Skip to content

7 jed metpo curation assignment #1 llm ontology definition review and editing#19

Merged
realmarcin merged 11 commits intomainfrom
7-jed-METPO-curation-assignment-#1---LLM-ontology-definition-review-and-editing
Nov 3, 2025
Merged

7 jed metpo curation assignment #1 llm ontology definition review and editing#19
realmarcin merged 11 commits intomainfrom
7-jed-METPO-curation-assignment-#1---LLM-ontology-definition-review-and-editing

Conversation

@jedkim-ozaeta
Copy link
Collaborator

@jedkim-ozaeta jedkim-ozaeta commented Oct 17, 2025

In the outputs - reviewed folder is my up-to-date JSON and TSV file for curator5 terms. In the prompts - executed folder are the different versions of prompts I have created (version 3 is the most updated one currently). Not so sure as to why the JSON and TSV files formatting is rough on here compared to when I view them in my branch.

Generated 26 OBO-compliant definitions for METPO terms with improved prompt template including batch processing, domain guidelines, and validation checklist. Organized outputs in raw/reviewed workflow.
…-#1---LLM-ontology-definition-review-and-editing

Add curator5 definitions and improved v2.0 prompt template
jedkim-ozaeta and others added 7 commits October 24, 2025 01:09
…SV converter

- Added definition-generation v2.1 prompt with batch processing (5-10 terms)
- Executed v2.1 prompt on all 33 curator5 terms in 4 batches
- Enhanced json_to_robot_tsv.py to support v2.1 format:
  - Structured sources with URLs
  - Parent class IDs
  - Quantitative values with measurement sources
  - Enhanced comments field with reasoning
- Generated 4 JSON outputs with ontology-verified definitions
- Generated 4 ROBOT template TSV files ready for ontology integration
- All definitions include OBO Foundry compliance with genus-differentia form
Removed detailed comments and version info from the script.
Add missing type annotations to satisfy mypy strict mode:
- Add type annotation for 'data' variable (line 35)
- Add type annotation for 'sources' parameter (line 40)
- Add type annotation for 'quant_values' parameter (line 70)
- Add return type annotation for main() function (line 283)
- Remove invalid comparison between dict and string literal (line 80)

All mypy checks now pass for this script.
…spell

Auto-fixes applied by pre-commit hooks:
- Remove trailing whitespace from 10 files
- Fix ruff linting errors (15 issues auto-fixed)
- Reformat code with ruff-format (1 file)

Manual fixes:
- Add 'formate' to codespell ignore list (it's a chemical compound, not a typo)
  Formate (HCOO⁻) is a legitimate term in microbiology/biochemistry

Files modified:
- pyproject.toml: Add 'formate' to ignore-words-list
- scripts/json_to_robot_tsv.py: Code formatting
- Multiple TSV, MD files: Trailing whitespace removed
@jedkim-ozaeta jedkim-ozaeta marked this pull request as ready for review November 3, 2025 17:38
Copy link
Collaborator

@realmarcin realmarcin left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nice work, merging ahead

@realmarcin realmarcin merged commit db68825 into main Nov 3, 2025
5 checks passed
@realmarcin realmarcin deleted the 7-jed-METPO-curation-assignment-#1---LLM-ontology-definition-review-and-editing branch November 3, 2025 19:16
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants