Abstract:Molecular representation learning has become a central approach in AI-driven drug discovery, yet existing molecular tokenizations such as SMILES remain largely syntactic and do not naturally align with chemically meaningful substructures. In this work, we introduce VQ-Atom, a semantic discretization framework that converts continuous atom-level graph representations into discrete tokens corresponding to local chemical environments. Using graph neural network embeddings and vector quantization, atoms are assigned to codebook entries representing chemically meaningful atomic contexts. These discrete tokens define a molecular language suitable for Transformer-based pretraining.
We evaluate VQ-Atom in protein-ligand interaction prediction under a protein-cold split setting without relying on 3D structural information. Experimental results show that VQ-Atom consistently improves predictive performance compared to conventional tokenization approaches, suggesting that semantically grounded discretization can substantially enhance molecular representation learning. Our findings indicate that token design itself plays a critical role in enabling effective language modeling for chemistry.
| Comments: | 7 pages, 6 figures. Submitted to ICML 2026 Workshop on Foundation Models for Life Sciences |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.16823 [cs.LG] |
| (or arXiv:2605.16823v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.16823 arXiv-issued DOI via DataCite (pending registration) |
From: Takayuki Kimura [view email]
[v1]
Sat, 16 May 2026 05:45:54 UTC (2,316 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。