer should be just the number.
#
#################################################################

L = 123456789
##add code for question 4 here



## do not remove the extra print statements
print('Question 5')
#####################################################################
# QUESTION 5                                                        #
#                                                                   #
# let's say you have a sequence of length L = 123,456,789 bp.
# How many overlapping k-mers of length k=27bp would their be? 
# Print the numerical value of the number of overlapping k-mers 
# only. You answer should be just the number.
#
#####################################################################

L = 123456789
##add code for question 5 here