PeptSol: A Translational Benchmark for Protected-Peptide Solubility in Drug Manufacturing

Liquid-phase peptide synthesis (LPPS) offers a scalable route to peptide manufacturing, but route development still depends on empirical solvent screens because each protected intermediate must be soluble for reaction and recoverable for purification. The protecting groups, terminal modifications, and noncanonical residues that govern this behaviour are poorly represented in existing peptide property benchmarks, limiting the ability to develop and rigorously evaluate molecular representation models for LPPS-relevant prediction tasks. We introduce PeptSol, an open benchmark of 1,388 hand-curated protected-peptide solubility measurements with chemistry-aware splits and strong fingerprint baselines. Across seven frozen molecular encoders, the best model reaches macro-F1 0.843 on binary solubility prediction, but no foundation model consistently outperforms a baseline combining chemical fingerprints with explicit molecular descriptors, and model rankings vary across prediction tasks and data splits. The released dataset, reproducible evaluation protocol, and diverse baseline study establish a standardized benchmark for measuring progress on molecular representations for synthesis-aware peptide developability.