Controllable generation of non-hemolytic antimicrobial peptides by multi-guided latent diffusion

Antimicrobial peptides (AMPs) are attractive anti-infective scaffolds, but their development is often constrained by hemolysis and by the narrow physicochemical separation between bacterial killing and host-cell damage. We developed NHAMP, a protein language model (PLM)-fused latent diffusion framework for generating peptides under explicit efficacy-safety constraints. NHAMP maps sequences into ESM-2 embeddings, denoises them with a conditional diffusion model that reuses PLM attention blocks, and decodes latent states with a noise-adapted masked-language-model head. During sampling, classifier-free guidance from antimicrobial, non-hemolytic and dual-property conditions is accumulated at each denoising step, allowing the model to search more directly for the overlap between activity and safety rather than maximise one property and filter later. Under a shared in silico evaluation pipeline, NHAMP maintained a high predicted AMP-positive rate (83.8%) while increasing the predicted non-hemolytic fraction to 71.4%, and ablation showed that combining all three guidance branches produced the strongest dual-objective yield among the tested settings ACCdual = 64.7%). Composition, physicochemical and embedding-space analyses showed a consistent shift toward more cationic, less hydrophobic and less aggregation-prone peptides. Overall, the results support the idea that introducing safety during denoising, rather than only after generation, can improve the practical yield of AMP libraries for downstream experimental prioritisation.