NExT-Mol：3D扩散与1D语言建模结合用于3D分子生成
NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation
AI总结：
NExT-Mol结合1D语言模型和3D扩散模型，实现高有效性3D分子生成，在GEOM-DRUGS和QM9-2014上分别提升26%和13%的3D FCD。
摘要：
3D分子生成对于药物发现和材料设计至关重要。尽管先前的工作侧重于3D扩散模型，因其在建模连续3D构象方面的优势，但它们忽略了基于1D SELFIES的语言模型（LMs）的优势，后者能够生成100%有效的分子，并利用十亿规模的1D分子数据集。为了结合这些优势用于3D分子生成，我们提出了一个基础模型——NExT-Mol：3D扩散与1D语言建模结合用于3D分子生成。NExT-Mol使用一个经过广泛预训练的分子LM进行1D分子生成，随后通过3D扩散模型预测所生成分子的3D构象。我们通过扩大LM的模型规模、改进扩散神经架构以及应用1D到3D的迁移学习来增强NExT-Mol的性能。值得注意的是，我们的1D分子LM在分布相似性方面显著优于基线，同时确保有效性，而我们的3D扩散模型在构象预测方面达到了领先性能。鉴于这些在1D和3D建模方面的改进，NExT-Mol在GEOM-DRUGS上的从头3D生成中实现了3D FCD相对改进26%，在QM9-2014上的条件3D生成中实现了平均相对增益13%。我们的代码和预训练检查点可在https://github.com/acharkq/NExT-Mol获取。
英文摘要：
3D molecule generation is crucial for drug discovery and material design. While prior efforts focus on 3D diffusion models for their benefits in modeling continuous 3D conformers, they overlook the advantages of 1D SELFIES-based Language Models (LMs), which can generate 100% valid molecules and leverage the billion-scale 1D molecule datasets. To combine these advantages for 3D molecule generation, we propose a foundation model -- NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation. NExT-Mol uses an extensively pretrained molecule LM for 1D molecule generation, and subsequently predicts the generated molecule's 3D conformers with a 3D diffusion model. We enhance NExT-Mol's performance by scaling up the LM's model size, refining the diffusion neural architecture, and applying 1D to 3D transfer learning. Notably, our 1D molecule LM significantly outperforms baselines in distributional similarity while ensuring validity, and our 3D diffusion model achieves leading performances in conformer prediction. Given these improvements in 1D and 3D modeling, NExT-Mol achieves a 26% relative improvement in 3D FCD for de novo 3D generation on GEOM-DRUGS, and a 13% average relative gain for conditional 3D generation on QM9-2014. Our codes and pretrained checkpoints are available at https://github.com/acharkq/NExT-Mol.
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。
