Multiobjective learning and design of bacteriophage specificity

Proteins are often optimized for single functions during design and engineering without the consideration of other functionalities that may interfere with the intended outcome. Here, we apply deep learning to understand and design the multifunctional host-targeting landscape of the T7 bacteriophage receptor-binding protein for enhanced infectivity, predefined specificity, and high generality toward unseen strains. We compare four model architectures and experimentally characterize engineered phages optimized for 26 tasks. With multiobjective machine learning, it is possible to engineer complex specificities at success rates that enable low-throughput validation of predicted hits. The targeting capabilities of T7 are highly plastic, with opposite specificities occasionally separated by only a few mutations. This tunability underscores how models trained on multifunctional data can uncover key principles of phage biology and specificity. The same framework can guide multiobjective optimization of other proteins or biological systems, offering a general strategy for modeling multifunctional landscapes.