Samenvatting voor tentamen programming en genomics

Open arbitrary resources by URL
import urllib.request
protocol = "http"
hostname = "cbio.bmt.tue.nl"
path = "~philbers/index.htm"
url = protocol+"://"+hostname+"/"+path
rf = urllib.request.urlopen(url)
data = rf.read() (.decode())
print(data)

data = data.decode()  convert data from bytes to string

import urllib.parse
import urllib.request
# Define a molecular formula string
mf = 'C4H5N3O'
# Define the parameters and send them to Chemcalc
pardict = {'mf': mf,'isotopomers':'jcamp,xy'}
params = urllib.parse.urlencode(pardict).encode()
# url of Chemcalc
url = 'https://www.chemcalc.org/chemcalc/mf'
# Open the url and read the page
response = urllib.request.urlopen(url, params)
data = response.read()

, Standard python search script for Entrez
from Bio import Entrez
Entrez.email = ""
m = ['"Escherichia coli"[Organism]']
m.append('"complete genome"[All Fields]')
m.append('"srcdb_refseq"[Properties]')
searchterm = ' AND '.join(m)
handle = Entrez.esearch(db="nucleotide", term=searchterm)

record = Entrez.read(handle)

idl = record['IdList']  accessing identifiers



Counting “CG’s” in DNA string
def count_list(l):
""" In this method the number of occurrences of the
pattern 'CG' in each of the string items of the list l is
returned
in a sorted list.
"""
outl = []
for dnas in l:
countCG = dnas.count("CG")
outl.append(countCG)
outl.sort()
return outl

print( count_list(['AAACGCGAA', 'CCGA', 'ACCC']) )


Small example of class making
class Student:
def __init__(self):
self.name = ''

def set_name(self, stname):
self.name = stname
print("Name of student '"+self.name+"' set")

stu1 = Student()
stu2 = Student()

>>> stu1.name
'' (inspect data by using name of object, followed by a dot,
and the name of the data attribute)
>>> stu1.name = 'Piet' (set data attributes)