Skip to content

Use left join for DE Spearman/AUC (Fixes #227) #228

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
noamteyssier merged 1 commit into from
Mar 19, 2026
Merged

Use left join for DE Spearman/AUC (Fixes #227) #228

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 17 additions & 11 deletions src/cell_eval/metrics/_de.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,11 +116,15 @@ def __call__(self, data: DEComparison) -> dict[str, float]:
"""Compute correlation between log fold changes of significant genes."""
correlations = {}

merged = data.real.filter_to_significant(fdr_threshold=self.fdr_threshold).join(
data.pred.data,
on=[data.real.target_col, data.real.feature_col],
suffix="_pred",
how="inner",
merged = (
data.real.filter_to_significant(fdr_threshold=self.fdr_threshold)
.join(
data.pred.data,
on=[data.real.target_col, data.real.feature_col],
suffix="_pred",
how="left",
)
.with_columns(pl.col(f"{data.real.fold_change_col}_pred").fill_null(0.0))
)

for row in (
Expand Down Expand Up @@ -224,17 +228,19 @@ def compute_generic_auc(
(pl.col(real_fdr_col) < 0.05).cast(pl.Float32).alias("label")
).select([target_col, feature_col, "label"])

pred_q = pl.col(pred_fdr_col).fill_null(1.0).clip(1e-10, 1.0)
merged = (
data.pred.data.select([target_col, feature_col, pred_fdr_col])
.join(
labeled_real,
labeled_real.join(
data.pred.data.select([target_col, feature_col, pred_fdr_col]),
on=[target_col, feature_col],
how="inner",
how="left",
coalesce=True,
)
.drop_nulls(["label"])
.with_columns((-pl.col(pred_fdr_col).replace(0, 1e-10).log10()).alias("nlp"))
.drop_nulls(["nlp"])
.with_columns(
pred_q.alias(pred_fdr_col),
(-pred_q.log10()).alias("nlp"),
)
Comment on lines +240 to +243

@gemini-code-assist gemini-code-assist Bot Mar 5, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

medium

The update to pred_fdr_col via pred_q.alias(pred_fdr_col) is not necessary, as this column isn't used again within the function. You can simplify this with_columns call by only creating the nlp column.

        .with_columns(
            (-pred_q.log10()).alias("nlp")
        )

)

results: dict[str, float] = {}
Expand Down