def info(seq):
s = Seq(seq)
s_length = s.len()
counter_A = s.count_base("A")
counter_C = s.count_base("C")
counter_G = s.count_base("G")
counter_T = s.count_base("T")
per_A = "{:.1f}".format(100 * counter_A / s_length)
per_C = "{:.1f}".format(100 * counter_C / s_length)
per_G = "{:.1f}".format(100 * counter_G / s_length)
per_T = "{:.1f}".format(100 * counter_T / s_length)
response_message = f"""Sequence: {s}
f"Total length: {s_length}"
A: {counter_A} ({per_A}%)
C: {counter_C} ({per_C}%)
G: {counter_G} ({per_G}%)
T: {counter_T} ({per_T}%)"""
return response_message
from P1.Seq1 import Seq
print('-----| Practice 1, Exercise 4 |------')
seq1 = Seq()
seq2 = Seq("ACTGA")
seq3 = Seq("Invalid sequence")
print("Sequence 1 : (Length: ", seq1.len(), ')', seq1)
print("Sequence 2 : (Length: ", seq2.len(), ')', seq2)
print("Sequence 3 : (Length: ", seq3.len(), ')', seq3)
def do_GET(self):
"""This method is called whenever the client invokes the GET method
in the HTTP protocol request"""
# Define the type of content returned by the server
content_type = "text/html"
# Define the sequences that we are going to use in "get" and the bases for exercise 4
sequence = ["GTAGCA", "ACGTTA", "CGTAGG", "ATTGTC"]
all_bases = ["A", "C", "G", "T"]
# Print the request line
termcolor.cprint(self.requestline, 'green')
# Processing the request line
req = self.requestline.split(" ")
# Path will be: "/"
path = req[1]
# We will need to split the "?" in order to leave the msg alone
argument = path.split("?")
# We define our first argument to determine if we could continue or an error in thrown
arg0 = argument[0]
# All the information appears in "form-4.html"
if arg0 == "/":
contents = Path("form-4.html").read_text()
status = 200
elif arg0 == "/ping":
contents = """
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title> ping </title >
</head >
<body>
<h2> PING ok!</h2>
<p> The SEQ2 Server in running... </p>
<a href="/">Main page</a>
</body>
</html>
"""
status = 200
elif arg0 == "/get":
# We define our second argument, the one after the "?" that we have split.
arg1 = argument[1]
# To split the "&" that is after the value
args = arg1.split("&")
# Is necessary to split the "=" after our name ("msg")
name, value = args[0].split("=")
# We define the argument n
n = int(value)
seq = sequence[n - 1]
contents = f"""
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title> get </title >
</head >
<body>
<h2>Sequence number {n}</h2>
<p> {seq}</p>
<a href="/">Main page</a>
</body>
</html>
"""
status = 200
elif arg0 == "/gene":
# We define our second argument, the one after the "?" that we have split.
arg1 = argument[1]
# To split the "&" that is after the value
args = arg1.split("&")
# Is necessary to split the "=" after our name ("msg")
name, gene_name = args[0].split("=")
# Sequence of the gene
s = Seq()
s_string = str(s.read_fasta(FOLDER + gene_name))
contents = f"""
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title> gene </title >
</head >
<body>
<h2>Gene {gene_name}</h2>
<textarea readonly rows="20" cols="80"> {s_string} </textarea>
<a href="/">Main page</a>
</body>
</html>
"""
status = 200
elif arg0 == "/operation":
