Harry Caufield

Followup on #353 - support including annotations in schemas to model KGX output

1

Schemas may currently be annotated with the `owl` slot to denote the OWL equivalent, e.g., in the `recipe` schema: ```yaml FoodItem: is_a: CompoundExpression annotations: owl: IntersectionOf attributes: food: description: the...

> Strengthening The Organization and Reporting of Microbiome Studies (STORMS) is a checklist for reporting on human microbiome studies, organized into six sections covering all sections of a scientific publication,...

Using value set expansion with non-OBO annotator leads to 404 error

2

Originally seen in #346. Using a Bioportal ontology (like bioportal:SNOMEDCT) as an annotator works fine on its own. If used in a value set expansion, e.g., with a `reachable_from`, it...

industrial-production-specific SPIRES

2

...I am trying to build an industrial-production-specific SPIRES. I found the upper level production ontology built by Industrial Foundry Ontology. Do you have any suggestions how to inverse-engineeringly design a...

Requesting model `orca-2-7b` raises `llm.UnknownModelError`

5

Issue c/o Bart Kleijngeld: Using the `llm` package to call `orca-2-7b` directly works as expected: ``` $ llm -m orca-2-7b "Hi!" 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3.83G/3.83G [05:58

Provide equivalencies for phenotype terms

6

From @matentzn at today's Monarch Huddle: > Wishlist to OntoGPT team: we need a scalable solution to suggestion EQs for phenotype ontologies.

Extraction of MAXO annotations is helpful but would be much more helpful if we get the output in a format compatible with the other MAXO annotations, as seen here: https://github.com/monarch-initiative/maxo-annotations/blob/master/annotations/maxo-annotations.tsv...

Relax truncation with `pubmed-annotate`

1

The `pubmed-annotate` command currently truncates inputs to ~3K characters. That's not necessary with the larger context models, so it can be relaxed and/or added as a CLI parameter.

For D4D extraction, it's likely we will need to integrate data from multiple sources. These could be provided manually if they're already known (like GH repo + official docs +...

Extraction should be able to parse: * individual columns from delimited files (CSV, TSV, etc) * dataframes (polars/pandas) * Excel spreadsheets per convo with @twhetzel