PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion
This work addresses the challenge of designing therapeutic peptides with multiple optimized properties for drug discovery applications, representing a novel method rather than an incremental improvement.
The authors tackled the problem of generating therapeutic peptides optimized for multiple properties by introducing PepTune, a multi-objective discrete diffusion model with Monte Carlo Tree Guidance, which produced diverse, chemically-modified peptides with improved target binding affinity, membrane permeability, solubility, hemolysis, and non-fouling for disease-relevant targets.
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.