Retrosynthesis, the strategy of devising laboratory pathways by working backwards from the target compound, is crucial yet challenging. Enhancing retrosynthetic efficiency requires overcoming the vast complexity of chemical space, the limited known interconversions between molecules, and the challenges posed by limited experimental datasets. This study introduces generative machine learning methods for retrosynthetic planning. The approach features three innovations: generating reaction templates instead of reactants or synthons to create novel chemical transformations, allowing user selection of specific bonds to change for human-influenced synthesis, and employing a conditional kernel-elastic autoencoder (CKAE) to measure the similarity between generated and known reactions for chemical viability insights. These features form a coherent retrosynthetic framework, validated experimentally by designing a 3-step synthetic pathway for a challenging small molecule, demonstrating a significant improvement over previous 5-9 step approaches. This work highlights the utility and robustness of generative machine learning in addressing complex challenges in chemical synthesis.
While hundreds of thousands of new chemical reactions are reported annually, efficient use of this vast collection of synthetic knowledge remains a persistent challenge in modern chemistry. Recent applications of large language models (LLMs) have shown promise, but systems that reliably work for de novo compounds and molecular transformations have remained elusive. Here we introduce MOSAIC (Multiple Optimized Specialists for AI-Driven Chemical Prediction), a computational framework that enables chemists to harness the collective knowledge of millions of reaction protocols. In contrast to existing approaches relying on agentic models, MOSAIC leverages the open-source Llama3.1-8B-instruct architecture. By training 2,489 specialized chemical experts on Voronoi-clustered reaction spaces, we establish a scalable paradigm that delivers reproducible and human-readable experimental protocols for complex syntheses. Experimental validation demonstrates MOSAIC's ability to predict and execute previously unreported transformations, including challenging reactions via Buchwald-Hartwig amination, Suzuki coupling, and olefin metathesis. We validate this approach through the successful synthesis of over 35 novel compounds spanning pharmaceuticals, materials, agrochemicals, and cosmetics. This framework establishes a new relationship between computational and experimental chemistry, providing a foundation for accelerated chemical discovery across disciplines.
13 October 2025 in The Journal of Organic Chemistry
The identification of catalysts that promote chemical reactions is a critical challenge in the production of pharmaceuticals. One of the main bottlenecks in this process is the synthesis of vast libraries of precatalysts, although assessing catalyst effectiveness can be rapidly conducted through high-throughput experimentation. The rational design and development of high-performing precatalysts can circumvent this challenge and lead to important advances. In this study, we apply the transformer-based Kernel-Elastic Autoencoder (KAE) equipped with a conditioned latent space, enabling the targeted generation of ligands with desired steric and electronic properties. Our KAE model has facilitated the identification of a monodentate alkynylphosphine, dubbed MachinePhos A, as an effective precatalyst for forming carbon-carbon bond. Its utility was demonstrated experimentally in the Mizoroki-Heck reaction, using a variety of nitrogen-rich arenes pertinent to pharmaceutical applications.