Second attempt at gene list annotator #7
Merged
Conversation
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
1. new utilities subpackage has simple wrapper code for openAI API calls - DeepSearch; One shot LLM calls. 2. New services run the first two steps of the workflow. a. DeepSearch with gene list + context. Tested with 4o mini using examples in branch b. Draft Decomposer - one shot GPT5 call. Not yet tested. 3. Vibe coded agent for more general ontology grounding though OLS, based on existing code. Untested. 4. Vibe coded command line runner for gene list annotation pipeline - rescued from first attempt. I kinda like the many options for running and debugging. Not yet wired up to anything in this branch. 4. Claude.md has goals for this branch, not just general instructions 5. Progress.md is intended to support agentic coding - to be added to agent calls as needed, following updates to its contents.
There was a problem hiding this comment.
Pull Request Overview
This PR introduces a second attempt at a gene list annotation system, establishing key infrastructure components and workflow services for analyzing gene lists using LLM capabilities. The changes implement utility wrappers for OpenAI API interactions and create new services for deep search and annotation workflows.
Key changes:
- New OpenAI API utility wrappers for simple responses and deep research functionality
- Gene list contextual deep search service with schema definition and examples
- Ontology mapping agent for grounding biological terms to standardized ontologies
- Command-line interface for gene list annotation workflows
Reviewed Changes
Copilot reviewed 14 out of 20 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| pyproject.toml | Adds OpenAI dependency as optional package |
| gene_list_annotation_cli.py | Complete CLI implementation for gene annotation workflows |
| cellsem_agent/utils/openai/simple_response_wrapper.py | Wrapper for basic OpenAI API responses |
| cellsem_agent/utils/openai/deepsearch.py | Deep research client using OpenAI's research models |
| cellsem_agent/services/gene_list_contextual_deepsearch/ | Service implementation with schema and examples |
| cellsem_agent/agents/ontology_mapping/ | Agent for mapping terms to biological ontologies |
| cellsem_agent/utils/init.py | Package initialization |
| cellsem_agent/init.py | Main package initialization |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
|
|
||
| def __init__(self): | ||
| self.output_dir = Path("./gene_annotation_output") | ||
| self.examples_dir = Path(__file__).parent / "cellsem_agent" / "graphs" / "gene_list_annotation" / "examples" |
There was a problem hiding this comment.
The path construction is incorrect. Since this file is at the root level, it should not include 'cellsem_agent' in the path, or use a proper relative path resolution.
updated schema, prompt for deep search contextual and added examples
- Edits to prompts + prompts in schema - New data from Glioblastoma paper - support for list examples
# Conflicts: # cellsem_agent/agents/annotator/annotator_agent.py # poetry.lock
Collaborator
|
Merging this long lived branch to main: |
hkir-dev
approved these changes
Oct 14, 2025
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.
a. DeepSearch with gene list + context. Tested with 4o mini using examples in branch
b. Draft Decomposer - one shot GPT5 call. Not yet tested.