AI 中文总结
UBio-MolFM是经1.6亿量子化学标签训练的基础模型，可在单GPU上以近线性成本实现DFT精度的10^5原子生物分子动力学模拟，突破了第一性原理模拟的原子数限制，能重现关键生物过程的结构与能量特征。
AI 中文摘要
离子传导、膜渗透和金属识别依赖于电子结构，但第一性原理模拟仅能处理数百个原子。UBio-MolFM打破了这一限制：它是一个在1.6亿个量子化学标签上训练的基础模型，其感受野覆盖非共价距离，且计算成本接近线性。瓶颈在于成本而非原理。一个未调谐的势在原子数超过1000时仍保持力误差接近20 meV/Å，重现了水的X射线结构和离子水合作用，且无需离子特异性参数即可稳定RNA的Mg²⁺位点。环孢素A在水中为其可渗透构象付出了3.5 kcal/mol的能量代价，该构象由一个动力学不对称氢键门控，而固定电荷模型会将该氢键抹平。在单个GPU上的108964原子KcsA通道模拟中，五个复制品的松弛四离子柱均无水，其中四个复制品的离子直接接触，形成了十个固定电荷模拟从未得到的碰撞几何结构，而该模拟的成本仍比第一性原理模拟低几个数量级。当电子结构决定结果时，第一性原理模拟成为可行之选。
英文摘要
Ion conduction, membrane permeation and metal recognition hinge on electronic structure, yet first-principles simulation reaches only hundreds of atoms. UBio-MolFM lifts that ceiling: a foundation model trained on 160 million quantum-chemical labels, its receptive field spanning non-covalent distances at near-linear cost. The barrier is cost, not principle. One untuned potential keeps force error near 20 meV/Å past a thousand atoms, reproduces water's X-ray structure and ion hydration, and holds an RNA Mg$^{2+}$ site without ion-specific parameters. Cyclosporine A pays 3.5 kcal/mol in water for its permeable conformer, gated by one kinetically asymmetric hydrogen bond that a fixed-charge model flattens. In a 108,964-atom KcsA channel on one GPU, the relaxed four-ion column is anhydrous in all five replicas, in direct contact in four---the knock-on geometry ten fixed-charge simulations never form. It remains orders of magnitude costlier. Where electronic structure decides the answer, first-principles simulation is in reach.
