AI 中文总结
研究提出AlphaFold2的参数可直接分析，通过高斯卷积等方法揭示其产生物理结构化构象景观，经实验验证不同蛋白在扰动下的表现，表明其权重编码结构约束，此方法被称为神经光谱，为研究蛋白质结构提供新视角。
AI 中文摘要
AlphaFold2拥有9300万个参数，由蛋白质数据库和序列比对中编码的蛋白质结构进化记录塑造，传统上仅被视为将序列转换为结构的工具。我们提出它也是一个可直接分析的科学对象：一种可探测和表征的蛋白质构象组织的学习编码。通过用高斯卷积平滑Evoformer的权重张量并缩放结果，表明训练后的模型产生物理结构化的构象景观。在扰动下，泛素的天然接触按数十年折叠实验确定的顺序断裂。对于KaiB，五个独立训练的模型一致认为在扰动下无法恢复替代折叠。对于α-突触核蛋白，五个模型产生五个不同但连贯的景观，映射出训练信号决定表征的位置和未决定的位置。匹配功率噪声控制证实，同等大小的随机破坏产生碎片而非构象。该模型学会预测静态结构；扰动下可见的构象组织并非明确的训练目标，表明它是该目标的副产品。AlphaFold2的权重似乎编码了由进化和结构训练数据塑造的结构约束，超出了无扰动推断所揭示的范围。我们将读取它们的方法称为神经光谱，缩放高斯卷积就是这样一种协议。
英文摘要
AlphaFold2's 93 million parameters, shaped by the evolutionary record of protein structure encoded in the Protein Data Bank and in sequence alignments, are conventionally treated only as machinery for converting sequence to structure. We propose they are also a scientific object that can be analyzed directly: a learned encoding of protein conformational organization that can be probed and characterized. By smoothing the Evoformer's weight tensors with a Gaussian convolution and scaling the result, we show that the trained model produces physically structured conformational landscapes. Under perturbation, ubiquitin's native contacts break in the order established by decades of folding experiments. For KaiB, five independently trained models agree that the alternative fold is not recovered under perturbation. For alpha-synuclein, five models produce five different but coherent landscapes, mapping where the training signal has determined the representation and where it has not. Matched-power noise controls confirm that random corruption of equal magnitude produces debris, not conformations. The model learned to predict static structures; the conformational organization visible under perturbation was not an explicit training target, suggesting it emerged as a byproduct of that objective. AlphaFold2's weights appear to encode structural constraints, shaped by evolutionary and structural training data, that extend beyond what unperturbed inference reveals. We call the approach of reading them neural spectroscopy, and Scaled Gaussian Convolution one such protocol.
