Although artificial neural networks are powerful classifiers, their internal structures are hard to interpret. In the life sciences, extensive knowledge of cell biology provides an opportunity to design visible neural networks (VNNs) that couple the model's inner workings to those of real systems. Here we develop DCell, a VNN embedded in the hierarchical structure of 2,526 subsystems comprising a eukaryotic cell (http://d-cell.ucsd.edu/). Trained on several million genotypes, DCell simulates cellular growth nearly as accurately as laboratory observations. During simulation, genotypes induce patterns of subsystem activities, enabling in silico investigations of the molecular mechanisms underlying genotype–phenotype associations. These mechanisms can be validated, and many are unexpected; some are governed by Boolean logic. Cumulatively, 80% of the importance for growth prediction is captured by 484 subsystems (21%), reflecting the emergence of a complex phenotype. DCell provides a foundation for decoding the genetics of disease, drug resistance and synthetic life.

尽管人工神经网络是强大的分类器，但其内部结构却难以解释。在生命科学中，对细胞生物学的广泛了解为设计可见神经网络（VNN）提供了机会，这些神经网络将模型的内部工作机制与实际系统的内部工作机制耦合在一起。在这里，我们开发了DCell，这是一种VNN，嵌入在包含真核细胞的2,526个子系统的分层结构中（http://d-cell.ucsd.edu/）。经过培训的数百万种基因型，DCell可以模拟细胞生长，几乎与实验室观察结果一样准确。在模拟过程中，基因型会诱导子系统活动的模式，从而实现计算机模拟基因型-表型关联的分子机制研究。这些机制可以验证，许多机制是出乎意料的。有些受布尔逻辑控制。总计484个子系统（21％）捕获了80％的增长预测重要性，反映了复杂表型的出现。DCell为解码疾病，耐药性和合成生命的遗传学提供了基础。