arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.02130cs.LGq-bio.QM
收藏

基于三维形状相似性的分子表示学习对比方法

A 3D-Shape Similarity-based Contrastive Approach to Molecular Representation Learning

Genentech Research and Early Development(基因泰克研究与早期开发部);Stanford University(斯坦福大学)

Austin Atsango, Nathaniel L. Diamant, Ziqing Lu, Tommaso Biancalani, Gabriele Scalia, Kangway V. Chuang

摘要:

分子的形状和几何形状决定了关键的生物物理识别过程,然而许多图神经网络忽略了分子性质预测的3D信息。在这里,我们提出了一个新的对比学习过程的图神经网络,分子对比学习从形状相似性(MolCLaSS),隐式学习的三维表示。MolCLaSS不是直接编码或靶向三维姿态,而是基于高斯叠加匹配相似性目标,以学习分子形状的有意义的表示。我们展示了这个框架如何自然地捕捉二维表示不能的三维的关键方面,并提供了一个诱导框架的脚手架跳跃。

英文摘要:

Molecular shape and geometry dictate key biophysical recognition processes, yet many graph neural networks disregard 3D information for molecular property prediction. Here, we propose a new contrastive-learning procedure for graph neural networks, Molecular Contrastive Learning from Shape Similarity (MolCLaSS), that implicitly learns a three-dimensional representation. Rather than directly encoding or targeting three-dimensional poses, MolCLaSS matches a similarity objective based on Gaussian overlays to learn a meaningful representation of molecular shape. We demonstrate how this framework naturally captures key aspects of three-dimensionality that two-dimensional representations cannot and provides an inductive framework for scaffold hopping.

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。

↑