Packora：生成式分子晶体结构预测的系统设计

中文摘要 AI 辅助

分子晶体结构预测（CSP）在制药、农用化学品和有机电子领域具有重要意义，分子构象与堆积的细微差异会强烈影响材料性能。我们提出Packora，一种用于分子CSP的基于流的生成模型，可从分子图联合预测原子坐标与晶格。Packora支持多组分晶体和有机金属晶体，且能在单一模型中基于分子构象体、立体化学标签和空间群信息的任意子集进行条件生成。受CCDC CSP盲测启发，我们分别评估生成与排序性能：生成环节用于分离生成器质量，排序环节则在通用弛豫与排序流程下测量端到端性能。我们还系统研究了架构、训练、条件生成、推理及缩放，确定了基于可缓存成对推理、训练目标与数值求解器选择、条件丢弃及成对与单表示平衡缩放的有效设计。Packora在结构生成与排序基准上均优于基线模型，在全部6项生成基准中实现了最佳匹配预算覆盖率，同时具备更高的实验形式恢复率、更低的实验形式排名，以及更快的排序收敛速度。

英文摘要

Molecular crystal structure prediction (CSP) is important in pharmaceuticals, agrochemicals, and organic electronics, where subtle differences in molecular conformation and packing can strongly affect material properties. We present Packora, a flow-based generative model for molecular CSP that jointly predicts atomic coordinates and the lattice from molecular graphs. Packora supports multi-component and organometallic crystals and can condition on any subset of molecular conformers, stereochemical labels, and space-group information within a single model. Inspired by the CCDC CSP blind test, we evaluate generation and ranking separately, using generation to isolate generator quality and ranking to measure end-to-end performance under a common relaxation and ranking pipeline. We also systematically study architecture, training, conditioning, inference, and scaling, identifying an effective design based on cacheable pairwise reasoning, training objective and numerical solver choices, conditioning dropout, and balanced scaling of pairwise and single representations. Packora outperforms the baselines on both structure generation and ranking benchmarks, achieving the best matched-budget coverage across all six generation benchmarks, as well as higher experimental-form recovery, lower experimental-form ranks, and faster convergence in ranking.

发表机构

• Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

37 pages, 21 figures