# We define our second argument, the one after the "?" that we have split.
arg1 = argument[1]
# To split the "&" that is after the value
args = arg1.split("&")
# Name and values (=arguments)
#seq in order to create the sequence
name, seq = args[0].split("=")
#op are the different options that can be chosen after the sequence is written
name, op = args[1].split("=")
#Introduce the sequence
s = Seq(seq)
if "info" in op:
s = Seq(seq)
s_length = s.len()
list1 = []
list2 = []
for b in all_bases:
count_b = s.count_base(b)
p = round(count_b * (100 / s_length),
1) # percentage calculation with just 1 decimal
list1.append(
count_b) # list 1: where we put the total bases
list2.append(
p
) # list2 : where we put the percentage of all the bases
response = f"""
Total length: {s_length}
<p>A: {list1[0]} ({list2[0]}%)</p>
<p>C: {list1[1]} ({list2[1]}%)</p>
<p>G: {list1[2]} ({list2[2]}%)</p>
<p>G: {list1[3]} ({list2[3]}%)</p>
"""
elif "comp" in op:
response = s.complement()
elif "rev" in op:
response = s.reverse()
contents = f"""
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title> operation </title >
</head >
<body>
<h2>Sequence :</h2>
<p>{seq}</p>
<h2>Operation :</h2>
<p>{op}</p>
<h2>Result :</h2>
<p>{response}</p>
<a href="/">Main page</a>
</body>
</html>
"""
status = 200
else:
# Error.html file
contents = Path("Error.html").read_text()
status = 404
# Generating the response message
self.send_response(status)
# Define the content-type header:
self.send_header('Content-Type', content_type)
self.send_header('Content-Length', len(contents.encode()))
# The header is finished
self.end_headers()
# Send the response message
self.wfile.write(contents.encode())
return
from P1.Seq1 import Seq
print("-----| Exercise 1 |------")
seq = Seq("ACTGA")
print("Sequence" + str(1) + ": (Length: " +str(seq.len()), ")" + str(seq))
# -- form the JSON received
response = json.loads(data1)
# Information of the gene
Description = response["desc"]
termcolor.cprint(f"Gene:", "green", end=" ")
print(gene_input)
termcolor.cprint(f"Description:", "green", end=" ")
print(Description)
# Introduce the sequence
seq = Seq(response["seq"])
s_length = seq.len()
counter_A = seq.count_base(all_bases[0])
counter_C = seq.count_base(all_bases[1])
counter_G = seq.count_base(all_bases[2])
counter_T = seq.count_base(all_bases[3])
per_A = "{:.1f}".format(100 * counter_A / s_length)
per_C = "{:.1f}".format(100 * counter_C / s_length)
per_G = "{:.1f}".format(100 * counter_G / s_length)
per_T = "{:.1f}".format(100 * counter_T / s_length)
# Print the length
termcolor.cprint(f"Total length:", "green", end=" ")
print(s_length)
termcolor.cprint(f"A", "blue", end=" ")
print(f"{counter_A} {per_A}%")
exit()
r1 = conn.getresponse()
print(f"Response received!: {r1.status} {r1.reason}")
data1 = r1.read().decode()
gene = json.loads(data1)
termcolor.cprint("Gene", 'green', end="")
print(f": {name}")
termcolor.cprint("Description", 'green', end="")
print(f": {gene['desc']}")
genestr = gene['seq']
s = Seq(genestr)
length = s.len()
termcolor.cprint("Total length", 'green', end="")
print(f": {length}")
for e in BASES:
count = s.count_base(e)
percentage = round(s.count_base(e) * (100 / s.len()), 2)
termcolor.cprint(f"{e}", 'blue', end="")
print(f": {count} ({percentage}%)")
dictionary = s.seq_count()
list_values = list(dictionary.values())
max_base = max(list_values)
termcolor.cprint("Most frequent base", 'green', end="")
print(f": {BASES[list_values.index(max_base)]}")
from P1.Seq1 import Seq
print("-----| Practice 1, Exercise 9 |------")
FOLDER = "../Session-04/"
TypeDoc = '.txt'
seq = Seq(FOLDER + 'U5' + TypeDoc)
seq.read_fasta(FOLDER + 'U5' + TypeDoc)
print("Sequence ", seq, ':', "(Length: ", seq.len(), ')', seq)
print(" Bases:", seq.seq_count())
print(' Rev: ', seq.reverse(), '\n Comp: ', seq.complement())
from P1.Seq1 import Seq
print('----| Exercise 1 |------')
seq = Seq("ACTGA")
print("Sequence 1:", "(Length: ", seq.len(), ')', seq)
def do_GET(self):
"""This method is called whenever the client invokes the GET method
in the HTTP protocol request"""
# Print the request line
termcolor.cprint(self.requestline, 'green')
request = self.requestline.split(' ')
raw_arg = request[1]
clean_arg = raw_arg.split('?')
