more documentation for AI datasets

[ValWood]

https://github.com/pombase/website/blob/master/src/docs/datasets/ai_and_ml_training_datasets.md

we have

but our syntax for alleles.tsv descriptions is not documented on the website, it is only avaiable in

Manuel Lera-Ramírez, Jürg Bähler, Juan Mata, Kim Rutherford, Charles S Hoffman, Sarah Lambert, Snezhana Oliferenko, Sophie G Martin, Kathleen L Gould, Li-Lin Du, Sarah A Sabatinos, Susan L Forsburg, Olaf Nielsen, Paul Nurse, Valerie Wood
Revised fission yeast gene and allele nomenclature guidelines for machine readability
Genetics, September 2023, iyad031
PMID:37758508 10.1093/genetics/iyad143

table 2 https://academic.oup.com/view-large/482460424
(includes also the reg ex patter)

can we include this on a pombase page and link to it from the AI allele data description (and for the PHAF file descriptions)

[kimrutherford]

can we include this on a pombase page and link to it from the AI allele data description

Would it be enough to link to the paper from the table?

[kimrutherford]

Would it be enough to link to the paper from the table?

That's what we're doing in the new PHAF description table:

• new descriptions for phenotype PHAF output #2417 (comment)

[ValWood]

For our use case, I think it might be better to have a copy locally we can point to because this is some of the information we will provide directly to the models.

@manulera should have a copy that can be more easily converted to html hopefully?

This isn't urgent. Let's see if it works just providing the URL of the paper to the model, and if not we will make a more explicit link