Towards A Generative Protein Evolution Machine with DPLM-Evo

TL;DR

DPLM-Evo is a novel discrete diffusion model for proteins that explicitly predicts biological mutations, enabling more realistic evolution simulation, guided generation, and improved mutation effect prediction.

Contribution

It introduces DPLM-Evo, a diffusion framework that models substitutions and indels explicitly, improving biological plausibility and flexibility in protein sequence generation and editing.

Findings

Achieves state-of-the-art mutation effect prediction on ProteinGym.

Enables variable-length simulated evolution and post-editing of proteins.

Improves sequence understanding through explicit mutation modeling.

Abstract

Proteins are shaped by gradual evolution under biophysical and functional constraints. Protein language models learn rich evolutionary constraints from large-scale sequences, and discrete diffusion-based protein language models~(\eg, DPLMs) are promising for both understanding and generation. However, existing DPLMs typically rely on masking-based absorbing diffusion that contradicts a simple biological intuition: proteins evolve through accumulated edits, not by emerging from masks. Consequently, these frameworks lack explicit pretraining objectives for substitution and insertion/deletion (indel) operations, limiting both optimization-style post-editing and flexible guided generation. To address these limitations, we present DPLM-Evo, an evolutionary discrete diffusion framework that explicitly predicts substitution, insertion, and deletion operations during denoising. DPLM-Evo decouples an upsampled-length latent alignment space from the variable-length observed sequence space, which makes indel-aware generation tractable and enables adaptive scaffold growth throughout the process with negligible computational overhead. To better align substitutions with real evolution, we further introduce a contextualized evolutionary noising kernel that produces biologically informed, context-dependent mutation patterns. Across tasks, DPLM-Evo improves sequence understanding and achieves state-of-the-art mutation effect prediction performance on ProteinGym in the single-sequence setting. It also enables variable-length simulated evolution, and post-editing/optimization of existing proteins via explicit edit trajectories.