arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.13802cs.LGcs.AIcs.CEq-bio.QM
收藏

通过潜在空间融合改进分子性质预测

Improving Molecular Properties Prediction Through Latent Space Fusion

IBM Research - Brazil(IBM研究院(巴西));IBM Research - Japan(IBM研究院(日本))

Eduardo Soares, Akihiro Kishimoto, Emilio Vital Brazil, Seiji Takeda, Hiroshi Kajino, Renato Cerqueira

AI总结:

本文提出一种融合 MHG-GNN 和 MoLFormer 潜在空间的多视图方法,通过结合图结构与化学语言嵌入提升分子性质预测,在六个基准数据集中有五个优于现有方法。

摘要:

预训练语言模型已成为预测分子性质的有前景的工具,但其发展仍处于早期阶段,需要进一步研究以提高其有效性并解决泛化和样本效率等挑战。在本文中,我们提出了一种多视图方法,该方法结合了源自最先进化学模型的潜在空间。我们的方法依赖于两个关键要素:源自 MHG-GNN 的嵌入(将分子结构表示为图)和植根于化学语言的 MoLFormer 嵌入。MoLFormer 的注意力机制能够识别即使相距很远的两个原子之间的关系,而 MHG-GNN 的 GNN 可以更精确地捕获紧密位于多个原子之间的关系。在这项工作中,我们展示了我们提出的多视图方法与现有最先进方法(包括在 11 亿个分子上训练的 MoLFormer-XL)相比的卓越性能,特别是在预测临床试验药物毒性和抑制 HIV 复制等复杂任务中。我们使用来自 MoleculeNet 的六个基准数据集评估了我们的方法,其中它在五个数据集中优于竞争对手。我们的研究突出了潜在空间融合和特征集成在推进分子性质预测方面的潜力。在这项工作中,我们使用了 MHG-GNN 和 MoLFormer 的小版本,这为我们的方法使用更大规模数据集时进一步改进提供了机会。

英文摘要:

Pre-trained Language Models have emerged as promising tools for predicting molecular properties, yet their development is in its early stages, necessitating further research to enhance their efficacy and address challenges such as generalization and sample efficiency. In this paper, we present a multi-view approach that combines latent spaces derived from state-of-the-art chemical models. Our approach relies on two pivotal elements: the embeddings derived from MHG-GNN, which represent molecular structures as graphs, and MoLFormer embeddings rooted in chemical language. The attention mechanism of MoLFormer is able to identify relations between two atoms even when their distance is far apart, while the GNN of MHG-GNN can more precisely capture relations among multiple atoms closely located. In this work, we demonstrate the superior performance of our proposed multi-view approach compared to existing state-of-the-art methods, including MoLFormer-XL, which was trained on 1.1 billion molecules, particularly in intricate tasks such as predicting clinical trial drug toxicity and inhibiting HIV replication. We assessed our approach using six benchmark datasets from MoleculeNet, where it outperformed competitors in five of them. Our study highlights the potential of latent space fusion and feature integration for advancing molecular property prediction. In this work, we use small versions of MHG-GNN and MoLFormer, which opens up an opportunity for further improvement when our approach uses a larger-scale dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