Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling

2026-07-26

AI Summary

Current approaches to protein binder design are largely constrained by assumptions of single-target binding and static conformations, limiting their applicability to multifunctional or multi-state scenarios. This work proposes a novel cross-context binder design paradigm that leverages context-aware joint modeling of sequence and structure, integrating an In-Context Complex Co-Design training mechanism with a Mixture-of-Paths Sampling inference strategy to enable end-to-end generation of binders for multiple targets and conformational states. Experiments on the newly introduced CROSS benchmark demonstrate that the method efficiently generates protein sequences compatible with diverse conformational landscapes and multi-target constraints, substantially overcoming the limitations inherent in conventional single-context design frameworks.

Abstract

The rapid evolution of generative models has unlocked new potentials in protein binder design, a pivotal task in structural biology, by facilitating end-to-end generation via joint sequence-structure modeling or hallucination. However, existing approaches are predominantly implemented under a single-target, single-state assumption, limiting their ability to model multi-target or multi-state interactions required for advanced function-oriented protein design. Here, we introduce Chamaileon, which unifies multi-target and multi-state binder design by formulating the problem as cross-context binding landscape modeling. The framework is underpinned by a training paradigm termed In-Context Complex Co-Design (I3CD) for context-aware sequence-structure co-modeling. During inference, we employ Mixture-of-Paths Sampling (MoPS), a scalable strategy that optimizes a single sequence across contexts while alleviating the scarcity of high-quality multi-conformational paired data. Extensive evaluation on our newly constructed benchmark, CROSS, demonstrates that Chamaileon effectively generates sequences adaptable to diverse conformational landscapes and multi-target requirements. The code is available on https://github.com/caohengyuan/Chamaileon.

Problem

• protein binder design
• multi-target
• multi-state
• cross-context binding
• conformational landscape

Innovation

• cross-context binding
• contextualized modeling
• mixed sampling
• multi-state design
• protein binder generation