DGL-LifeSci：生命科学图深度学习的开源工具包,ACS Omega

当前位置： X-MOL 学术 › ACS Omega › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

DGL-LifeSci：生命科学图深度学习的开源工具包
ACS Omega ( IF 3.7 ) Pub Date : 2021-10-05 , DOI: 10.1021/acsomega.1c04017
Mufei Li ₁ , Jinjing Zhou ₁ , Jiajing Hu ₂ , Wenxuan Fan ₃ , Yangkang Zhang ₄ , Yaxin Gu ₃ , George Karypis _{5,

6}

Affiliation

图神经网络（GNN）构成了一类图数据的深度学习方法。它们在化学和生物学中具有广泛的应用，例如分子性质预测、反应预测和药物-靶标相互作用预测。尽管有兴趣，基于 GNN 的建模仍然具有挑战性，因为除了编程和深度学习之外，它还需要图数据预处理和建模。在这里，我们展示了深度图库 (DGL)-LifeSci，这是一个用于生命科学图深度学习的开源包。Deep Graph Library (DGL)-LifeSci 是一个基于 RDKit、PyTorch 和 Deep Graph Library (DGL) 的 Python 工具包。DGL-LifeSci 允许在自定义数据集上进行基于 GNN 的建模，用于分子特性预测、反应预测和分子生成。凭借其命令行界面，用户无需任何编程和深度学习背景即可进行建模。我们使用标准基准测试 MoleculeNet、USPTO 和 ZINC 测试命令行界面。与之前的实现相比，DGL-LifeSci 实现了高达 6 倍的速度提升。为了建模灵活性，DGL-LifeSci 为建模管道的各个阶段提供了优化良好的模块。此外，DGL-LifeSci 提供了预训练模型，用于重现测试实验结果和应用无需训练的模型。该代码在 Apache-2.0 许可下分发，可在 https://github.com/awslabs/dgl-lifesci 上免费访问。DGL-LifeSci 为建模管道的各个阶段提供了优化良好的模块。此外，DGL-LifeSci 提供了预训练模型，用于重现测试实验结果和应用无需训练的模型。该代码在 Apache-2.0 许可下分发，可在 https://github.com/awslabs/dgl-lifesci 上免费访问。DGL-LifeSci 为建模管道的各个阶段提供了优化良好的模块。此外，DGL-LifeSci 提供了预训练模型，用于重现测试实验结果和应用无需训练的模型。该代码在 Apache-2.0 许可下分发，可在 https://github.com/awslabs/dgl-lifesci 上免费访问。

"点击查看英文标题和摘要"

DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life Science

Graph neural networks (GNNs) constitute a class of deep learning methods for graph data. They have wide applications in chemistry and biology, such as molecular property prediction, reaction prediction, and drug–target interaction prediction. Despite the interest, GNN-based modeling is challenging as it requires graph data preprocessing and modeling in addition to programming and deep learning. Here, we present Deep Graph Library (DGL)-LifeSci, an open-source package for deep learning on graphs in life science. Deep Graph Library (DGL)-LifeSci is a python toolkit based on RDKit, PyTorch, and Deep Graph Library (DGL). DGL-LifeSci allows GNN-based modeling on custom datasets for molecular property prediction, reaction prediction, and molecule generation. With its command-line interfaces, users can perform modeling without any background in programming and deep learning. We test the command-line interfaces using standard benchmarks MoleculeNet, USPTO, and ZINC. Compared with previous implementations, DGL-LifeSci achieves a speed up by up to 6×. For modeling flexibility, DGL-LifeSci provides well-optimized modules for various stages of the modeling pipeline. In addition, DGL-LifeSci provides pretrained models for reproducing the test experiment results and applying models without training. The code is distributed under an Apache-2.0 License and is freely accessible at https://github.com/awslabs/dgl-lifesci.

更新日期：2021-10-19

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南