Additive baselines furnish no evidence for epistasis learning by MULTI-evolve (opens in new tab)

Recent work from Tran et al. (Science, 2026) introduced MULTI-evolve, a framework for protein engineering that combines single-mutant nomination via a protein language model (PLM) or a deep mutational scan (DMS), experimental single- and double-mutant characterization, and neural networks to engineer hyperactive multimutant proteins. The authors attribute the framework's performance to "epistasis-aware modeling" and claim that their neural networks "learn the epistatic landscape" and "identif...