Created
April 11, 2017 19:55
-
-
Save matteoferla/660de8a3fb8559ca664c4211c24e490a to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def zoospotter(zoo,fn='pubmed_scored.csv', assoclist=['infection']): | |
""" | |
Method that downloads the number of Pubmed entries associataed with a given species listed in the zoo variable. | |
The variable assoclist has the fields sought. | |
:param zoo: list of species names | |
:param fn: file name to save. | |
:param assoclist: list of terms that one wishes to see the association. E.g. 'infection' to find pathogenicity. | |
:return: None. | |
""" | |
#debugprint=print | |
debugprint=lambda *x: None | |
debugprint('MODE: Pubmed association') | |
def get_count(terms): | |
handle = Entrez.esearch(db="pubmed", term=' AND '.join(terms)) | |
record = Entrez.read(handle) | |
handle.close() | |
return record["Count"] | |
Entrez.email = EMAIL | |
w=csv.DictWriter(open(fn,'w',newline=''),fieldnames=['name']+['PM_'+s for s in ['plain']+assoclist]) | |
w.writeheader() | |
for species in zoo: | |
data={'name':species} | |
bn=genomeArk.binomialiser(species) | |
if bn: | |
sp='{genus} {species}'.format(**bn) | |
n = get_count([sp]) | |
print(species, '>>> ', sp, ' — ','x', ': ', n) | |
data['PM_plain']=n | |
for assoc in assoclist: | |
n=get_count([sp, assoc]) | |
print(species,'>>> ',sp,' — ',assoc,': ',n) | |
data['PM_'+assoc]=n | |
debugprint(data) | |
w.writerow(data) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment