Guiding large language models to predict edit sequences for molecular synthesizability optimization

Abstract

Generative artificial intelligence has revolutionized the exploration of chemical space, yet a critical bottleneck remains that a substantial fraction of generated molecules is synthetically inaccessible. Current solutions, such as post hoc filtering or projection-based methods, often compromise structural novelty or disrupt key pharmacophores by forcing molecules into predefined synthetic templates. Here we introduce SynCraft, a reasoning-based framework that reframes synthesizability optimization not as a sequence translation task but as a precise structural editing problem. Leveraging the emergent reasoning capabilities of large language models, SynCraft navigates the ‘synthesis cliff’ where minimal structural modifications yield substantial gains in synthetic feasibility. By predicting executable sequences of atom-level edits rather than generating SMILES strings directly, SynCraft circumvents the syntactic fragility of LLMs while harnessing their chemical intuition. Extensive benchmarks demonstrate that SynCraft outperforms state-of-the-art baselines in generating synthesizable analogues with high structural fidelity, with comparable performance across both proprietary and open-weight backends. Furthermore, through interaction-aware prompting, SynCraft successfully replicates expert medicinal chemistry intuition in editing PLK1 inhibitors and rescuing high-scoring RIPK1 candidates previously discarded in the molecular generation literature. For application convenience, we package the framework as an agent skill and demonstrate an end-to-end rescue workflow on candidate molecules generated for the SARS-CoV-2 main protease as an example. Computational drug design often generates molecules that cannot be synthesized. Li and Lai show how large language models can predict precise structural edits to fix these molecules, outperforming traditional methods and preserving key features.