Abstract:Molecular similarity plays a central role in ligand-based drug discovery, such as virtual screening, analog searching, and goal-directed molecular generation. However, traditional similarity measures, ranging from fingerprint-based Tanimoto coefficients to 3D shape overlays, are often computationally expensive at scale or rely on hand-crafted molecular descriptors. Meanwhile, many deep learning approaches to similarity-aware design still depend on similarity-specific supervision or costly data curation, limiting their generality across targets. In this work, we propose pretrained embedding distance (PED) as an effective alternative, computed directly from pretrained molecular models without task-specific training. Experimental results show that PED exhibits distinct correlations with traditional similarity metrics, and performs effectively in both ranking molecules for virtual screening and guiding molecular generation via reward design. These findings suggest that pretrained molecular embeddings capture rich structural information and can serve as a promising and scalable similarity measurement for modern AI-aided drug discovery.
| Comments: | 26 pages, 12 figures, 9 tables |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.24474 [cs.LG] |
| (or arXiv:2604.24474v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.24474 arXiv-issued DOI via DataCite (pending registration) |
From: Shiyun Wa [view email]
[v1]
Mon, 27 Apr 2026 13:43:20 UTC (9,558 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。