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 2602.17602cs.AI
收藏

MolHIT: 通过分层离散扩散模型推进分子图生成

MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models

Hojung Jung, Rodrigo Hormazabal, Jaehyeong Jo, Youngrok Park, Kyunggeun Roh, Se-Young Yun, Sehui Han, Dae-Woong Jeong

AI总结:

MolHIT通过分层离散扩散模型提升分子图生成的有效性和性能,首次在图扩散中实现接近完美的化学有效性,并在多个指标上超越1D基线。

摘要:

分子生成与扩散模型在人工智能驱动的药物发现和材料科学中已成为有前途的方向。尽管图扩散模型由于2D分子图的离散性质被广泛应用,但现有模型在化学有效性方面表现较低,并且难以满足与1D建模相比的期望属性。在本工作中,我们介绍了MolHIT,一种强大的分子图生成框架,克服了现有方法中长期存在的性能限制。MolHIT基于分层离散扩散模型,将离散扩散推广到额外类别,这些类别编码了化学先验知识,并通过解耦原子编码将原子类型根据其化学作用进行划分。总体而言,MolHIT在MOSES数据集上实现了新的最先进的性能,首次在图扩散中实现了接近完美的有效性,在多个指标上超越了强大的1D基线。我们进一步在下游任务中展示了强劲的性能,包括多属性引导生成和支架扩展。

英文摘要:

Molecular generation with diffusion models has emerged as a promising direction for AI-driven drug discovery and materials science. While graph diffusion models have been widely adopted due to the discrete nature of 2D molecular graphs, existing models suffer from low chemical validity and struggle to meet the desired properties compared to 1D modeling. In this work, we introduce MolHIT, a powerful molecular graph generation framework that overcomes long-standing performance limitations in existing methods. MolHIT is based on the Hierarchical Discrete Diffusion Model, which generalizes discrete diffusion to additional categories that encode chemical priors, and decoupled atom encoding that splits the atom types according to their chemical roles. Overall, MolHIT achieves new state-of-the-art performance on the MOSES dataset with near-perfect validity for the first time in graph diffusion, surpassing strong 1D baselines across multiple metrics. We further demonstrate strong performance in downstream tasks, including multi-property guided generation and scaffold extension.

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。

↑