def __init__(self, strbases):
# Initialize the sequence with the value
# passed as argument when creating the object
if Seq0.is_valid_sequence(strbases):
print("New sequence created")
self.strbases = strbases
else:
self.strbases = "Error"
print("incorrect sequence detected!")
import Seq0
FOLDER = "./sequences/"
ID = "U5.txt"
U5_Seq = Seq0.seq_read_fasta(FOLDER + ID)
fragment = U5_Seq[0:20]
print("-----| Exercise 7 |------ \nGene U5: \nFrag: " + str(fragment) +
"\nComp: " + str(Seq0.seq_complement(fragment)))
import Seq0
folder = "../Session-04/"
gene_list = ["RNU6_269P", "U5", "ADA", "FRAT1", "FXN"]
print("-----| Exercise 5 |------ \n")
for gene in gene_list:
bases_dict = {}
filename = folder + gene + ".txt"
A, C, T, G = Seq0.seq_count_bases(filename)
bases_dict["A"] = A
bases_dict["T"] = T
bases_dict["C"] = C
bases_dict["G"] = G
print(f"Gene {gene}: {bases_dict}")
import Seq0
ID = "U5.txt"
FOLDER = "./sequences/"
U5_Seq = Seq0.seq_read_fasta(FOLDER + ID)
print("The first 20 bases are: ", U5_Seq[0:20])
import Seq0
GENE_FOLDER = "./sequences/"
gene_list = ["U5", "ADA", "FRAT1", "FXN"]
try:
if Seq0.correct_directory(GENE_FOLDER) == True:
print("------- |Exercise 3|-------")
for gene in gene_list:
sequence = Seq0.seq_read_fasta(GENE_FOLDER + gene + ".txt")
print("Gene " + str(gene) + " ---->" + " Length: " +
str(Seq0.seq_len(sequence)))
except FileNotFoundError:
print("ERROR. INCORRECT FILE")
except ZeroDivisionError:
print("ERROR. INCORRECT DIRECTORY")
import Seq0
GENE_FOLDER = "./sequences/"
bases = ["A", "C", "T", "G"]
gene_list = ["U5", "ADA", "FRAT1", "FXN", "RNU6_269P"]
print("-----| Exercise 8 |------")
for gene in gene_list:
ID = Seq0.seq_read_fasta(GENE_FOLDER + gene + ".txt")
dict_bases = Seq0.seq_count(ID)
min_value = 0
best_base = ""
for base, value in dict_bases.items():
while value > min_value:
min_value = value
best_base = base
print("Gene", gene, ": Most frequent Base: ", best_base, ": value",
min_value)
# Implement the seq_count_base(seq, base) function, that calculates the number of times the given base appears in the sequence.
# It should be written in the Seq0.py file.
import Seq0
GENE_FOLDER = "./Sequences/"
gene_list = ["U5", "ADA", "FRAT1", "FXN"]
base_list = ["A", "C", "T", "G"]
print("-----| Exercise 4|-----")
for gene in gene_list:
sequence = Seq0.seq_read_fasta(GENE_FOLDER + gene + ".txt")
print("Gene", gene)
for base in base_list:
print(base + ":", Seq0.seq_count_base(sequence, base))
import Seq0
from Seq0 import Seq
seq_list1 = Seq0.generate_seqs("A", 3)
seq_list2 = Seq0.generate_seqs("AC", 5)
print("List 1:")
Seq.print_seqs(seq_list1)
print()
print("List 2:")
Seq.print_seqs(seq_list2)
import Seq0
GENE_FOLDER = "./sequences/"
gene_list = ["U5","ADA","FRAT1","FXN"]
print("-----|Excersise 5|-----")
for gene in gene_list:
sequence = Seq0.seq_read_fasta(GENE_FOLDER + gene + ".txt")
print('Gene',gene,':',Seq0.seq_count(sequence))
import Seq0
FOLDER = "../SESSION-04/"
FILENAME = "U5.txt"
body = Seq0.seq_read_fasta(FOLDER + FILENAME)[0:20]
print("DNA file:", FILENAME)
print("The first 20 DNA bases are:\n", body)
# Implement the seq_complement(seq) function, that calculates a new sequence composed of the complement base of each of the original bases.
