7 jed metpo curation assignment #1 llm ontology definition review and editing#19
Merged
realmarcin merged 11 commits intomainfrom Nov 3, 2025
Conversation
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
…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
…ology-definition-review-and-editing
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.
…ology-definition-review-and-editing
…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
realmarcin
approved these changes
Nov 3, 2025
Collaborator
realmarcin
left a comment
There was a problem hiding this comment.
nice work, merging ahead
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
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.