argument = clean_arg[0]
if argument == '/':
contents = Path('form-4.html').read_text()
elif argument == '/ping':
contents = f"""
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title> PING </title >
</head >
<body>
<h2> PING OK!</h2>
<p> The SEQ2 server is running </p>
<a href="/">Main page</a>
</body>
</html> """
elif argument == '/get':
argument1 = clean_arg[1].split('&')
name, value = argument1[0].split('=')
value = int(value)
sequence = Sequences[value]
contents = f"""
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title> GET </title >
</head >
<body>
<h2> Sequence number {value}</h2>
<p> {sequence} </p>
<a href="/">Main page</a>
</body>
</html> """
elif argument == '/gene':
argument1 = clean_arg[1].split('&')
name, gene = argument1[0].split('=')
sequence = Seq()
sequence.read_fasta(FOLDER + gene + TypeDoc)
gene_str = str(sequence)
contents = f"""
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title> GENE </title >
</head >
<body>
<h2> Gene: {gene}</h2>
<textarea readonly rows="20" cols="80"> {gene_str} </textarea>
<br>
<br>
<a href="/">Main page</a>
</body>
</html>"""
elif argument == '/operation':
argument1 = clean_arg[1].split('&')
name, sequence = argument1[0].split("=")
name, operation = argument1[1].split("=")
seq = Seq(sequence)
if operation == 'comp':
result = seq.complement()
elif operation == 'rev':
result = seq.reverse()
else:
length = seq.len()
num_bases = []
perc_bases = []
for element in bases:
counter_bases = seq.count_base(element)
percentage = round(
(seq.count_base(element) * 100 / seq.len()), 2)
num_bases.append(counter_bases)
perc_bases.append(percentage)
result = f"""
<p>Total length: {length}</p>
<p>A: {num_bases[0]} ({perc_bases[0]}%)</p>
<p>C: {num_bases[1]} ({perc_bases[1]}%)</p>
<p>G: {num_bases[2]} ({perc_bases[2]}%)</p>
<p>T: {num_bases[3]} ({perc_bases[3]}%)</p>"""
contents = f"""
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title> OPERATION </title >
</head >
<body>
<h2>Sequence</h2>
<p>{seq}</p>
<h2>Operation</h2>
<p>{operation}</p>
<h2>Result</h2>
<p>{result}</p>
<br>
<br>
<a href="/">Main page</a>
</body>
</html>"""
else:
contents = Path('error.html').read_text()
# Generating the response message
self.send_response(200) # -- Status line: OK!
