Update _de.py

[MingzeDong]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @MingzeDong, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request enhances the differential expression (DE) gene evaluation metrics by streamlining the calculation of Precision-Recall AUC and introducing configurability for the False Discovery Rate threshold. These improvements aim to make the DE gene comparison process more flexible and maintainable.

Highlights

• AUC-PR Calculation Refinement: The method for calculating the Area Under the Curve for Precision-Recall (AUC-PR) has been updated to directly use average_precision_score from sklearn.metrics, simplifying the code and potentially offering a more robust calculation than the previous precision_recall_curve followed by auc.
• Configurable FDR Threshold: The False Discovery Rate (FDR) threshold used in the filter_to_significant method is no longer a hardcoded value (0.05). It now dynamically uses self.fdr_threshold, allowing for greater flexibility and configurability of the significance filtering.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces several improvements to the differential expression metrics. It correctly replaces a hardcoded FDR threshold in DEDirectionMatch with the configurable class attribute, enhancing consistency. It also updates the precision-recall AUC calculation to use sklearn.metrics.average_precision_score, which is a more accurate and standard method. My review includes one suggestion for a further improvement: I've pointed out another hardcoded FDR threshold within the compute_generic_auc function. Parameterizing this value would improve the flexibility and consistency of the AUC metrics, aligning them with the other metrics in this module.

[gemini-code-assist]

Using average_precision_score is a great improvement for calculating the PR-AUC. While reviewing this function, I noticed a hardcoded FDR threshold on line 224:

(pl.col(real_fdr_col) < 0.05).cast(pl.Float32).alias("label")

This is inconsistent with the change you made in DEDirectionMatch to use a configurable fdr_threshold. To improve consistency and flexibility, consider parameterizing this threshold in compute_generic_auc and the functions that call it (compute_pr_auc, compute_roc_auc).

For example:

def compute_pr_auc(data: DEComparison, fdr_threshold: float = 0.05) -> dict[str, float]:
    """Compute precision-recall AUC per perturbation for significant recovery."""
    return compute_generic_auc(data, method="pr", fdr_threshold=fdr_threshold)

def compute_generic_auc(
    data: DEComparison,
    method: Literal["pr", "roc"] = "pr",
    fdr_threshold: float = 0.05,
) -> dict[str, float]:
    ...
    labeled_real = data.real.data.with_columns(
        (pl.col(real_fdr_col) < fdr_threshold).cast(pl.Float32).alias("label")
    )
    ...