| 徐涛,秦越,单伟,贾辰阳,朱加良,邓志光,李卓玥,刘丹会.化学通报,2023,86(3):312-322. |
| 基于人工智能和互联网时代的化合物毒性预测综述 |
| A review: Toxicity prediction based on artificial intelligence and the Internet era |
| 投稿时间：2021-06-08 修订日期：2022-08-09 |
| DOI： |
| 中文关键词: 人工智能 深度学习 机器学习 毒性预测 网络服务器 |
| 英文关键词:artificial intelligence deep learning machine learning toxicity prediction web server |
| 基金项目: |
|
| 摘要点击次数: 417 |
| 全文下载次数: 14 |
| 中文摘要: |
| 随着商品中所含各种化合物的不断使用,人们日益关注其对人类及生态环境的安全危害。在过去的几年里,通过计算方法预测化合物毒性已经显示出极大的潜力。在此,总结了常用的机器学习和深度学习算法在建立毒性预测模型上的优缺点,并系统回顾了近三年发表的可免费访问的毒性预测网络服务器。此外,还讨论了基于人工智能和互联网时代下毒性预测所面临的机遇和挑战。希望指导人们合理的选择算法和网络服务器进行建模及化合物毒性评估。 |
| 英文摘要: |
| With the continuous using compounds contained in commodities, there is growing concern about their safety hazards on human and environment. In the past few years, computational techniques have showed their potential to predict toxicity of compounds. Here, we summarize the advantages and drawbacks of machine learning and deep learning algorithms for establishing toxicity prediction models, and systematic review the last three years of freely accessible web servers for in silico toxicity prediction. Additionally, the opportunities and challenges of toxicity prediction based on artificial intelligence and Internet are discussed. In order to guide rational selection algorithms and web servers for modeling and toxicity evaluation. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|