monprin/gnormplus repository overview

⁠gnormplus

Docker for Gnormplus for gene named entity recognition & gene normalisation

⁠How to Run

Run as follows from the command line (assuming input and output folders and your optional setup.txt are at /mnt/tank/gnormdata):

A sample dataset and setup.txt file are contained in this repo in gnormdata for reference.

If no setup.txt file is defined, it will use the default as defined below.

It takes in either PubTator⁠ format or BioC format files and gives them back in the same format.

⁠Note for Rebuilding

While all of the code is contained in the same folder as the Dockerfile, for building purposes, have the GNormPlus folder in a parent folder with the Dockerfile. This was done to keep the source untouched for potential future upgrades.

⁠Sample setup.txt

#===Annotation
#Attribution setting:
#FocusSpecies = Taxonomy ID
#	All: All species
#	9606: Human
#	4932: yeast
#	7227: Fly
#	10090: Mouse
#	10116: Rat
#	7955: Zebrafish
#	3702: Arabidopsis thaliana
#open: True
#close: False

[Focus Species]
	FocusSpecies = All
[Dictionary & Model]
	DictionaryFolder = Dictionary
	GNRModel = Dictionary/GNR.Model
	SCModel = Dictionary/SimConcept.Model
	GeneIDMatch = True
	Normalization2Protein = False
	DeleteTmp = True

⁠Additional Information

GNormplus - https://www.ncbi.nlm.nih.gov/research/bionlp/Tools/gnormplus/⁠ Dockerfile derived from - https://github.com/elangovana/docker-gnormplus⁠