RipplePLM: Structural and Property Decoupling for Protein Mutation Effect Generation

Protein mutation effect generation asks a model to describe the functional consequence of a point mutation in natural language. Existing protein-to-text systems typically encode mutation information into undifferentiated representations, overlooking the organization of mutation-induced evidence across structural and biochemical factors. We propose RipplePLM, a mutation-aware generation framework centered on Direct-Distal Cross-Attention (DDCA). By constructing a residue-level Mutation Perturbation Field from pre-trained protein language models, DDCA leverages predicted contact maps to explicitly decouple structural perturbations into two pathways: the mutation site's immediate contact neighborhood and its multi-hop distal context. To complement this structural decomposition, we further introduce the Property Latent Chain (PLChain), which injects expert-guided biochemical supervision (e.g., thermostability and optimal pH) into the LLM hidden-state pathway through latent property tokens. On MutaDescribe, RipplePLM improves over mutation-specific baselines on temporal and structural splits; under a matched-backbone comparison, average structural-split ROUGE-L increases from $\textit{22.23}$ to $\textit{35.65}$. Additional ablations, representation diagnostics, and low-$N$ fitness regression experiments further support the effectiveness of the learned mutation-aware representations.