DPLM: Diffusion Protein Language Model

DPLM-2.1 achieves advanced structural modeling capabilities beyond DPLM-2. The proposed designs enable the 650M multimodal PLM to outperform 3B-scale baselines and specialized structure folding models.

DPLM-2 is a brand-new multimodal protein foundation model that extends Diffusion Protein Language Model to model, understand, generate and reason over both protein structures and sequences.

This paper introduces diffusion protein language model (DPLM), a versatile protein language model that demonstrates strong generative and predictive capabilities for protein sequences.

We present LM-DESIGN, a generic approach to reprogramming sequence-based protein language models (pLMs) to acquire an immediate capability to design preferable protein sequences for given folds.