Toxicity-Prediction-GCN

KO | EN

gitlite — search

#javascript #python #react #ai #typescript #llm #linux #docker #macos #java #awesome #cli #pytorch #open-source

Toxicity-Prediction-GCN

(★ 10)

A Graph convolution neural network based toxicity prediction, project of SJTU-CS410 Artificial Intelligence(B),2020 Fall

Toxicity-Prediction-GCN 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Toxicity Prediction GCN

### :book: Introduction

During our lifetimes, we are exposed to different chemicals and some of which may be toxic and harmful to our health. It is ideal and promising that a time saving and human-free toxicity prediction methods is developed for human or animals involved toxicity tests are quite time-consuming and dangerous. Deep neural networks, in this case, are ideal to conquer this problem with large amount of data. GCN, with an accuracy of 88.798% are used to solve the problem.

### :earth_asia: Environment

![](https://img.shields.io/badge/Python-3.7.9-green)![](https://img.shields.io/badge/Pytorch-1.1.0-orange)![](https://img.shields.io/badge/rdkit-2020-blue)

### :oil_drum: Data set

The data set is from the kaggle competition [Drug Molecular Toxicity Prediction](https://www.kaggle.com/c/cs410-2020-fall-ai-project-1).

### :m: Model

![](https://github.com/PeiyuChen1005/Toxicity-Prediction-GCN/blob/main/img/GCN.png?raw=true)

### :triangular_flag_on_post: Performance

| AUC of Training set and Validation set | AUC of Test set |
| -------------------------------------- | --------------- |
| 87.964%                                | 88.798%         |

Toxicity-Prediction-GCN

Toxicity-Prediction-GCN 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Toxicity-Prediction-GCN

Toxicity-Prediction-GCN 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README