arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.02798cs.LGphysics.chem-phq-bio.QM
收藏

用于将结构层级整合到上下文依赖分子表示中的多通道学习

Multi-channel learning for integrating structural hierarchies into context-dependent molecular representation

University of Pittsburgh(匹兹堡大学);Zhejiang University(浙江大学)

Yue Wan, Jialu Wu, Tingjun Hou, Chang-Yu Hsieh, Xiaowei Jia

AI总结:

针对现有分子自监督学习忽略化学知识、难学构效关系细微变化的问题,提出一种利用分子结构层级、跨通道预训练嵌入、微调时任务特定聚合的新框架,在多基准和活性悬崖场景表现优异。

摘要:

可靠的分子性质预测对于药物发现等各类科学研究和工业应用至关重要。然而,数据稀缺性,加上物理化学性质、生物性质与传统分子特征化方案之间高度非线性的因果关系,使得鲁棒的分子机器学习模型的开发变得复杂。自监督学习(SSL)已成为一种热门解决方案,它利用大规模无标注分子数据来学习化学空间的基础表示,这可能对下游任务有利。但现有的分子SSL方法在化学空间中运行时,很大程度上忽略了化学知识,包括分子结构相似性、骨架组成以及分子性质的上下文依赖方面,也难以学习构效关系中的细微变化。本文提出了一种新型预训练框架,用于学习鲁棒且可泛化的化学知识。该框架利用分子内部的结构层级,通过跨通道的不同预训练任务对其进行嵌入,并在微调期间以任务特定的方式聚合通道信息。我们的方法在各类分子性质基准测试中展现出具有竞争力的性能,在活性悬崖等极具挑战性且普遍存在的场景中具备显著优势。

英文摘要:

Reliable molecular property prediction is essential for various scientific endeavors and industrial applications, such as drug discovery. However, the data scarcity, combined with the highly non-linear causal relationships between physicochemical and biological properties and conventional molecular featurization schemes, complicates the development of robust molecular machine learning models. Self-supervised learning (SSL) has emerged as a popular solution, utilizing large-scale, unannotated molecular data to learn a foundational representation of chemical space that might be advantageous for downstream tasks. Yet, existing molecular SSL methods largely overlook chemical knowledge, including molecular structure similarity, scaffold composition, and the context-dependent aspects of molecular properties when operating over the chemical space. They also struggle to learn the subtle variations in structure-activity relationship. This paper introduces a novel pre-training framework that learns robust and generalizable chemical knowledge. It leverages the structural hierarchy within the molecule, embeds them through distinct pre-training tasks across channels, and aggregates channel information in a task-specific manner during fine-tuning. Our approach demonstrates competitive performance across various molecular property benchmarks and offers strong advantages in particularly challenging yet ubiquitous scenarios like activity cliffs.

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。

↑