用多目标引导扩散模型生成高效安全的治疗肽
PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion
- 基于掩码离散语言模型，设计新型键依赖掩码策略保证结构有效性
- 通过蒙特卡洛树引导算法，同时优化结合力、通透性等五项关键性质
- 适合药物研发人员快速生成多样化、可化学修饰的候选治疗肽
我们提出PepTune，一种基于掩码离散语言模型（MDLM）框架的多目标离散扩散模型，用于同步生成与优化治疗肽的SMILES。通过创新的键依赖掩码策略和无效损失函数，确保生成结构的有效性。为引导扩散过程，引入蒙特卡洛树引导（MCTG）算法，在推理阶段平衡探索与利用，迭代优化帕累托最优序列。MCTG结合分类器奖励与搜索树扩展，克服梯度估计难题与数据稀疏问题。实验生成了多种化学修饰的肽，同时优化了靶标结合亲和力、膜通透性、溶解度、溶血性和非黏附性等多项治疗特性，适用于多种疾病相关靶点。结果表明，该方法在离散状态空间中实现高效多目标序列设计，具有强大且模块化的优势。
原文摘要 · Abstract (English)
We present PepTune, a multi-objective discrete diffusion model for simultaneous generation and optimization of therapeutic peptide SMILES. Built on the Masked Discrete Language Model (MDLM) framework, PepTune ensures valid peptide structures with a novel bond-dependent masking schedule and invalid loss function. To guide the diffusion process, we introduce Monte Carlo Tree Guidance (MCTG), an inference-time multi-objective guidance algorithm that balances exploration and exploitation to iteratively refine Pareto-optimal sequences. MCTG integrates classifier-based rewards with search-tree expansion, overcoming gradient estimation challenges and data sparsity. Using PepTune, we generate diverse, chemically-modified peptides simultaneously optimized for multiple therapeutic properties, including target binding affinity, membrane permeability, solubility, hemolysis, and non-fouling for various disease-relevant targets. In total, our results demonstrate that MCTG for masked discrete diffusion is a powerful and modular approach for multi-objective sequence design in discrete state spaces.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。