Skip to main content

Use Minimal Named-Entity Recognizer (MER) inside python

Project description


Use MER scripts inside python.

(from the MER repository)

MER is a Named-Entity Recognition tool which given any lexicon and any input text returns the list of terms recognized in the text, including their exact location (annotations).

Given an ontology (owl file) MER is also able to link the entities to their classes.

More information about MER can be found in:

  • MER: a Shell Script and Annotation Server for Minimal Named Entity Recognition and Linking, F. Couto and A. Lamurias, Journal of Cheminformatics, 10:58, 2018 []
  • MER: a Minimal Named-Entity Recognition Tagger and Annotation Server, F. Couto, L. Campos, and A. Lamurias, in BioCreative V.5 Challenge Evaluation, 2017 []





MER was developed and tested using the GNU awk (gawk) and grep. If you have another awk interpreter in your machine, there's no assurance that the program will work.

For example, to install GNU awk on Ubuntu:

sudo apt-get install gawk


To calculate similarities between the recognized entities

pip install ssmpy


pip install merpy


python install

Then you might want to update the MER scripts and download preprocessed data:

>>> import merpy
>>> merpy.download_mer()
>>> merpy.download_lexicons()

Basic Usage

>>> import merpy
>>> merpy.download_lexicons()
>>> lexicons = merpy.get_lexicons()
>>> merpy.show_lexicons()
lexicons preloaded:
['lexicon', 'bireme_decs_por2020', 'bireme_decs_spa2020', 'wordnet-hyponym', 'radlex', 'doid', 'bireme_decs_eng2020', 'go', 'hp', 'chebi_lite']
lexicons loaded ready to use:
['bireme_decs_por2020', 'chebi_lite', 'hp', 'bireme_decs_spa2020', 'wordnet-hyponym', 'doid', 'lexicon', 'radlex', 'go', 'bireme_decs_eng2020']
lexicons with linked concepts:
['bireme_decs_eng2020', 'doid', 'hp', 'go', 'lexicon', 'bireme_decs_spa2020', 'bireme_decs_por2020', 'radlex', 'chebi_lite']

>>> document = 'Influenza, commonly known as "the flu", is an infectious disease caused by an influenza virus. Symptoms can be mild to severe. The most common symptoms include: a high fever, runny nose, sore throat, muscle pains, headache, coughing, and feeling tired ... Acetylcysteine for reducing the oxygen transport and caffeine to stimulate ... fever, tachypnea ... fiebre, taquipnea ... febre, taquipneia' 
>>> entities = merpy.get_entities(document, "hp") # get_entities_mp uses multiprocessing (set n_cores param)
>>> print(entities)
[['111', '115', 'mild', ''], ['119', '125', 'severe', ''], ['168', '173', 'fever', ''], ['181', '185', 'nose', ''], ['200', '206', 'muscle', ''], ['214', '222', 'headache', ''], ['224', '232', 'coughing', ''], ['246', '251', 'tired', ''], ['288', '294', 'oxygen', ''], ['295', '304', 'transport', ''], ['335', '340', 'fever', ''], ['342', '351', 'tachypnea', ''], ['175', '185', 'runny nose', ''], ['187', '198', 'sore throat', '']]

>>> entities = merpy.get_entities(document, "bireme_decs_por2020") 
>>> print(entities)
[['0', '9', 'Influenza', ''], ['78', '87', 'influenza', ''], ['378', '383', 'febre', ''], ['385', '395', 'taquipneia', '']]

>>> merpy.create_lexicon(["gene1", "gene2", "gene3"], "genelist")
wrote genelist lexicon
>>> merpy.process_lexicon("genelist")
>>> merpy.delete_lexicon("genelist")
deleted genelist lexicon
>>> merpy.download_lexicon("", "chebi")
wrote chebi lexicon
>>> merpy.process_lexicon("chebi")

Semantic Similarities

gunzip -N chebi202104.db.gz
>>> import merpy
>>> merpy.process_lexicon("lexicon")
>>> document = "α-maltose and nicotinic acid was found, but not nicotinic acid D-ribonucleotide"
>>> entities = merpy.get_entities(document, "lexicon") 
>>> merpy.get_similarities(entities, 'chebi.db')
[['0', '9', 'α-maltose', '', 0.02834388514184269], ['14', '28', 'nicotinic acid', '', 0.07402224403263755], ['48', '62', 'nicotinic acid', '', 0.07402224403263755], ['48', '79', 'nicotinic acid D-ribonucleotide', '', 0.07402224403263755]]

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

merpy-1.7.12.tar.gz (25.7 kB view hashes)

Uploaded source

Built Distribution

merpy-1.7.12-py3-none-any.whl (28.8 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page