When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs

Recent progress has expanded the use of large language models (LLMs) in drug discovery, including synthesis planning. However, objective evaluation of retrosynthesis performance remains limited. Existing benchmarks and metrics typically rely on published synthetic procedures and Top-K accuracy based on single ground-truth, which does not capture the open-ended nature of real-world synthesis planning. We propose a new benchmarking framework for single-step retrosynthesis that evaluates both general-purpose and chemistry-specialized LLMs using ChemCensor, a novel metric for chemical plausibility. By emphasizing plausibility over exact match, this approach better aligns with human synthesis planning practices. We also introduce CREED, a novel dataset comprising millions of ChemCensor-validated reaction records for LLM training, and use it to train a model that improves over the LLM baselines under this benchmark.

Chemistry42: An AI-based platform for de novo molecular design

Chemistry42 is a software platform for de novo small molecule design that integrates Artificial Intelligence (AI) techniques with computational and medicinal chemistry methods. Chemistry42 is unique in its ability to generate novel molecular structures with predefined properties validated through in vitro and in vivo studies. Chemistry42 is a core component of Insilico Medicine Pharma.ai drug discovery suite that also includes target discovery and multi-omics data analysis (PandaOmics) and clinical trial outcomes predictions (InClinico).