# An All-Atom Generative Model for Designing Protein Complexes

Source: [An All-Atom Generative Model for Designing Protein Complexes](<https://www.sota2.com/research/paper/68fa7b201e209131cea86b7b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:33:44.062Z

Authors: Ruizhe Chen, Dongyu Xue, Xiangxin Zhou, Zaixiang Zheng, Xiangxiang Zeng, Quanquan Gu

Published: 2025-04-17T16:37:41.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Protein Binder Design on Protein targets 40-250 residues](<https://www.sota2.com/research/sota/protein-binder-design-on-protein-targets-40-250-residues.md>): Protein binder design; Protein targets 40-250 residues; Unique Successes: 3.15.

- [Unconditional all-atom protein structure generation on AFDB Foldseek cluster representatives lengths 100-500 (test)](<https://www.sota2.com/research/sota/unconditional-all-atom-protein-structure-generation-on-afdb-foldseek-cluster-representatives-lengths-100-500-test.md>): Unconditional all-atom protein structure generation; AFDB Foldseek cluster representatives lengths 100-500 unconditional generation (test); Co-designability (All-atom): 19.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2504.13075>)

[PDF](<https://arxiv.org/pdf/2504.13075.pdf>)