# A and T are complement, as well as C and G.
import Seq0
FOLDER = "./Sequences/"
ID = "U5.txt"
U5_seq = Seq0.seq_read_fasta(FOLDER + ID)
print("-----| Exercise 7|-----")
print("Frag: ", U5_seq[0:20])
print("Comp: ", Seq0.seq_complement(U5_seq[0:20]))
# Implement the seq_complement(seq) function, that calculates a new sequence composed of the complement base of each of the original bases.
# The bases work in pairs. A and T are complement, as well as C and G. Therefore, the complement sequence of "ATTCG" is "TAAGC". It should be written in the Seq0.py file
#Desription: Write a python program for creating a new fragment composed of the first 20 bases of the U5 gene.
# This fragment should be printed on the console. Then calculate the complement of this fragment by calling the seq_complement() function. Finally print it on the console
import Seq0
print("Gene U5:")
sequence = Seq0.seq_read_fasta("./Sequences/U5.txt")[0:20]
print("Frag:", sequence)
print("Rev:", Seq0.seq_complement(sequence))
import Seq0
FOLDER = "./Sequences/"
gene_list = ["U5", "ADA", "FRAT1", "FXN", "RNU6_269P"]
DNA_bases = ["A", "C", "T", "G"]
print("---|EXERCISE 5|---")
for gene in gene_list:
sequence = Seq0.seq_read_fasta(FOLDER + gene + ".txt")
print("Gene " + gene + ": ", Seq0.seq_count(sequence))
import Seq0
ID = "U5.txt"
FOLDER = "./Sequences/"
U5_Seq = Seq0.seq_read_fasta(FOLDER + ID)[0:20]
print("Gene U5:")
print("Frag:", U5_Seq)
print("Comp:", Seq0.seq_complement(U5_Seq))
import Seq0
GENE_FOLDER = './sequences_downloaded/'
gene_list = ['U5', 'ADA', 'FRAT1', 'FXN']
print('-------Exercise 8---------')
for gene in gene_list:
sequence = Seq0.seq_read_fasta(GENE_FOLDER + gene)
print('Gene', gene,': Most frequent base:', (Seq0.most_common_base(Seq0.seq_count(sequence))))
import Seq0
GENE_FOLDER = "./sequences/"
gene_list = ["U5", "ADA", "FRAT1", "FXN"]
print("-------| Exercice 3 | -------")
for gene in gene_list:
sequence = Seq0.seq_read_fasta(GENE_FOLDER + gene + ".txt")
print("Gene " + gene + " ---> ", str(Seq0.seq_len(sequence)))
import Seq0
GENE_FOLDER = "./sequences/"
gene_list = ["U5"," ADA", "FRAT1", "FXN"]
print("-----| Exercise 3 |------")
for gene in gene_list:
sequence = Seq0.seq_read_fasta(GENE_FOLDER + gene + ".txt")
print ("Gene", gene, "---> Length", Seq0.seq_len(sequence))
import Seq0
ID = "U5.txt"
U5_Seq = Seq0.seq_read_fasta(ID)
complement = {"A": "T", "C": "G", "T": "A", "G": "C"}
original = U5_Seq[0:20]
cmp = "".join(complement[letter] for letter in original)
print("-----| Exercise 7 |-----")
print("The complement is: {}".format(cmp))
import Seq0
FOLDER = './Sequences/'
gene_list = ['U5', 'ADA', 'FRAT1', 'FXN']
print('-----| Exercise 3 |------')
for gene in gene_list:
sequence = Seq0.seq_read_fasta(FOLDER + gene + '.txt')
print('Gene ' + gene + '---> Length: ' + str(Seq0.seq_len(sequence)))
import Seq0
GENE_FOLDER = "./sequences/"
gene_list = ["U5", "ADA", "FRAT1", "FXN"]
print("-----|Excersise 3|-----")
for gene in gene_list:
sequence = Seq0.seq_read_fasta(GENE_FOLDER + gene + ".txt")
print('Gene' + gene + '---> lenght: ' + str(Seq0.seq_len(sequence)))
import Seq0
FOLDER = './sequences/'
ID = 'U5.txt'
U5_seq = Seq0.seq_read_fasta(FOLDER + ID)[0:20]
complement = Seq0.seq_complement(U5_seq)
print('Gene U5:')
print('Frag:', U5_seq)
print('Comp:', complement)
import Seq0
GENE_FOLDER = './sequences_downloaded/'
