DiffSDS：几何条件和约束下蛋白质主链修复的语言扩散模型
DiffSDS: A language diffusion model for protein backbone inpainting under geometric conditions and constraints
摘要：
你是否曾经被SE（3）蛋白质结构建模的复杂性和计算成本所困扰，并对语言建模的简单性和强大功能感到惊讶？最近的工作表明，在简化蛋白质结构的蛋白质角度序列的承诺，因此，语言模型可以用于无约束的蛋白质主链的产生。不幸的是，这种简化不适合于受约束的蛋白质修复问题，其中模型需要恢复以未掩蔽结构为条件的掩蔽结构，因为它显著增加了几何约束的计算成本。为了克服这一困境，我们建议插入一个隐藏的\textbf{a}拓扑\textbf{d}方向\textbf{s}步伐（\textbf{ADS}）的语言模型，转换不变的骨干角度等价的方向向量，并保持简单性，称为Seq 2Direct编码器（$\text{Enc}_{s2d}$）。几何约束可以有效地施加在新引入的方向空间。本文还引入了一种具有数学保证的Direct 2Seq解码器（$\text{Dec}_{d2s}$），建立了一个\textbf{SDS}（$\text{Enc}_{s2d}$ + $\text{Dec}_{d2s}$）模型。在条件扩散过程中，我们应用SDS模型作为去噪神经网络，从而得到一个约束生成模型-- \textbf{DiffSDS}。大量的实验表明，即插即用的ADS可以将语言模型转换成一个强大的结构模型，而不损失简单性。更重要的是，所提出的DiffSDS在蛋白质修复任务上远远优于以前的强基线。
英文摘要：
Have you ever been troubled by the complexity and computational cost of SE(3) protein structure modeling and been amazed by the simplicity and power of language modeling? Recent work has shown promise in simplifying protein structures as sequences of protein angles; therefore, language models could be used for unconstrained protein backbone generation. Unfortunately, such simplification is unsuitable for the constrained protein inpainting problem, where the model needs to recover masked structures conditioned on unmasked ones, as it dramatically increases the computing cost of geometric constraints. To overcome this dilemma, we suggest inserting a hidden \textbf{a}tomic \textbf{d}irection \textbf{s}pace (\textbf{ADS}) upon the language model, converting invariant backbone angles into equivalent direction vectors and preserving the simplicity, called Seq2Direct encoder ($\text{Enc}_{s2d}$). Geometric constraints could be efficiently imposed on the newly introduced direction space. A Direct2Seq decoder ($\text{Dec}_{d2s}$) with mathematical guarantees is also introduced to develop a \textbf{SDS} ($\text{Enc}_{s2d}$+$\text{Dec}_{d2s}$) model. We apply the SDS model as the denoising neural network during the conditional diffusion process, resulting in a constrained generative model--\textbf{DiffSDS}. Extensive experiments show that the plug-and-play ADS could transform the language model into a strong structural model without loss of simplicity. More importantly, the proposed DiffSDS outperforms previous strong baselines by a large margin on the task of protein inpainting.
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。
