Proteins are used in various biotechnological applications, often requiring the optimization of protein properties by introducing specific amino‐acid exchanges. Deep mutational scanning (DMS) is an effective high‐throughput method for evaluating the effects of these exchanges on protein function. DMS data can then inform the training of a neural network to predict the impact of mutations. Most approaches use some representation of the protein sequence for training and prediction. As proteins are characterized by complex structures and intricate residue interaction networks, directly providing structural information as input reduces the need to learn these features from the data. We introduce a method for encoding protein structures as stacked 2D contact maps, which capture residue interactions, their evolutionary conservation, and mutation‐induced interaction changes. Furthermore, we explored techniques to augment neural network training performance on smaller DMS datasets. To validate our approach, we trained three neural network architectures originally used for image analysis on three DMS datasets, and we compared their performances with networks trained solely on protein sequences. The results confirm the effectiveness of the protein structure encoding in machine learning efforts on DMS data. Using structural representations as direct input to the networks, along with data augmentation and pretraining, significantly reduced demands on training data size and improved prediction performance, especially on smaller datasets, while performance on large datasets was on par with state‐of‐the‐art sequence convolutional neural networks. The methods presented here have the potential to provide the same workflow as DMS without the experimental and financial burden of testing thousands of mutants. Additionally, we present an open‐source, user‐friendly software tool to make these data analysis techniques accessible, particularly to biotechnology and protein engineering researchers who wish to apply them to their mutagenesis data.

中文翻译：

---

压平曲线——如何利用小型深度突变扫描数据集获得更好的结果

蛋白质用于各种生物技术应用，通常需要通过引入特定的氨基酸交换来优化蛋白质特性。深度突变扫描（DMS）是一种有效的高通量方法，用于评估这些交换对蛋白质功能的影响。然后，DMS 数据可以为神经网络的训练提供信息，以预测突变的影响。大多数方法使用蛋白质序列的某种表示来进行训练和预测。由于蛋白质的特点是复杂的结构和复杂的残基相互作用网络，直接提供结构信息作为输入可以减少从数据中学习这些特征的需要。我们引入了一种将蛋白质结构编码为堆叠二维接触图的方法，该方法捕获残基相互作用、它们的进化保守性和突变诱导的相互作用变化。此外，我们还探索了增强神经网络在较小 DMS 数据集上训练性能的技术。为了验证我们的方法，我们在三个 DMS 数据集上训练了最初用于图像分析的三个神经网络架构，并将它们的性能与仅在蛋白质序列上训练的网络进行了比较。结果证实了 DMS 数据机器学习中蛋白质结构编码的有效性。使用结构表示作为网络的直接输入，以及数据增强和预训练，显着降低了对训练数据大小的需求并提高了预测性能，特别是在较小的数据集上，而在大型数据集上的性能与最先进的技术相当序列卷积神经网络。这里介绍的方法有可能提供与 DMS 相同的工作流程，而无需测试数千个突变体的实验和财务负担。此外，我们还提供了一个开源、用户友好的软件工具，使这些数据分析技术变得可用，特别是对于希望将其应用于突变数据的生物技术和蛋白质工程研究人员。