# Define the content-type header:
self.send_header('Content-Type', 'text/html')
self.send_header('Content-Length', len(str.encode(contents)))
# The header is finished
self.end_headers()
# Send the response message
self.wfile.write(str.encode(contents))
return
response = json.loads(data1)
# Information of the gene
Description = response["desc"]
termcolor.cprint(f"Gene:","green",end=" ")
print(G)
termcolor.cprint(f"Description:","green",end=" ")
print(Description)
# Introduce the sequence
s = Seq(response["seq"])
s_length = s.len()
termcolor.cprint(f"Total length: ","green",end="")
print(s_length)
for b in all_bases:
count_b = s.count_base(b)
p =round(count_b *( 100 / s_length),1)#percentage calculation with just 1 decimal
termcolor.cprint(f"{b}", "blue", end=" ")
print(f"{count_b} {p} %")
dict = s.count() # method from P1 to find the most repeated base
list_dict = list(dict.values())
maximum = max(list_dict)
freq_base = all_bases[list_dict.index(maximum)]
termcolor.cprint("Most frequent base : ","green",end="")
print(freq_base)
from P1.Seq1 import Seq
print("-----|Practice 1, Exercise 4|-----")
s1 = Seq()
s2 = Seq("ACTGA")
s3 = Seq("jskdhs")
print("Sequence 1: " + ": (Length:" + str(s1.len()) + " ) " + str(s1))
print("Sequence 2: " + ": (Length:" + str(s2.len()) + " ) " + str(s2))
print("Sequence 3: " + ": (Length:" + str(s3.len()) + " ) " + str(s3))
def do_GET(self):
"""This method is called whenever the client invokes the GET method
in the HTTP protocol request"""
# Define the type of content returned by the server
content_type = "text/html"
# Print the request line
termcolor.cprint(self.requestline, 'green')
# Processing the request line
req = self.requestline.split(" ")
# Path will be: "/"
path = req[1]
# We will need to split the "?" in order to leave the msg alone
argument = path.split("?")
# We define our first argument to determine if we could continue or an error in thrown
arg0 = argument[0]
contents = Path("Error.html").read_text()
status = 404
# All the information appears in "form-4.html"
if arg0 == "/":
contents = Path("index.html").read_text()
status = 200
elif arg0 == "/listSpecies":
try:
Endpoint = "/info/species"
conn = http.client.HTTPConnection(Server)
conn.request("GET", Endpoint + Parameters)
r1 = conn.getresponse()
data1 = r1.read().decode("utf-8")
response = json.loads(data1)
d = response["species"]
length = len(d)
limit = argument[1]
l = limit.split("=")[1]
limit_ = l.split("&msg")[0]
counter = 0
contents = """
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title>Basic Level</title >
</head >
<body style="background-color:lightblue;">
</body>
</html>
"""
contents += f"<p>The total number of species in the ensembl is : {length} </p>"
if len(limit[1]) in range(1, length):
contents += f"<p>The limit you have selected is: {limit_} </p>"
contents += f"<p>The name of the species are: </p>"
for i in d:
if counter < int(limit_):
contents += f"* {i['display_name']} "
contents += f"<br><br>"
counter += 1
else:
contents = Path("Error.html").read_text()
status = 404
contents += f"""<p><a href="/">Main page </a></body></html>"""
status = 200
except ValueError:
contents = Path("Error.html").read_text()
status = 404
except KeyError:
contents = Path("Error.html").read_text()
status = 404
elif arg0 == "/karyotype":
try:
s = argument[1]
species = s.split("=")[1]
Endpoint = f"/info/assembly/{species}"
conn = http.client.HTTPConnection(Server)
conn.request("GET", Endpoint + Parameters)
r1 = conn.getresponse()
data1 = r1.read().decode("utf-8")
karyotype_response = json.loads(data1)
k = karyotype_response["karyotype"]
contents = """
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title>Basic Level</title >
