INCATools / biosample-analysis

analysis of biosamples in INSDC
3 stars 1 forks source link

provide NER output from SQLlite/basex tables #81

Open realmarcin opened 2 years ago

realmarcin commented 2 years ago

NER methods were run on an earlier version of the Biosample data, specifically for the Title and Description fields. This process used a simple TSV file with these fields source from the Biosample table:

biosample id title description

For the next iteration, it should be possible to have an additional piece of code as part of the NER pipeline to execute a basex query and output the results in the TSV format above for NER input.

@hrshdhgd @turbomam