AlphaFold has transformed protein structure prediction, but emerging applications such as virtual ligand screening, proteome-wide folding, and de novo binder design demand predictions at a massive scale, where runtime and memory costs become prohibitive. A major bottleneck lies in the Pairformer backbone of AlphaFold3-style models, which relies on computationally expensive triangular primitives-especially triangle attention-for pairwise reasoning. We introduce Pairmixer, a streamlined alternative that eliminates triangle attention while preserving higher-order geometric reasoning capabilities that are critical for structure prediction. Pairmixer substantially improves computational efficiency, matching state-of-the-art structure predictors across folding and docking benchmarks, delivering up to 4x faster inference on long sequences while reducing training cost by 34%. Its efficiency alleviates the computational burden of downstream applications such as modeling large protein complexes, high-throughput ligand and binder screening, and hallucination-based design. Within BoltzDesign, for example, Pairmixer delivers over 2x faster sampling and scales to sequences ~30% longer than the memory limits of Pairformer. Code is available at https://github.com/genesistherapeutics/pairmixer.

翻译：AlphaFold 已彻底改变了蛋白质结构预测领域，但虚拟配体筛选、全蛋白质组折叠及从头设计结合蛋白等新兴应用需要大规模预测，此时运行时间和内存成本变得难以承受。主要瓶颈在于 AlphaFold3 风格模型中的 Pairformer 主干网络，该网络依赖计算成本高昂的三角形原语——尤其是三角形注意力机制——进行成对推理。我们提出 Pairmixer，一种简化的替代方案，它消除了三角形注意力，同时保留了结构预测所需的关键高阶几何推理能力。Pairmixer 显著提升了计算效率，在折叠和对接基准测试中与最先进的结构预测模型性能相当，在长序列上实现高达 4 倍的推理加速，并将训练成本降低 34%。其高效性减轻了下游应用的计算负担，例如大型蛋白质复合物建模、高通量配体与结合蛋白筛选，以及基于幻觉的设计。以 BoltzDesign 为例，Pairmixer 实现了超过 2 倍的采样速度，并可处理比 Pairformer 内存限制长约 30% 的序列。代码发布于 https://github.com/genesistherapeutics/pairmixer。