English

Towards A Generative Protein Evolution Machine with DPLM-Evo

Machine Learning 2026-05-14 v2

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.

Keywords

Cite

@article{arxiv.2605.00182,
  title  = {Towards A Generative Protein Evolution Machine with DPLM-Evo},
  author = {Xinyou Wang and Liang Hong and Jiasheng Ye and Zaixiang Zheng and Yu Li and Shujian Huang and Quanquan Gu},
  journal= {arXiv preprint arXiv:2605.00182},
  year   = {2026}
}

Comments

A peer-reviewed version was accepted to ICML 2026

R2 v1 2026-07-01T12:44:27.468Z