# transformercpi

**Repository Path**: mirrors_lifanchen-simm/transformercpi

## Basic Information

- **Project Name**: transformercpi
- **Description**: TransformerCPI: Improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments(BIOINFORMATICS 2020)  https://doi.org/10.1093/bioinformatics/btaa524
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2023-02-27
- **Last Updated**: 2026-01-25

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# TransformerCPI: Improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments

This repository contains the source code ,the data and trained models.

## TransformerCPI

![](model.png)



## Setup and dependencies 

Dependencies:
- python 3.6
- pytorch >= 1.2.0
- numpy
- RDkit = 2019.03.3.0
- pandas
- Gensim >=3.4.0

## Data sets

The data sets with train/test splits are provided as .7z file in a directory called 'data'. 

The test set is created specially for label reversal experiments.

---

## Using

1.`mol_featurizer.py` generates input for TransformerCPI model.

2.`main.py` trains TransformerCPI model.

---

## Author

Lifan Chen 

Mingyue Zheng

## Citation

Lifan Chen, Xiaoqin Tan, Dingyan Wang, Feisheng Zhong, Xiaohong Liu, Tianbiao Yang, Xiaomin Luo, Kaixian Chen, Hualiang Jiang, Mingyue Zheng, TransformerCPI: improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments, Bioinformatics, Volume 36, Issue 16, 15 August 2020, Pages 4406–4414, https://doi.org/10.1093/bioinformatics/btaa524

## TransformerCPI2.0
TransformerCPI2.0 is now available at https://github.com/lifanchen-simm/transfomerCPI2.0 !