Track genomics, neuroscience and molecular biology.
Search papers, labs, and topics across Lattice.
StabilityArc decodes frozen ESM-600M residue embeddings into a generalizable protein stability landscape by mapping them through a shared RoPE transformer to predict substitution effects, incorporating a contact-aware residual for epistasis. This approach enables cross-protein transfer for prescreening mutations, achieving a 0.7134 Spearman correlation on unseen proteins and outperforming strong zero-shot baselines. When used as a prior for a supervised model, it further boosts predictive accuracy to 0.8280.
A single, frozen protein language model decoder can predict mutation effects across diverse protein families, unlocking generalizable stability landscapes without protein-specific fine-tuning.
Every protein has a unique stability landscape, but the physical consequences of mutation are governed by recurring biochemical constraints. We test whether a shared decoder, trained on measurements from diverse proteins, can interpret these constraints in an unseen target, enabling cross-protein transfer for initial experimental round prescreening. We present StabilityArc , which maps frozen ESMC-600M residue representations through a shared RoPE transformer to an Lx20 matrix of substitution effects; a symmetric, contact-aware residual aids in predicting epistasis in simultaneous substitutions. In 66 strict leave-one-protein-out evaluations covering 134,794 ProteinGym variants, StabilityArc achieves 0.7134 Spearman correlation, exceeding the strongest zero-shot baseline, ProSST-2048 (0.6526), by 0.0608. We further explore the utility of this method by providing the score as a prior for Kermut, achieving Spearman correlation of 0.8280 across three supervised split schemes, improving on Kermut's reported 0.8167.