catELMo

Context-Aware Amino Acid Embedding Advances Analysis of TCR-Epitope Interactions

catELMo is a bi-directional amino acid embedding model that learns contextualized amino acid representations, treating an amino acid as a word and a sequence as a sentence. It learns patterns of amino acid sequences with its self-supervision signal, by predicting each the next amino acid token given its previous tokens. It has been trained on 4,173,895 TCR $beta$ CDR3 sequences (52 million of amino acid tokens) from ImmunoSEQ. catELMo yields a real-valued representation vector for a sequence of amino acids, which can be used as input features of various downstream tasks. This is the official implementation of catELMo.

Publication

Context-Aware Amino Acid Embedding Advances Analysis of TCR-Epitope Interactions
Pengfei Zhang^1,2, Michael Cai^1,2, Seojin Bang², Heewook Lee^1,2
1 School of Computing and Augmented Intelligence, Arizona State University, ² Biodesign Institute, Arizona State University
Published in: eLife, 2023.

Paper | Code | Poster | Slides | Presentation (YouTube)

Dependencies

• Linux
• Python 3.6.13
• Keras 2.6.0
• TensorFlow 2.6.0

Steps to train a Binding Affinity Prediction model for TCR-epitope pairs.

1. Clone the repository

git clone https://github.com/Lee-CBG/catELMo
cd catELMo/
conda create --name bap python=3.6.13
pip install pandas==1.1.5 tensorflow==2.6.0 keras==2.6.0 scikit-learn==0.24.2 tqdm
source activate bap

2. Prepare TCR-epitope pairs for training and testing

• Download training and testing data from datasets folder.
• Obtain embeddings for TCR and epitopes following instructions from embedders folder.

3. Train and test models

An example for epitope split

python -W ignore bap.py 
                --embedding catELMo_4_layers_1024 
                --split epitope 
                --gpu 0 
                --fraction 1 
                --seed 42

Citation

If you use this code or use our catELMo for your research, please cite our paper:

@article {catelmobiorxiv,
	author = {Pengfei Zhang and Seojin Bang and Michael Cai and Heewook Lee},
	title = {Context-Aware Amino Acid Embedding Advances Analysis of TCR-Epitope Interactions},
	elocation-id = {2023.04.12.536635},
	year = {2023},
	doi = {10.1101/2023.04.12.536635},
	publisher = {Cold Spring Harbor Laboratory},
	journal = {bioRxiv}
}

License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.