论文标题
物理感知的图形神经网络，用于精确RNA 3D结构预测
Physics-aware Graph Neural Network for Accurate RNA 3D Structure Prediction
论文作者
论文摘要
RNA的生物学功能取决于其三维（3D）结构。因此，鉴于实验确定的RNA结构数量有限，RNA结构的预测将有助于阐明RNA功能和靶向RNA的药物发现，但仍然是一个具有挑战性的任务。在这项工作中，我们提出了一个基于图形神经网络（GNN）的评分函数，仅在有限的溶液RNA 3D结构上使用原子类型和坐标进行训练，以区分准确的结构模型。提出的物理学多重多重图神经网络（PAXNET）分别模拟了受分子力学启发的局部和非本地相互作用。此外，PaxNet包含一个基于注意力的融合模块，该模块了解每种相互作用类型对最终预测的个人贡献。我们严格评估PaxNet在两个基准测试上的性能，并将其与几个最先进的基线进行比较。结果表明，PaxNet的总体上明显胜过所有基准，并证明了PaxNet在改善RNA和其他大分子的3D结构建模方面的潜力。我们的代码可从https://github.com/zetayue/physics-aware-multiplex-gnn获得。
Biological functions of RNAs are determined by their three-dimensional (3D) structures. Thus, given the limited number of experimentally determined RNA structures, the prediction of RNA structures will facilitate elucidating RNA functions and RNA-targeted drug discovery, but remains a challenging task. In this work, we propose a Graph Neural Network (GNN)-based scoring function trained only with the atomic types and coordinates on limited solved RNA 3D structures for distinguishing accurate structural models. The proposed Physics-aware Multiplex Graph Neural Network (PaxNet) separately models the local and non-local interactions inspired by molecular mechanics. Furthermore, PaxNet contains an attention-based fusion module that learns the individual contribution of each interaction type for the final prediction. We rigorously evaluate the performance of PaxNet on two benchmarks and compare it with several state-of-the-art baselines. The results show that PaxNet significantly outperforms all the baselines overall, and demonstrate the potential of PaxNet for improving the 3D structure modeling of RNA and other macromolecules. Our code is available at https://github.com/zetayue/Physics-aware-Multiplex-GNN.
