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 2602.13249q-bio.BMcs.AIcs.LG
收藏

小分子学习的共折叠模型表示的系统评估

A Systematic Evaluation of Co-folding Model Representations for Small-Molecule Learning

KAIST(韩国科学技术院)

Hyosoon Jang, Hyunjin Seo, Honghui Kim, Seonghyun Park, Taewon Kim, Yunhui Jang, Sungsoo Ahn

AI总结:

本研究利用现代共折叠模型Boltz2,通过系统探测和蒸馏,评估其原子级配体表示在小分子任务中的表现,发现共折叠表示在ADMET基准上匹配或超越现有模型,加速分子生成建模,并提高结构引导配体优化的样本效率,表明蛋白质-配体共折叠是小分子表示学习的有前景的预训练范式。

摘要:

小分子基础模型通常仅在独立分子数据上进行预训练,这与视觉和语言模型不同,后者通常受益于跨模态或关系监督。蛋白质-配体共折叠通过将模型暴露于原子级配体-蛋白质相互作用,提供了这种监督的分子类似物,引发了一个问题:共折叠模型能否产生强大的小分子表示。我们使用现代共折叠模型Boltz2研究这个问题,通过将其原子级配体表示转移到独立的小分子任务。通过系统探测和蒸馏,我们表明Boltz2表示在ADMET基准上匹配或超越现有模型,加速分子生成建模,并提高结构引导配体优化的样本效率。我们进一步发现Boltz2表示与从传统独立分子监督(包括3D构象、生物测定标签和量子化学性质)中学习到的表示互补。最后,我们将表示对齐扩展到强化学习,表明密集的表示级监督可以补充分子发现中的标量奖励。这些结果将蛋白质-配体共折叠确定为小分子表示学习的有前景的预训练范式,并将Boltz2定位为强大的现成分子基础模型。

英文摘要:

Small-molecule foundation models are typically pretrained on standalone molecular data, unlike vision and language models that often benefit from cross-modal or relational supervision. Protein-ligand co-folding provides a molecular analogue of such supervision by exposing models to atom-level ligand-protein interactions, raising the question of whether co-folding models can yield strong small-molecule representations. We study this question using Boltz2, a modern co-folding model, by transferring its atom-level ligand representations to standalone small-molecule tasks. Through systematic probing and distillation, we show that Boltz2 representations match or outperform existing models on the ADMET benchmark, accelerate molecular generative modeling, and improve sample efficiency in structure-guided ligand optimization. We further find that Boltz2 representations are complementary to those learned from conventional standalone molecular supervision, including 3D conformers, bioassay labels, and quantum-chemical properties. Finally, we extend representation alignment to reinforcement learning, showing that dense representation-level supervision can complement scalar rewards in molecular discovery. These results identify protein-ligand co-folding as a promising pretraining paradigm for small-molecule representation learning and position Boltz2 as a strong, off-the-shelf molecular foundation model.

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。

↑