An AI lab partner for chemical synthesis

RXN for Chemistry

An AI lab partner for chemical synthesis

Predict reactions, find retrosynthesis pathways, and derive experimental procedures with RXN for Chemistry.
Interface screenshotInterface screenshot

New ideas for retrosynthesis

RXN uses AI trained on millions of chemical reaction records to suggest optimal synthesis routes, dramatically reducing manual effort, saving time and cost.

Plan retrosynthesis routes

Upload molecules to determine reactions and ingredients

Predict chemical reactions
Generate experimental procedures

The first language model for chemistry

RXN is based on molecular transformer models that understand the natural language of chemistry, trained on over 3 million chemical reactions. Scientists can upload molecules to the cloud to determine reactions and ingredients. Results are accurate and fast, at a rate of ~7ms/reaction. Huge data sets containing millions of reactions can be mapped within a few hours.

Inferring experimental procedures from text-based representations of chemical reactionsA. C. Vaucher, P.Schwaller, J. Geluykens, V. H. Nair, A. Iuliano, T. Laino. Nat.Commun. 2021, 12, 2573
"Found in Translation": predicting outcomes of complexorganic chemistry reactions using neural sequence-to-sequence models.P. Schwaller, T. Gaudin, D Lanyi, C. Bekas,T. Laino. Chem. Sci., 2018, 9, 6091-6098
Predicting retrosynthetic pathways using a combined linguistic model and hyper-graph exploration strategy.P. Schwaller, R. Petraglia, V. Zullo, V. H. Nair, R. A. Haeuselmann, R. Pisoni, C. Bekas, A. Iuliano, T. Laino. Chem. Sci., 2020,11, 3316-3325
Unassisted Noise-Reduction of Chemical Reactions Data Sets.A. C. Vaucher, P. Schwaller, J. Geluykens, V. H. Nair, A.Iuliano, T. Laino. ChemRxiv preprint, 2020
Automated extraction of chemical synthesis actions from experimental procedures.A. C. Vaucher, P. Schwaller, J.Geluykens, V. H. Nair, A. Iuliano, T. Laino. Nat. Commun.2020, 11, 3601

Lab-ready features


Work with text-based or drawn representations of molecules and reactions as inputs

Lab integration

Convert chemical recipes to machine-readable instructions for use on autonomous lab hardware


Built-in model tuning, with domain-specific models ready in minutes

Data catalog

Third-party data sources made available to tune models on specific chemistry domains

Try RXN now, for free

Start accelerating your chemical synthesis today, risk-free, with RXN for Chemistry.

RXN for enterprise

RXN for Chemistry is most powerful when used by your entire team. Request a meeting to learn more.