Decoding Interaction Patterns from the Chemical Sequence of Polymers Using Neural Networks

The relation between chemical sequences and the properties of polymers is considered using artificial neural networks with a low-dimensional bottleneck layer of neurons. These encoder–decoder architectures may compress the input information into a meaningful set of physical variables that describe the correlation between distinct types of data. In this work, neural networks were trained to translate a sequence of hydrophilic and hydrophobic segments into the effective free energy landscape of a copolymer interacting with a lipid membrane. The training data were obtained by the sampling of coarse-grained polymer conformations in a given membrane density field. Neural networks that were split into separate channels have learned to decompose the free energy into independent components that are explainable by known concepts from polymer physics. The semantic information in the hidden layers was employed to predict polymer translocation events through a membrane for a more detailed dynamic model via a transfer learning procedure. The search for minimal translocation times in the compressed chemical space underlined that nontrivial sequence motifs may lead to optimal properties.

本研究采用带有低维神经元瓶颈层的人工神经网络，探讨化学序列与聚合物性能之间的关联。这类编码器-解码器（encoder–decoder）架构可将输入信息压缩为一组具备物理意义的变量，用以刻画不同类型数据间的相关性。本工作中，我们训练神经网络将亲水与疏水片段序列转换为与脂质膜相互作用的共聚物的有效自由能景观。训练数据通过在给定膜密度场中对粗粒度聚合物构象进行采样得到。拆分为独立通道的神经网络已学会将自由能分解为独立组分，这些组分可通过高分子物理学的已知概念予以解释。借助隐藏层中的语义信息，我们通过迁移学习（transfer learning）流程，针对更精细的动态模型预测了聚合物跨膜易位（polymer translocation）事件。在压缩后的化学空间中搜寻最短易位时间的研究表明，非平凡的序列基序（sequence motif）可带来最优性能。