Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling
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.
Related
- Convergence is not correctness: context-dependent performance of enhanced-sampling methods across biological complexity
- Spatially explicit sampling of AM fungal biomass reveals links to community characteristics and landscape context
- Development of A Modeling Framework for Characterizing Protein–Polymer Bioconjugates with Enhanced Sampling Molecular Dynamics Simulations
- RiboBridge: protein-conditioned de novo RNA binder structure design
- Agent-guided epitope excision enables economical de novo binder design
BibTeX
@misc{cao2026chamaileon,
title = {{Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling}},
author = {Hengyuan Cao and Shizhuo Cheng and Mingxuan Liu and Weicheng Huang and Yunhong Lu and Chenxi Cai and Yan Zhang and Min Zhang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2607.23518},
eprint = {2607.23518},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.23518},
}
RIS
TY - UNPB
TI - Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling
AU - Hengyuan Cao
AU - Shizhuo Cheng
AU - Mingxuan Liu
AU - Weicheng Huang
AU - Yunhong Lu
AU - Chenxi Cai
AU - Yan Zhang
AU - Min Zhang
PY - 2026
DA - 2026/09/13
PB - arXiv
DO - 10.48550/arxiv.2607.23518
UR - https://arxiv.org/abs/2607.23518
AB - 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.
ER -