Training datasets for ML/AI - publication centric

ValWood commented 1 week ago

Create a "publication centric" file containing all entities / annotations (all datatypes) for each publication.

Json?

kimrutherford commented 1 week ago

JSON makes sense. How urgent is this?

ValWood commented 1 week ago

It would be good to have it in a few of weeks I think to keep the ball rolling. I'm meeting the ePMC ML person on Monday if you want to join (forwarded the invite) v

kimrutherford commented 1 week ago

I'll start this on Monday. It might take a couple of days because the existing code needs improving first. A lot was written in a hurry for PomBase v2. Now I've had time (7 years?) to think about it, there are better ways to do things.

Proposed JSON structure (work in progress):

PMID:

MF annotations
- gene
- term
- evidence
- extension (as JSON)
- comment
BP annotations
- (same details)
CC annotations
- (same details)
FYPO annotations
- genotype
  - loci (one or more)
  - alleles (one or more):
    - type
    - name
    - description
- term
- evidence
- conditions (as JSON)
- extension (as JSON)
- comment
Modification annotations
- ...

kimrutherford commented 3 days ago

From Zoom: make sure to include annotation comments in the output.

ValWood commented 2 days ago

related: https://github.com/pombase/pombase-chado/issues/1185 we'll discuss this on the next call....

pombase / pombase-chado

Training datasets for ML/AI - publication centric #1181