Recent advances in protein structure prediction, such as AlphaFold, have demonstrated the power of deep neural architectures like the Evoformer for capturing complex spatial and evolutionary constraints on protein conformation. However, the depth of the Evoformer, comprising 48 stacked blocks, introduces high computational costs and rigid layerwise discretization. Inspired by Neural Ordinary Differential Equations (Neural ODEs), we propose a continuous-depth formulation of the Evoformer, replacing its 48 discrete blocks with a Neural ODE parameterization that preserves its core attention-based operations. This continuous-time Evoformer achieves constant memory cost (in depth) via the adjoint method, while allowing a principled trade-off between runtime and accuracy through adaptive ODE solvers. Benchmarking on protein structure prediction tasks, we find that the Neural ODE-based Evoformer produces structurally plausible predictions and reliably captures certain secondary structure elements, such as alpha-helices, though it does not fully replicate the accuracy of the original architecture. However, our model achieves this performance using dramatically fewer resources, just 17.5 hours of training on a single GPU, highlighting the promise of continuous-depth models as a lightweight and interpretable alternative for biomolecular modeling. This work opens new directions for efficient and adaptive protein structure prediction frameworks.

翻译：近年来，蛋白质结构预测领域取得了显著进展，例如AlphaFold等模型，它们展示了如Evoformer等深度神经架构在捕捉蛋白质构象的复杂空间与进化约束方面的强大能力。然而，Evoformer的深度——包含48个堆叠模块——带来了高昂的计算成本与严格的逐层离散化处理。受神经常微分方程（Neural ODEs）的启发，我们提出了一种Evoformer的连续深度形式，将其48个离散模块替换为神经常微分方程参数化，同时保留了其核心的基于注意力的操作。这一连续时间Evoformer通过伴随方法实现了恒定的内存成本（在深度上），并允许通过自适应常微分方程求解器在运行时间与精度之间进行有原则的权衡。在蛋白质结构预测任务上的基准测试表明，基于神经常微分方程的Evoformer能够生成结构合理的预测，并可靠地捕捉某些二级结构元素（如α-螺旋），尽管其未能完全复现原始架构的精度。然而，我们的模型以显著更少的资源实现了这一性能——仅需在单个GPU上训练17.5小时，这凸显了连续深度模型作为生物分子建模的轻量级且可解释替代方案的潜力。此项工作为高效且自适应的蛋白质结构预测框架开辟了新的方向。