Algebraic Graph-assisted Bidirectional Transformers for Molecular Prediction-猫眼课题宝

DOI：

10.21203/rs.3.rs-152856/v1

发表时间：

2021-01

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Dong Chen;Kaifu Gao;D. Nguyen;Xin Chen;Yi Jiang;G. Wei;F. Pan

分子定量预测的能力对药物开发、人类健康和环境保护具有重要意义。尽管付出了巨大的努力，各种分子性质的定量预测仍然是一个挑战。尽管一些机器学习模型，例如来自变压器的双向编码器，可以通过自监督学习策略将大量未标记的分子数据合并到分子表示中，但它忽略了三维立体化学信息。代数图，特别是特定元素的多尺度加权彩色代数图，将互补的三维分子信息嵌入到图不变量中。我们提出了一个代数图辅助双向变压器（AGBT）模型，该模型融合了代数图和双向变压器生成的表示，以及各种机器学习算法，包括决策树、多任务学习和深度神经网络。我们在五个基准分子数据集上验证了所提出的AGBT模型，包括定量毒性和分配系数。大量的数值实验表明，AGBT在所有这些分子预测方面优于所有其他现有方法。

The ability of quantitative molecular prediction is of great significance to drug discovery, human health, and environmental protection. Despite considerable efforts, quantitative prediction of various molecular properties remains a challenge. Although some machine learning models, such as bidirectional encoder from transformer, can incorporate massive unlabeled molecular data into molecular representations via a self-supervised learning strategy, it neglects three-dimensional (3D) stereochemical information. Algebraic graph, specifically, element-specific multiscale weighted colored algebraic graph, embeds complementary 3D molecular information into graph invariants. We propose an algebraic graph-assisted bidirectional transformer (AGBT) model by fusing representations generated by algebraic graph and bidirectional transformer, as well as a variety of machine learning algorithms, including decision trees, multitask learning, and deep neural networks. We validate the proposed AGBT model on five benchmark molecular datasets, involving quantitative toxicity and partition coefficient. Extensive numerical experiments suggest that AGBT outperforms all other existing methods for all these molecular predictions.

Algebraic Graph-assisted Bidirectional Transformers for Molecular Prediction

文献摘要

相似文献