Scalable Multimer Structure Prediction using Diffusion Models

Accurate protein complex structure modeling is a necessary step in understanding the behavior of biological pathways and cellular systems. While some works have attempted to address this challenge, there is still a need for scaling existing methods to larger protein complexes. To address this need, we propose a novel diffusion generative model (DGM) that predicts large multimeric protein structures by learning to rigidly dock its chains together. Additionally, we construct a new dataset specifically for large protein complexes used to train and evaluate our DGM. We substantially improve prediction runtime and completion rates while maintaining competitive accuracy with current methods.