Does anyone know whether Apache Ctakes can run UMLS without internet connection and whether there is a good Python wrapper around Ctakes ?
Does anyone know whether Apache Ctakes can run UMLS without internet connection and whether there is a good Python wrapper around Ctakes ?
3
Answers
Can it? Or should it? Can? yes, source code is available. Should? not if you are in violation of the NLM UMLS license agreement.
This is a partial answer. I have no idea about the Python wrapper.
The UMLS files can be downloaded download here:
https://www.nlm.nih.gov/research/umls/licensedcontent/umlsknowledgesources.html
You need to be a registered UMLS user in order to download the zip file. The MetamorphoSys tool is included in the download. This tool can be used to load the UMLS data files into MySQL, SQL Server, or an Oracle database.
You can use cTAKES dictionary creator GUI to create dictionary of your choice and load the script in MySQL DB. This was you dont need internet connection as you will be relying on local database for analysis.
We have used this approach in our development where cTAKES REST service will be talking to our local DB.