-
Notifications
You must be signed in to change notification settings - Fork 5
Open
Description
Hello,
I have found a bug that ignores specific strings from the input lexicon.
In this case the strings that I detected are "A2M" and "A1BG".
The code that I used to test this lexicon is the following:
import merpy
merpy.download_mer()
geneSyn=merpy.create_lexicon_from_file("gene_synonyms_lexicon.txt", "geneSyn")
merpy.process_lexicon("geneSyn")
#Examples
print(merpy.get_entities("The genes encoding myeloperoxidase (MPO) and alpha(2)-macroglobulin (A2M)", "geneSyn"))
print(merpy.get_entities("The association between polymorphisms in the alpha-2-macroglobulin (a2m) gene", "geneSyn"))
print(merpy.get_entities("The gene A2M with A1BG and NAT1 are", "geneSyn"))
print(merpy.get_entities("fragment of A1BG in urine in SRNS", "geneSyn"))The file in use:
gene_synonyms_lexicon.txt
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels