SpliceTransformer tissue specificity score

Score tissue-specific splicing with SpliceTransformer on three segments concatenated into one 1-kb target.

License: SpliceTransformer is open source and free for academic and commercial use under an Apache-2.0 license. 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/rna_splicing/splice_transformer_specificity.py

View source

@article{you2024splicetransformer,
  title={SpliceTransformer predicts tissue-specific splicing linked to human diseases},
  author={You, Ningyuan and Liu, Chang and Gu, Yuxin and Wang, Rong and Jia, Hanying and Zhang, Tianyun and Jiang, Song and Shi, Jinsong and Chen, Ming and Guan, Min-Xin and Sun, Siqi and Pei, Shanshan and Liu, Zhihong and Shen, Ning},
  journal={Nature Communications},
  volume={15},
  number={1},
  pages={9129},
  year={2024},
  doi={10.1038/s41467-024-53088-6}
}

Copy citation

Score tissue-specific splice site usage for three-segment intron boundaries.

Accepts three segments (left_flank, intron_core, right_flank), concatenates them into a single 1-kb target sequence, and scores tissue-specific splice site usage.

API Reference

ConfigSpliceTransformerSpecificityConfig Source

Configuration for SpliceTransformer tissue-specific splicing constraint.

This class defines configuration parameters for evaluating tissue-specific splicing patterns using SpliceTransformer, a deep learning model trained to predict splice site usage across different human tissues. The constraint can be used to either maximize splicing in a specific tissue (tissue-specific activation) or minimize it (tissue-specific repression), enabling design of sequences with controlled tissue-specific alternative splicing.

left_context · string · required

Sequence of the left context for SpliceTransformer

right_context · string · required

Sequence of the right context for SpliceTransformer

splice_pos · List[integer] · required

0-indexed position(s) into the concatenated target sequence on which to compute the score

tissue · enum · default: "AVERAGE"

Tissue on which to define the score. By default, averages across all tissues.

Options: AVERAGE, ADIPOSE_TISSUE, BLOOD, BLOOD_VESSEL, BRAIN, COLON, HEART, KIDNEY, LIVER, LUNG, MUSCLE, NERVE, SMALL_INTESTINE, SKIN, SPLEEN, STOMACH

direction · enum · default: "max"

Whether to maximize or minimize the value. Defaults to ‘max’

Options: max, min

splice_transformer_config · SpliceTransformerConfig

Advanced parameter configuration for SpliceTransformer.

ReturnsConstraintOutput

One result per input. score is in [0.0, 1.0] (interpretation depends on direction). metadata carries specificity_direction_<tissue> and specificity_score_<tissue>.

Usage

python

from proto_language.core import Constraint
from proto_language.constraint import splice_transformer_specificity, SpliceTransformerSpecificityConfig

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

scores = constraint.evaluate()

Metadata

Property	Value
Key	splice-transformer-specificity
Function	splice_transformer_specificity
Category	rna_splicing
Mode	discrete
Uses GPU	True
Supported Types	dna