microbiomedata / nmdc-schema

National Microbiome Data Collaborative (NMDC) unified data model
https://microbiomedata.github.io/nmdc-schema/
Creative Commons Zero v1.0 Universal
27 stars 8 forks source link

Add NER routine for suggesting biome terms based on package + sample description for fao_soil_class or other mixs controlled field of relevance to NMDC #113

Open ssarrafan opened 3 years ago

ssarrafan commented 3 years ago

Part of larger issue: https://github.com/microbiomedata/nmdc-metadata/issues/330

ssarrafan commented 3 years ago

@turbomam should this issue be closed, moved to the backlog or moved to the October sprint?

turbomam commented 3 years ago

I would say move to October. This approach would really enrich sample metadata, and I can do it. I just haven't gotten to it yet.

ssarrafan commented 2 years ago

@turbomam should this issue be closed, moved to the backlog or moved to the November sprint?

turbomam commented 2 years ago

move to November sprint please

ssarrafan commented 2 years ago

@emileyfadrosh @turbomam would you prefer if I move this to December or to the backlog?

ssarrafan commented 2 years ago

Moving this to the December sprint based on the lower priority discussed at the mid-sprint review.

turbomam commented 2 years ago

I won't be able to work on this before GSP

ssarrafan commented 2 years ago

Thanks for the update @turbomam. I can move it to March for now.

ssarrafan commented 2 years ago

@turbomam said to continue this for April

turbomam commented 2 years ago

I thought DataGood might get to this, but I think that's less likely now.

I have started this related https://github.com/microbiomedata/sample-annotator/pull/65 which should be applciable to the FAO class cleanup but not necessarily the predction part.

Actually, that PR will be a general refactoring of all of my previous work on string to term lookups with BioPortal and OLS.

turbomam commented 2 years ago

@ssarrafan: this will not be complete in time for April 22nd release

ssarrafan commented 2 years ago

@turbomam will remove this from this sprint and add the backlog label. Let me know if you prefer to move this to May.

ssarrafan commented 10 months ago

@turbomam should this still be open in the backlog? Or can this one be closed? FYI @mslarae13

mslarae13 commented 9 months ago

Can we get some more context on what exactly this issue was for?

What is NER?

'based on package + sample description' : what sample description?