scastlara / ppaxe Goto Github PK

Following errors:
File "/ppaxe/bin/ppaxe", line 173, in
main()
File "/ppaxe/bin/ppaxe", line 163, in main
stats = get_ppi(options, start_time, pmids)
File "/ppaxe/bin/ppaxe", line 89, in get_ppi
query.get_articles()
File "/usr/local/lib/python2.7/dist-packages/ppaxe/core.py", line 227, in get_articles
self.__get_pubmed(req)
File "/usr/local/lib/python2.7/dist-packages/ppaxe/core.py", line 182, in __get_pubmed
article_text = minidom.parseString(req.content)
File "/usr/lib/python2.7/xml/dom/minidom.py", line 1928, in parseString
return expatbuilder.parseString(string)
File "/usr/lib/python2.7/xml/dom/expatbuilder.py", line 940, in parseString
return builder.parseString(string)
File "/usr/lib/python2.7/xml/dom/expatbuilder.py", line 223, in parseString
parser.Parse(string, True)
xml.parsers.expat.ExpatError: not well-formed (invalid token): line 34403, column 55

Error occurring on docker ppaxe.

i have down the FINAL-ner-model.AImed+MedTag+BioInfer.ser.gz, but i don't know how to use.
if can give me some idea, i'll appreciate

Scale confidence to a 0-1 value.

Add docker container to distribute ppaxe together with the StanfordCoreNLP and all the dependencies.

Right now, we only have absolute counts of each protein symbol found.

I've had a play with this and its really nice.

I'm somewhat unfamiliar with the NLP that goes into this (and NLP in general), but I wanted to know if this should be straightforward to extend to looking for interactions other than protein-protein.

For example, I'm particular interested in looking for protein-disease interactions. If I have some list of proteins and diseases I am interested in finding interactions of, do you have any advice on how I can modify the ppaxe module to do this?

Thanks!