2026/01/01 by Yves Grandjean, David Kreutter, Jean-Louis Reymond · 1 voice
Computer Science · Engineering · Materials Science · #Computational Drug Discovery Methods #Machine Learning in Materials Science #SAS software applications and methods
paper · pdf · doi:10.1039/d5dd00465a
openalex publication_date 2026/01/01 · openalex created_date 2026/01/22 · openalex updated_date 2026/07/15
Reactions in the US Patent Office (USPTO) are biased towards a few over-represented reaction types, which potentially limits their usefulness for computer-assisted synthesis planning (CASP). To obtain an equilibrated dataset, we applied retrosynthesis templates to USPTO molecules as products (P) to generate starting materials (SM). We then used transformer T2 from our recently reported triple transformer loop (TTL) retrosynthesis model to predict reagents (R) for the SM → P reaction. Finally, we validated the prediction by requesting a high confidence prediction (>95%) for the prediction of P from SM + R by TTL transformer T3. We generated up to 5000 reactions per template, resulting in 27.5m validated fictive reactions covering the chemical space of the original USPTO dataset. To exemplify the use of this dataset, we demonstrate that a single-step retrosynthesis transformer model trained on a template equilibrated subset of 1 097 374 fictive reactions outperforms the corresponding model trained on USPTO reactions only.