</head >
<body style="background-color:lightblue;">
"""
contents += f"The names of the chromosomes are:"
for j in k:
contents += f"<p> * {j} </p>"
contents += f"""<p><a href="/">Main page </a></body></html>"""
status = 200
except ValueError:
contents = Path("Error.html").read_text()
status = 404
except KeyError:
contents = Path("Error.html").read_text()
status = 404
elif arg0 == "/chromosomeLength":
try:
Endpoint = "/info/assembly/"
s = argument[1]
spl = s.split("=")
species= spl[1].split("&")
conn = http.client.HTTPConnection(Server)
conn.request("GET", Endpoint + species[0] + Parameters)
r1 = conn.getresponse()
data1 = r1.read().decode("utf-8")
cl = json.loads(data1)
n = cl['top_level_region']
contents = """
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title>Basic Level</title >
</head >
<body style="background-color:lightblue;">
"""
for m in n:
if m['name'] == spl[-1]:
contents += f"<p>The length of the chromosome is: {m['length']}</p>"
else:
contents = Path("Error.html").read_text()
status = 404
contents += f"""<p><a href="/">Main page </a></body></html>"""
status = 200
except ValueError:
contents = Path("Error.html").read_text()
status = 404
except KeyError:
contents = Path("Error.html").read_text()
status = 404
elif arg0 == "/geneSeq":
try:
s = argument[1]
gene = s.split("=")[1]
Endpoint = f"/xrefs/symbol/homo_sapiens/{gene}"
conn = http.client.HTTPConnection(Server)
conn.request("GET", Endpoint + Parameters)
r1 = conn.getresponse()
data1 = r1.read().decode("utf-8")
d1 = json.loads(data1)
d = d1[0]
idd = d["id"]
Endpoint_ = f"sequence/id/{idd}"
conn = http.client.HTTPConnection(Server)
conn.request("GET", Endpoint_ + Parameters)
r2 = conn.getresponse()
d2 = r2.read().decode("utf-8")
d_ = json.loads(d2)
s = d_["seq"]
contents = """
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title>Medium Level</title >
</head >
<body style="background-color:violet;">
"""
contents += f"""<p> The sequence of the gene {gene} is: </p>"""
contents += f"<textarea readonly rows = 20 cols = 80>{s}</textarea>"
contents += f"""<p><a href="/">Main page </a></body></html>"""
status = 200
except ValueError:
contents = Path("Error.html").read_text()
status = 404
except KeyError:
contents = Path("Error.html").read_text()
status = 404
elif arg0 == "/geneInfo":
try:
s = argument[1]
gene = s.split("=")[1]
Endpoint = f"/xrefs/symbol/homo_sapiens/{gene}"
conn = http.client.HTTPConnection(Server)
conn.request("GET", Endpoint + Parameters)
r1 = conn.getresponse()
data1 = r1.read().decode("utf-8")
d1 = json.loads(data1)
d = d1[0]
idd = d["id"]
Endpoint_ = f"lookup/id/{idd}"
conn = http.client.HTTPConnection(Server)
conn.request("GET", Endpoint_ + Parameters)
r2 = conn.getresponse()
d2 = r2.read().decode("utf-8")
d_ = json.loads(d2)
start = d_["start"]
end = d_["end"]
length = d_["end"]-d_["start"]
id = d_["id"]
chrom = d_["seq_region_name"]
contents = """
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title>Medium Level</title >
</head >
<body style="background-color:violet;">
"""
contents += f"""<h1> {gene} </h1>"""
contents += f"""<p> The start of the gene is {start} </p>"""
contents += f"""<p> The end of the gene is {end} </p>"""
contents += f"""<p> The length of the gene is {length} </p>"""
contents += f"""<p> The id of the gene is {id} </p>"""
contents += f"""<p> The chromosome of the gene is {chrom}"""
contents += f"""<p><a href="/">Main page </a></body></html>"""
status = 200
except ValueError:
contents = Path("Error.html").read_text()
status = 404
except KeyError:
contents = Path("Error.html").read_text()
status = 404
elif arg0 == "/geneCalc":
try:
s = argument[1]
