arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.08830cs.LGcs.CLphysics.chem-ph
收藏

基于对比预训练的多语言分子表示学习

Multilingual Molecular Representation Learning via Contrastive Pre-training

Microsoft Corporation(微软公司)

Zhihui Guo, Pramod Sharma, Andy Martinez, Liang Du, Robin Abraham

摘要:

分子表示学习在化学信息学中起着重要的作用。最近,基于语言模型的方法作为传统的专家设计的特征来编码分子的替代方案已经得到普及。然而,这些方法仅利用单个分子语言进行表示学习。一个给定的分子可以使用不同的语言,如简化的分子线输入系统(SMILES),国际纯粹与应用化学联合会(IUPAC),和国际化学标识符(InChI)的动机,我们提出了一种多语言的分子嵌入生成方法,称为MM-Deacon(通过对比学习的多语言分子结构域嵌入分析)。MM-Deacon使用SMILES和IUPAC作为大规模分子的两种不同语言进行预训练。我们评估了我们的方法对MoleculeNet基准的七个分子性质预测任务,zero-shot跨语言检索和药物相互作用预测任务的鲁棒性。

英文摘要:

Molecular representation learning plays an essential role in cheminformatics. Recently, language model-based approaches have gained popularity as an alternative to traditional expert-designed features to encode molecules. However, these approaches only utilize a single molecular language for representation learning. Motivated by the fact that a given molecule can be described using different languages such as Simplified Molecular Line Entry System (SMILES), The International Union of Pure and Applied Chemistry (IUPAC), and The IUPAC International Chemical Identifier (InChI), we propose a multilingual molecular embedding generation approach called MM-Deacon (multilingual molecular domain embedding analysis via contrastive learning). MM-Deacon is pre-trained using SMILES and IUPAC as two different languages on large-scale molecules. We evaluated the robustness of our method on seven molecular property prediction tasks from MoleculeNet benchmark, zero-shot cross-lingual retrieval, and a drug-drug interaction prediction task.

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。

↑