Scaling SMILES-Based Chemical Language Models for Therapeutic Peptide Engineering

Therapeutic peptides occupy a unique middle ground in drug discovery, offering the high specificity of protein interactions with the chemical diversity of small molecules, yet they currently fall in a computational blind spot. Existing AI tools cannot handle them effectively: protein models are restricted to natural amino acids, while chemical models struggle to process large, polymer-like sequences. This disconnect has forced the field to rely on static chemical descriptors that fail to capture subtle chemical details. To bridge this gap, we present PeptideCLM-2, a chemical language model trained on over 100 million molecules to natively represent complex peptide chemistry. PeptideCLM-2 consistently outperforms both chemical descriptors and specialized AI models on critical drug development tasks, including aggregation, membrane diffusion, and cell targeting. Notably, we find that when model parameters reach the 100 million scale, the transformer architecture is able to learn chemical properties from molecular syntax alone.