search

HazyResearch / dd-genomics

The Genomics DeepDive project
Apache License 2.0
11 stars 6 forks source link

Also extract full gene names #171

Open Colossus opened 9 years ago

Colossus commented 9 years ago

We're currently only extracting gene acronyms (whether canonical or noncanonical), ensembl IDs and RefSeq IDs. In sentences such as the following:

SDF-1 and CXC receptor 4 ( CXCR4 ) expression in rheumatoid arthritis ( RA ) and osteoarthritis synovium and graft SDF-1 , tumor necrosis factor alpha ( TNF alpha ) , and human and murine vascular markers were examined by immunohistochemistry and double-immunofluorescence .

we might want to extract tumor necrosis factor alpha separately.

ThomasPalomares commented 8 years ago

Other example: The genetic cause of FOP was recently disc overed to be a recurrent missense activating mutation in the activin A type I receptor , a bone morp hogenetic protein type I receptor in all classically affected individuals worldwide .

mention_id: 18352811_Abstract.0_2_17 gene_name: activin

This sentence is currently extracted for high expectation in genepheno_causation (>0.9) but low gene expectation (<0.5)