def info(self):
return dataio.get_pubmeds([self.pmid])
def get_pubmed_data(pp, cachefile=None, htp_threshold=20):
"""
For one PyPath object, obtains metadata for all PubMed IDs
through NCBI E-utils.
:param pp:
``pypath.PyPath`` object
:param htp_threshold:
The number of interactions for one reference
above the study considered to be high-throughput.
"""
if cachefile is None:
cachefile = settings.get('pubmed_cache')
if htp_threshold is not None:
pp.htp_stats()
pubmeds = common.uniqList(
common.flatList([[r.pmid for r in e['references']]
for e in pp.graph.es]))
if htp_threshold is not None:
pubmeds = set(pubmeds) - pp.htp[htp_threshold]['htrefs']
notpmid = [i for i in pubmeds if not i.isdigit()]
sys.stdout.write('\t:: Number of non PubMed ID references: %u\n' %
len(notpmid))
pmdata = {}
if os.path.exists(cachefile):
sys.stdout.write('\t:: Loading data previously downloaded '
'from PubMed, from file `%s`\n' % cachefile)
pmdata = pickle.load(open(cachefile, 'rb'))
missing = list(set(pubmeds) - set(pmdata.keys()))
sys.stdout.write('\t:: Downloading data from PubMed about %s papers\n' %
len(missing))
cached_pubmeds_len = len(pmdata)
pmdata_new = dataio.get_pubmeds(missing)
pmdata.update(pmdata_new)
sys.stdout.write('\t:: Saving PubMed data to file `%s`\n' % cachefile)
if len(pmdata) > cached_pubmeds_len:
pickle.dump(pmdata, open(cachefile, 'wb'))
pmdata = dict(i for i in pmdata.items() if i[0] in pubmeds)
points = []
earliest = []
for e in pp.graph.es:
for s, rs in iteritems(e['refs_by_source']):
pms = [
r.pmid for r in rs
if (htp_threshold is None
or r.pmid not in pp.htp[htp_threshold]['htrefs'])
and r.pmid in pmdata and 'pubdate' in pmdata[r.pmid]
]
if len(pms) > 0:
yrs = [int(pmdata[pm]['pubdate'][:4]) for pm in pms]
earliest.append((s, 0, min(yrs), '', e.index))
for pm in pms:
points.append((s, pm, int(pmdata[pm]['pubdate'][:4]),
pmdata[pm]['source'], e.index))
points = common.uniqList(points)
earliest = common.uniqList(earliest)
points = pd.DataFrame.from_records(points)
earliest = pd.DataFrame.from_records(earliest)
points.columns = ['database', 'pmid', 'year', 'journal', 'eid']
earliest.columns = ['database', 'none', 'year', 'none', 'eid']
return points, earliest
