Skip to content

feat: Added FDR threshold as a user defined option in prediction pipeline #245

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

Open
Rive-001 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

feat: Added FDR threshold as a user defined option in prediction pipeline #245

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4ae0822
build: converted fdr threshold to user provided arg
Rive-001 Dec 16, 2025
fadbb52
chore: updated version
Rive-001 Dec 16, 2025
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
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[project]
name = "arc-state"
version = "0.9.32"
version = "0.9.33"
description = "State is a machine learning model that predicts cellular perturbation response across diverse contexts."
readme = "README.md"
authors = [
Expand Down
8 changes: 8 additions & 0 deletions src/state/_cli/_tx/_predict.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,13 @@ def add_arguments_predict(parser: ap.ArgumentParser):
help="If set, evaluate the model on the training data rather than on the test data.",
)

parser.add_argument(
"--fdr-threshold",
type=float,
default=1e-3,
help="FDR threshold for DE significance in cell-eval metrics. Default is 1e-3.",
)
Comment on lines +55 to +60

@gemini-code-assist gemini-code-assist Bot Dec 16, 2025

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

medium

The new --fdr-threshold argument accepts any float value, which could lead to errors or unexpected behavior in cell-eval if an invalid value (e.g., negative or > 1) is provided. It would be more robust to add validation to ensure the input is within a sensible range, like (0, 1).

You can achieve this by using a custom type function with argparse.

For example:

import argparse

def fdr_threshold_range(value):
    try:
        f_value = float(value)
    except ValueError:
        raise argparse.ArgumentTypeError(f"{value} is not a floating-point number")
    if not (0.0 < f_value < 1.0):
        raise argparse.ArgumentTypeError(f"{value} is not a valid FDR threshold, it must be between 0 and 1.")
    return f_value

# ... in add_arguments_predict ...
parser.add_argument(
    "--fdr-threshold",
    type=fdr_threshold_range,
    default=1e-3,
    help="FDR threshold for DE significance in cell-eval metrics. Default is 1e-3.",
)



def run_tx_predict(args: ap.ArgumentParser):
import logging
Expand Down Expand Up @@ -422,6 +429,7 @@ def load_config(cfg_path: str) -> dict:
prefix=ct,
pdex_kwargs=pdex_kwargs,
batch_size=2048,
fdr_threshold=args.fdr_threshold,
)

evaluator.compute(
Expand Down