gene_list = ['U5', 'ADA', 'FRAT1', 'FXN']
print('-------Exercise3---------')
for gene in gene_list:
sequence = Seq0.seq_read_fasta(GENE_FOLDER + gene)
print('Gene', gene, '-------> length:', Seq0.seq_len(sequence))
import Seq0
GENE_FOLDER = "./sequences/"
ID = "U5.txt"
U5_seq = Seq0.seq_read_fasta(GENE_FOLDER + ID)
print("------|EXERCISE 6|------")
print("Gene " + ID)
print("Fragment:", U5_seq[0:20])
print("Reverse:", Seq0.seq_reverse(U5_seq[0:20]))
import Seq0
GENE_FOLDER = "./sequences/"
gene_list = ["U5", "ADA", "FRAT1", "FXN"]
base_list = ["A", "C", "G", "T"]
try:
if Seq0.correct_directory(GENE_FOLDER) == True:
print("\n" + "------|Exercise 5|------")
for gene in gene_list:
sequence = Seq0.seq_read_fasta(GENE_FOLDER + gene + ".txt")
print("\n" + "Gene" + gene)
for base in base_list:
print(base + ":" + str(Seq0.seq_count_bases(sequence, base)))
except FileNotFoundError:
print("ERROR. INCORRECT FILE")
except ZeroDivisionError:
print("Error. INCORRECT DIRECTORY")
import Seq0
print("We are testing Seq.py module")
Seq0.seq_ping()
import Seq0
GENE_FOLDER = "./sequences/"
gene_list = ["U5", "ADA", "FRAT1", "FXN"]
print("-----| Exercise 8 |------")
for gene in gene_list:
sequence = Seq0.seq_read_fasta(GENE_FOLDER + gene + ".txt")
print("Gene", gene, "Most frequent Base: ", Seq0.most_frequent(sequence))
import Seq0
FOLDER = "./sequences/"
FILE = "U5"
try:
if Seq0.correct_directory(FOLDER) == True:
sequence = Seq0.seq_read_fasta(FOLDER + FILE + ".txt")
fragment = sequence[0:20]
reverse_fragment = Seq0.seq_reverse(fragment)
print("------|Exercise 6|-------")
print("Frag: " + str(fragment))
print("Rev : " + str(reverse_fragment))
except FileNotFoundError:
print("ERROR.INCORRECT FILE")
except ZeroDivisionError:
print("ERROR. INCORRECT DIRECTORY")
import Seq0
GENE_FOLDER = "./sequences/"
gene_list = ["U5", "ADA", "FRAT1", "FXN"]
for gene in gene_list:
seque = Seq0.seq_read_fasta(GENE_FOLDER + gene + ".txt")
seqq = seque[0:20]
print("Gene", gene, ":", Seq0.seq_reverse(seqq))
for i in seq:
if i == "A":
x = "T"
elif i == "C":
x = "G"
elif i == "G":
x = "C"
elif i == "T":
x = "A"
print("ola")
seq = ["A", "C", "A", "A", "T", "G", "G"]
gene_dict = {"A", "C", "G", "T"}
for d in seq:
if gene_dict[d] == "A":
d = "T"
import Seq0
folder = "../Session-04/"
genes_list = ["RNU6_269P", "U5", "ADA", "FRAT1", "FXN"]
print("-----| Exercise 8 |------ \n")
for gene in genes_list:
A, C, T, G = Seq0.seq_count_bases(folder + gene + ".txt")
bases_dict = {"A": A, "C": C, "T": T, "G": G}
max_base = max([A, C, G, T])
for k, v in bases_dict.items():
if v == max_base:
print(f"Gene {gene}: Most frequent Base: {k}")
import Seq0
GENE_FOLDER = './sequences/'
gene_list = ['U5', 'ADA', 'FRAT1', 'FXN']
print('-----------|EXERCISE 8|--------')
for gene in gene_list:
sequence = Seq0.seq_read_fasta(GENE_FOLDER + gene + '.txt')
A, C, G, T = sequence.count('A'), sequence.count('C'), sequence.count('G'), sequence.count('T')
if A >= C and A >=G and A >= T:
print ('Gene ', gene, ': Most frequent Base is A')
elif C >= A and C >= G and C >= T:
print('Gene ', gene, ': Most frequent Base is C')
elif G >= A and G >= C and G >= T:
print('Gene ', gene, ': Most frequent Base is G')
elif T >= A and T >= C and T >= G:
print('Gene ', gene, ': Most frequent Base is T')
else:
print('Gene ', gene, ': Most frequent Base is 0')