Harvard:Biophysics 101/2007/Notebook:Xiaodi Wu/2007-4-2

Code for parsing OMIM, transposed from the 20 March notebook.

from Bio.EUtils import DBIdsClient
import xml.dom.minidom
from xml.dom.minidom import parse, parseString

# C-style struct to pass parameters
class AllelicVariant:
	pass

# queries the database and returns all info in an XML format
def omim_snp_search(dnsnp_id):
	client = DBIdsClient.DBIdsClient()
	query = client.search(dnsnp_id, "omim")
	records = [i.efetch(rettype="xml") for i in query]
	return records

# basic text extraction from XML; based on http://docs.python.org/lib/dom-example.html
def get_text(node_list):
    rc = ""
    for node in node_list:
        if node.nodeType == node.TEXT_NODE:
            rc = rc + node.data
    return rc

# extracts allelic variant data, as the name implies, using the struct above
def extract_allelic_variant_data(str):
	dom = parseString(str)
	variants = dom.getElementsByTagName("Mim-allelic-variant")
	if len(variants) == 0:
		return
	parsed = []
	for v in variants:
		a = AllelicVariant() # create empty instance of struct
		# now populate the struct
		a.name = get_text(v.getElementsByTagName("Mim-allelic-variant_name")[0].childNodes)
		a.mutation = get_text(v.getElementsByTagName("Mim-allelic-variant_mutation")[0].getElementsByTagName("Mim-text_text")[0].childNodes)
		a.description = get_text(v.getElementsByTagName("Mim-allelic-variant_description")[0].getElementsByTagName("Mim-text_text")[0].childNodes)
		parsed.append(a)
	return parsed
	
for i in omim_snp_search("rs11200638"):
	v = extract_allelic_variant_data(i.read())
	if v != None:
		for a in v:
			print a.name
			print a.mutation
			print a.description