Gene extraction from documents

Question

[singh.vishu]

Hello - I have just started working in Bioinformatics. One project where I am involved is the extraction of genes from documents. There is also another goal of finding a relationship between genes in documents. What we have done so far is used Abner tagger and fuzzy text match. Is my question are reinventing the wheel? Are there already good services already available? When I do some search there seem to be so many services available like Pubtator. How does one find a good reliable service?

Answer 1

[Jean-Karim Heriche]

There's already been work on extracting genes and other biological entities from text. This is part of a field called biomedical text mining and the task you're describing is called named entity recognition.
As examples of existing tools, have a look at iHOP and Reflect. There are other tools listed in this review.

Answer 2

[Emily]

This is what Europe PMC use: https://europepmc.org/Annotations