---
title: "MP2D: Constrained Monte Carlo Tree-Guided Diffusion for Multi-Objective Protein Sequence Design"
authors:
  - "Zitai Kong"
  - "Yifan Dong"
  - "Yixuan Wu"
  - "Zhaokang Liang"
  - "Jian Wu"
  - "Hongxia Xu"
doi: "10.24963/ijcai.2026/617"
url: "https://ijcai.org/proceedings/2026/617"
pdf: "https://ijcai.org/proceedings/2026/0617.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "5540-5548"
track: "Main Track"
keywords:
  - "Multidisciplinary Topics and Applications: Bioinformatics"
  - "Multidisciplinary Topics and Applications: Life sciences"
---

# MP2D: Constrained Monte Carlo Tree-Guided Diffusion for Multi-Objective Protein Sequence Design

Zitai Kong, Yifan Dong, Yixuan Wu, Zhaokang Liang, Jian Wu, Hongxia Xu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 5540-5548. DOI: [10.24963/ijcai.2026/617](https://doi.org/10.24963/ijcai.2026/617)

## Abstract

Designing functional protein sequences that satisfy multiple desired properties is a core research focus of protein engineering. Prior methods struggle with inability or inefficiency when dealing with numerous, often conflicting, properties. We propose Multi-Property Protein Diffusion, (MP2D), a unified framework for multi-objective protein sequence optimization that integrates conditional discrete diffusion with constrained MCTS and global iterative refinement. MP2D formulates diffusion denoising as a constrained sequential decision-making process and employs MCTS to explore diverse denoising trajectories guided by Pareto-based rewards. A global iterative refinement strategy further enables repeated remasking and re-optimization of candidate sequences, while a dynamic Pareto constraint prevents candidate bloat and maintains balanced trade-offs across objectives. We evaluate MP2D on two challenging multi-objective protein design tasks: antimicrobial peptide and protein binder optimization, involving four to five conflicting properties. Experimental results demonstrate that MP2D consistently outperforms existing multi-objective baselines, achieving robust and balanced improvements across all objectives without retraining generative models. These results highlight MP2D as a practical and scalable solution for multi-objective functional protein design.