def importGene(filename):
filename = filename or r'C:\work\caida\Dropbox\precon\engineering\Contents\GBM_BN-symbols.txt'
cnt = 0
set = {}
col = mongo.db()['entity']
with open(filename) as f:
content = f.read()
for line in content.split('\n'):
line = line.strip()
sym = line.lower()
if (sym in set): continue
set[sym] = 1
doc = ObjDict()
doc._id = 'enti_sym_%s' % sym
doc.symbol = sym
doc.group = 'protein'
doc.name = line
doc.label = line
if (col.find({'symbol': sym}).count() > 0): continue
col.save(doc, safe=True)
cnt += 1
print "Added # %d: %s" % (cnt, sym)
print "Inserted %d gene" % cnt
def medline2ris(content, style=ENDNOTE):
articles = []
lines = content.splitlines()
import re
marker = re.compile("([A-Z ]{4})- (.*)$")
key = None
for indx, line in enumerate(lines):
if (not line.strip()): continue
m = marker.match(line)
if (m):
key = m.group(1)
if (key == 'PMID'):
article = ObjDict()
articles.append(article)
if (key in article): # more than one entry
if (type(article[key]) == list):
article[key].append(m.group(2))
else:
article[key] = [article[key]]
else:
article[key] = m.group(2)
else:
if (key):
if (type(article[key]) == list):
article[key][len(article[key]) - 1] = "%s\r\n%s" % (
article[key][len(article[key]) - 1], line)
else:
article[key] = "%s\r\n%s" % (article[key], line
) #continuation of last line
else:
raise Exception("Invalid data at line %d: %s" % (indx, line))
# now handles the article
#if len(articles) != len(pubmed_ids):
# msg = "Expecting %d articles, but harvested %d" %(len(pubmed_ids), len(articles))
# raise Exception(msg)
ret = ''
for article in articles:
ret += "TY - JOUR\r\n"
tmp = {}
for key in article.keys():
if (key not in MEDLINE_ENDNOTE_MAPPING):
tmp[key] = article[key]
else:
tmp[MEDLINE_ENDNOTE_MAPPING[key]] = article[key]
for key in sorted(tmp.keys()):
vals = tmp[key] if (type(tmp[key]) == list) else [tmp[key]]
for val in vals:
ret = "%s%s- %s\r\n" % (ret, key, val)
# end article
ret += "ER - \r\n\r\n\r\n"
return ret
def _parse_node(self, node):
node_tree = ObjDict()
# Save attrs and text, hope there will not be a child with same name
if node.text:
node_tree.value = node.text
for (k, v) in node.attrib.items():
k, v = self._namespace_split(k, ObjDict({'value': v}))
node_tree[k] = v
#Save childrens
for child in node.getchildren():
tag, tree = self._namespace_split(child.tag,
self._parse_node(child))
if tag not in node_tree: # the first time, so store it in dict
node_tree[tag] = tree
continue
old = node_tree[tag]
if not isinstance(old, list):
node_tree.pop(tag)
node_tree[tag] = [
old
] # multi times, so change old dict to a list
node_tree[tag].append(tree) # add the new one
return node_tree
def fromstring(self, s):
"""parse a string"""
t = ET.fromstring(s)
root_tag, root_tree = self._namespace_split(t.tag, self._parse_node(t))
return ObjDict({root_tag: root_tree})
