This workflow does four things: it retrieves documents relevant for the query string it discovers entities in those documents, these are considered relevant entities it filters proteins from those entities (on the tag protein_molecule) it removes all terms from the list produced by 3 (query terms temporarily considered proteins) ToDo Replace step 4 by the following procedure: 1. remove the query terms from the output of NER (probably by a regexp matching on what is inside the tag, ...