## do not remove the extra print statements
print('Question 1')
#################################################################
# QUESTION 1                                                    #
# 
# Given the RNA sequence defined below, write an If-statement 
# that will print the sequence if the length is greater than or 
# equal to 10. In addition, it should print the length of the 
# sequence if it is not greater than or equal to 10. Either way
# there should be one line of output.
#################################################################


RNA = "AUGCUAGCUA"
##add code for question 1 here


## do not remove the extra print statements
print('Question 2')
#################################################################
# QUESTION 2                                                    #
#                                                               #
# The following code defines a sequence and also defines a      # 
# dictionary called "complement", which contains a mapping from #
# a given DNA nucleotide to its complementary nucleotide.
#
# Then, the code uses a "For-loop" to loop through each         #
# one at a time, and prints out each character to illustrate    #
# visiting each base in the sequence.
#
# Please modify the following function to, instead of printing  #
# out each character, create a complementary sequence called    # 
# "complementary", which contains the complementary DNA sequence#
# as a python string. You don't have to reverse, just complement#
#  it. For example, the complementary sequence of "ATG" would be#
#  "TAC".      
#
# Then finally, once your complementary sequence is complete    #
# and the same length as the input sequence, you can print out  #
# the resulting string,
#
#################################################################


##add code for question 2 here
DNA = 'TGAGTCGAGCTCGCTAGTAAAGCTCGTAG'
complement = {'A':'T','C':'G','G':'C','T':'A'}
for b in DNA:
    print(b)


## do not remove the extra print statements
print('Question 3')
#################################################################
# QUESTION 3                                                    #
#                                                               #
# First, for the list of DNA sequences below, combine them into #
# one sequence by concatenation (hint: you should be able to do # 
# that in one step). Don't print out the resulting sequence 
#
# Second, calculate the GC-content for the concatenated 
# sequence you just print and print the GC-content as well.
# Print the GC-content in percentage on line line to 2 decimal 
# places
#                                                               #
#################################################################


##add code for question 3 here
DNA = ['GCTGATCGTACTACG','GCTACGTACTACTAC','GCGCGTACGCTAC','GCATCTGACGCGCGTAACG']



## do not remove the extra print statements
print('Question 4')
#################################################################
# QUESTION 4                                                    #
#                                                               #
# For the provided list of RNA sequences, please loop through   #
# them and print them out if they are a valid open reading frame
# We have discussed the criteria for ORFs in class, so this 
# should hopefully be clear.
#                                                               #
#################################################################

L = ['ATGGCATCCGTCCATGA','ATGGCGTATGCATCACCATAA','ATGGCATTGAACTGTCACTTA','ATCAACGGTCACGTACGCATATAG']
##add code for question 4 here



## do not remove the extra print statements
print('Question 5')
#####################################################################
# QUESTION 5                                                        #
#                                                                   #
# For the provided DNA sequence, produce the Rumer's transformation #
# of the sequence. Meaning, this is a mapping, much like complement #
# except it uses the following mapping:
#
# A -> C
# C -> A
# G -> T
# T -> G
#
# Your result should therefore be one sequence on line line. 
#
#####################################################################

DNA = 'AACTTAGGCATACTGACTATGATGTACG'
##add code for question 5 here