CupOFMoCA: Coupled Objective-Guided Discrete Flows for Molecular Conjugate Assembly

Molecular conjugates, including PROTACs and peptide-drug conjugates (PDCs), derive their function from the joint behavior of multiple coupled components, yet most generative approaches design these components independently and combine them only after generation. Such staged pipelines ignore cross-component dependencies and often produce conjugates that are chemically invalid or lose function upon assembly. We introduce $\textbf{C}$o$\textbf{up}$led $\textbf{O}$bjective-Guided Discrete $\textbf{F}$lows for $\textbf{Mo}$lecular $\textbf{C}$onjugate $\textbf{A}$ssembly ($\textbf{CupOFMoCA}$), a discrete generative framework that formulates conjugate design as a constrained, coupled generation problem. CupOFMoCA operates by restricting discrete generative trajectories to a chemically feasible conjugate manifold and biasing local transitions using a target-specific binding predictor, ensuring that peptide, linker, and drug components remain compatible throughout generation. Focusing on PDCs, we show that coupling constraints and objective guidance enable anticipatory design that preserves post-conjugation predicted binding and produces structurally realistic conjugates, outperforming staged baselines that attach drugs to independently generated peptides. These results demonstrate that explicit coupling and constraint enforcement are sufficient to recover functional molecular conjugates and provide a principled foundation for generative modeling in settings where function emerges only at the level of the assembled system.