Malinois Activity

Score regulatory DNA activity using Malinois with max/min cell-type objectives.

License: Malinois is open source and free for academic and commercial use under an MIT license and may require explicit attribution when utilized. Please refer to the license for full terms.

This constraint is open source. Any third-party models, product names, or trademarks referenced are the property of their respective owners, and Proto is not affiliated with them.

---

Tools Used Tools Used Source Source Cite Cite

Go to Tool Page

proto-bio/proto-language/proto_language/constraint/sequence_annotation/malinois_activity_constraint.py

View source

@article{gosai2024machine,
  title={Machine-guided design of cell-type-targeting cis-regulatory elements},
  author={Gosai, Sager J. and Castro, Rodrigo I. and Fuentes, Natalia and Butts, John C. and Mouri, Kousuke and Alasoadura, Michael and Kales, Susan and Nguyen, Thanh Thanh L. and Noche, Ramil R. and Rao, Arya S. and Joy, Mary T. and Sabeti, Pardis C. and Reilly, Steven K. and Tewhey, Ryan},
  journal={Nature},
  volume={634},
  pages={1211--1220},
  year={2024},
  doi={10.1038/s41586-024-08070-z},
  url={https://doi.org/10.1038/s41586-024-08070-z}
}

@misc{gosai2024machine_zenodo,
  title={Machine-guided design of cell-type-targeting cis-regulatory elements},
  author={Gosai, Sager and Castro, Rodrigo and Fuentes, Natalia and Butts, John and Mouri, Kousuke and Alasoadura, Michael and Kales, Susan and Nguyen, Thanh Thanh and Noche, Ramil and Rao, Arya and Joy, Mary Teena and Sabeti, Pardis and Reilly, Steven and Tewhey, Ryan},
  year={2024},
  publisher={Zenodo},
  version={1.0},
  doi={10.5281/zenodo.10698014},
  url={https://doi.org/10.5281/zenodo.10698014},
  note={Supplemental data and resources for the Nature article, including the Malinois model artifact}
}

Copy citation

Score DNA sequences with Malinois as a bounded lower-is-better objective.

API Reference

ConfigMalinoisActivityConfig Source

Configuration for Malinois regulatory DNA activity scoring.

Malinois predicts MPRA activity for 200 bp DNA inserts in K562, HepG2, and SK-N-SH contexts. This constraint maps the requested raw cell-type score to a bounded lower-is-better objective:

For direction="max":

score = 1 - sigmoid((raw_score - sigmoid_center) / sigmoid_scale)

For direction="min":

score = sigmoid((raw_score - sigmoid_center) / sigmoid_scale)

With the default center of 4.0, raw scores above 4.0 receive penalties below 0.5 in maximization mode and above 0.5 in minimization mode.

cell_type · enum · default: "K562"

Malinois cell-type output to optimize.

Options: K562, HepG2, SKNSH

direction · enum · default: "max"

Use ‘max’ to encourage activity or ‘min’ to suppress activity in the selected cell type.

Options: max, min

sigmoid_center · number · default: "4.0"

Raw Malinois score where the transformed constraint score is 0.5.

sigmoid_scale · number · default: "1.0"

Positive scale for the raw-score sigmoid transform.

seq_length · integer · default: "200"

Expected DNA insert length before Malinois MPRA flank padding.

artifact_path · string · default: ""

Optional local artifact tarball path; empty uses the managed cache download.

artifact_url · string

HTTPS URL used to provision the Malinois artifact.

artifact_md5 · string · default: "375142a714e7df73c463b46113a65210"

Expected MD5 checksum for the downloaded Malinois artifact.

malinois_dir · string · default: ""

Optional local Malinois metadata directory; empty uses the managed cache extraction.

batch_size · integer · default: "1"

Number of sequences to score simultaneously on GPU.

device · string · default: "cuda"

Device for Malinois inference.

Usage

python

from proto_language.core import Constraint
from proto_language.constraint import malinois_activity_constraint, MalinoisActivityConfig

constraint = Constraint(
    inputs=[segment],
    function=malinois_activity_constraint,
    function_config=MalinoisActivityConfig(
        # Configure parameters here
    ),
)

scores = constraint.evaluate()

Metadata

Property	Value
Key	malinois-activity
Function	malinois_activity_constraint
Category	sequence_annotation
Mode	discrete
Uses GPU	True
Supported Types	dna