#! /usr/bin/python
# module of useful functions, classes and variables for fetching and displaying protein data
import sys, re, urllib
# returns xml page of gids for supplied search term
def esearch(searchterm):
x = urllib.urlopen('http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=protein&term='+searchterm)
return x
# returns structure id for given pdb reference for image display
def structuresearch(term):
z = urllib.urlopen('http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=structure&term='+term).readlines()
for r in z:
q = re.search(r'(.*)',r)
if q:
return q.group(1)
# fetches protein information xml file when given gid
def efetch(gid):
y = urllib.urlopen("http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=protein&id="+gid+"&rettype=xml&retmode=text").read()
return y
# searches for information between given xml tags
def xmlsearch(term,file):
searchstring = r'<'+term+'>(.*)'
found = re.search(searchstring,file)
if found:
return found.group(1)
else:
return "no information available"
# takes command line arguments and gives error message if none are supplied
def takeargument(number=1,alttext="",default=None):
try:
x =sys.argv[number]
except:
print alttext
x = default
return x
# a datatype for protein information
class protein:
def __init__(self,a,b,c,q,d=None,e=None):
self.gid = a
self.name = b
self.sequence = c
self.organism = q
self.pdbid = d
self.image = e
# some useful strings for w3c valid html pages
doctype = "\n "
charset = "\n \n \n"
css = ""
header = doctype + charset + css
middle = "\n \n
"
bottom = "
\n "
# creates webpage for individual protein when given information
def createpage(prefix,ptn):
filename = prefix+ ptn.gid +".html"
filehandler = open(filename,"w")
title = "Information for protein "+ ptn.gid +"\n"
name = "
Name:
"+ ptn.name +"
\n"
gid = "
GID:
"+ ptn.gid +"
\n"
organism = "
Organism:
" + ptn.organism + "
\n"
pdbid = "
PDB id:
"+ ptn.pdbid +"
\n"
sequence = "
Sequence:
"+ ptn.sequence +"
\n"
if ptn.image:
image = "
Image:
\n"
else:
image = ""
filehandler.write(header+title+middle+name+gid+organism+sequence+pdbid+image+bottom)
webpagedata = [filename, ptn.gid, ptn.name]
return webpagedata
# creates index page of all the files
# and css file for style information
def createblankpage(name):
filehandler= open(name+".html","w")
stylesheet=open("index.css","w")
stylesheet.write(".seq{display: block; width: 30em; overflow-x:scroll;} html {background: black; color: #e7ebc3;} ")
stylesheet.write("table {border-collapse: collapse}td {border: 1px solid #ebc4d3} a, a:visited {color: #c3ebd3}")
title = "Collected protein information for keyword "+ name +"\n"
labels = "