Skip to main content
Enformer Chromatin Accessibility MORSE
License: Enformer uses Apache-2.0 for code and CC-BY-4.0 for model weights and may require explicit attribution when utilized. Please refer to the code license and model weights 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.


Go to Tool Page
proto-bio/proto-language/proto_language/constraint/sequence_annotation/enformer_chromatin_accessibility_morse_constraint.py
View source
@article{avsec2021enformer,
  title={Effective gene expression prediction from sequence by integrating long-range interactions},
  author={Avsec, {\v{Z}}iga and Agarwal, Vikram and Visentin, Daniel and Ledsam, Joseph R and Grabska-Barwinska, Agnieszka and Taylor, Kyle R and Assael, Yannis and Jumper, John and Kohli, Pushmeet and Kelley, David R},
  journal={Nature Methods},
  volume={18},
  number={10},
  pages={1196--1203},
  year={2021},
  publisher={Nature Publishing Group},
  doi={10.1038/s41592-021-01252-x}
}
Copy citation
Score target proposals against an Enformer chromatin accessibility MORSE objective.

API Reference

ConfigEnformerChromatinAccessibilityMorseConfig Source
Configuration for Enformer chromatin accessibility MORSE scoring.
organism
enum
default:"human"
Enformer species head to use: human or mouse.Options: human, mouse
pattern
string
default:".--. .-. --- - ---"
Morse pattern; use ’.’, ’-’, and spaces between letters.
dot_bp
integer
default:"25"
Length of each dot window.
dash_bp
integer
default:"75"
Length of each dash window.
intra_symbol_gap_bp
integer
default:"25"
Gap between symbols within a letter.
inter_letter_gap_bp
integer
default:"75"
Gap between letters in the Morse pattern.
pattern_start_bp
integer
default:"0"
Target-relative start coordinate where the Morse pattern begins.
pattern_normalization
enum
default:"global_max"
Scale signal by full-output max, target-region max, or not at all.Options: global_max, region_max, none
contrast_margin
number
default:"0.0"
Minimum normalized high-minus-low signal margin to reward.
contrast_weight
number
default:"0.0"
Penalty weight when the normalized contrast margin is too small.
raw_amplitude_weight
number
default:"0.0"
Reward weight for larger raw target signal range.
high_window_reward_weight
number
default:"0.0"
Reward weight for larger raw signal in dot and dash windows.
low_window_penalty_weight
number
default:"0.0"
Penalty weight for larger raw signal in gap windows.
window_stat_transform
enum
default:"log1p"
Transform for raw amplitude and window-mean reward terms.Options: log1p, identity
device
string
default:"cuda"
CUDA device for Enformer inference.
batch_size
integer
default:"1"
Candidate sequences per Enformer model batch.
trim_prefix_bp
integer
default:"0"
Leading target bases to ignore before accessibility scoring.
enformer_output_tracks
List[integer]
default:"[121]"
Enformer chromatin-accessibility tracks; defaults by organism.
enformer_track_reduce_method
enum
default:"mean"
How to combine selected Enformer tracks.Options: mean, min, std, lcb

Usage

python
from proto_language.core import Constraint
from proto_language.constraint import enformer_chromatin_accessibility_morse_constraint, EnformerChromatinAccessibilityMorseConfig

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

scores = constraint.evaluate()

Metadata

PropertyValue
Keyenformer-chromatin-accessibility-morse
Functionenformer_chromatin_accessibility_morse_constraint
Categorysequence_annotation
Modediscrete
Uses GPUTrue
Supported Typesdna