An All-Atom Generative Model for Designing Protein Complexes

Proteins typically exist in complexes, interacting with other proteins or biomolecules to perform their specific biological roles. Research on single-chain protein modeling has been extensively and deeply explored, with advancements seen in models like the series of ESM and AlphaFold2. Despite these developments, the study and modeling of multi-chain proteins remain largely uncharted, though they are vital for understanding biological functions. Recognizing the importance of these interactions, we introduce APM (all-Atom Protein generative Model), a model specifically designed for modeling multi-chain proteins. By integrating atom-level information and leveraging data on multi-chain proteins, APM is capable of precisely modeling inter-chain interactions and designing protein complexes with binding capabilities from scratch. It also performs folding and inverse-folding tasks for multi-chain proteins. Moreover, APM demonstrates versatility in downstream applications: it achieves enhanced performance through supervised fine-tuning (SFT) while also supporting zero-shot sampling in certain tasks, achieving state-of-the-art results. We released our code at https://github.com/bytedance/apm.

Proteins often work in groups called complexes to perform certain biological tasks. While we understand single proteins well, how these complexes form and function is less clear but equally important.We introduce APM, an AI that designs these multi-protein complexes with atomic precision. Unlike older methods focusing on single proteins or simpler views, APM models the detailed atomic interactions between protein chains.APM can create novel complexes, predict their formation, and design sequences for desired structures. It has shown superior performance in tasks like antibody and therapeutic peptide design. This work offers new avenues for creating custom protein complexes for medicine and biotech