gene = s.split("=")[1]
Endpoint = f"/xrefs/symbol/homo_sapiens/{gene}"
conn = http.client.HTTPConnection(Server)
conn.request("GET", Endpoint + Parameters)
r1 = conn.getresponse()
data1 = r1.read().decode("utf-8")
d1 = json.loads(data1)
d = d1[0]
idd = d["id"]
Endpoint_ = f"sequence/id/{idd}"
conn = http.client.HTTPConnection(Server)
conn.request("GET", Endpoint_ + Parameters)
r2 = conn.getresponse()
d2 = r2.read().decode("utf-8")
d_ = json.loads(d2)
seq = d_["seq"]
sequence = Seq(seq)
length = sequence.len()
contents = """
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title>Medium Level</title >
</head >
<body style="background-color:violet;">
"""
contents += f"""<h1> {gene} </h1>"""
contents += f"""<p> The total length is {length}"""
for base in all_bases:
count = sequence.count_base(base)
c.append(count)
percentage = (count / length) * 100
p.append(f"{round(percentage, 3)}")
contents += f"""<p>{all_bases[0]}: {c[0]} : {p[0]} %</p>"""
contents += f"""<p>{all_bases[1]}: {c[1]} : {p[1]} %</p>"""
contents += f"""<p>{all_bases[2]}: {c[2]} : {p[2]} %</p>"""
contents += f"""<p>{all_bases[3]}: {c[3]} : {p[3]} %</p>"""
contents += f"""<p><a href="/">Main page </a></body></html>"""
status = 200
except ValueError:
contents = Path("Error.html").read_text()
status = 404
except KeyError:
contents = Path("Error.html").read_text()
status = 404
elif arg0 == "/geneList":
try:
s = argument[1]
ch = s.split('&')[0]
st = s.split('&')[1]
en = s.split('&')[2]
chromo = ch.split("=")[1]
start = st.split("=")[1]
end = en.split("=")[1]
Endpoint = f"overlap/region/human/{chromo}:{start}-{end}"
Parameter = '?feature=gene;content-type=application/json'
conn = http.client.HTTPConnection(Server)
conn.request("GET", Endpoint + Parameter)
r1 = conn.getresponse()
data1 = r1.read().decode("utf-8")
d1 = json.loads(data1)
contents = """
<!DOCTYPE html>
<html lang = "en">
<head>
<meta charset = "utf-8" >
<title>Medium Level</title >
</head >
<body style="background-color:violet;">
"""
for i in d1:
contents += f"""<p> * {i["external_name"]} </p>"""
contents += f"""<p><a href="/">Main page </a></body></html>"""
status = 200
except ValueError:
contents = Path("Error.html").read_text()
status = 404
except KeyError:
contents = Path("Error.html").read_text()
status = 404
self.send_response(status)
# Define the content-type header:
self.send_header('Content-Type', content_type)
self.send_header('Content-Length', len(contents.encode()))
# The header is finished
self.end_headers()
# Send the response message
self.wfile.write(contents.encode())
return
response = 'OK!'
elif cmd1 == "GET":
for element in range(len(sequences)):
if element == int(cmd2):
termcolor.cprint("GET", 'green')
response = sequences[element]
elif cmd1 == "INFO":
seq0 = Seq(cmd2)
response = ""
termcolor.cprint("INFO", 'green')
response += f'Sequence: {cmd2}'
response += f"Total length: {seq0.len()}"
for element in bases:
resp = round(seq0.count_base(element) * (100 / seq0.len()), 2)
response += f'{element}: {seq0.count_base(element)} ( {resp}% ) \n'
elif cmd1 == "COMP":
seq0 = Seq(cmd2)
termcolor.cprint("COMP", 'green')
response = seq0.complement()
elif cmd1 == "REV":
seq0 = Seq(cmd2)
termcolor.cprint("REV", 'green')
response = seq0.reverse()
elif cmd1 == "GENE":
seq0 = Seq("")
seq0 = seq0.read_fasta(folder + cmd2 + '.txt')
from P1.Seq1 import Seq
print("-----| Practice 1, Exercise 4 |------")
s1 = Seq()
s2 = Seq("ACTGA")
s3 = Seq("Invalid Sequence")
print("Sequence" + str(1) + ": (Length: " + str(s1.len()), ")" + str(s1))
print("Sequence" + str(2) + ": (Length: " + str(s2.len()), ")" + str(s2))
print("Sequence" + str(3) + ": (Length: " + str(s3.len()), ")" + str(s3))