EvalRetro: Unifying the evaluation of machine learning frameworks to enhance understanding and transparency for retrosynthesis.
Synthesis planning relies on retrosynthesis models, yet this relationship is under-analyzed. We investigate the effect of contemporary single-step models trained on public and proprietary reaction data to analyze the synthesis routes produced.
This review outlines several organic chemistry tasks for which predictive machine learning models have been and can be applied.
New curation and atom-mapping routine leading to large database of enzymatic reactions boosts performance of deep learning models.
This work presents a novel strategy for human-guided multistep retrosynthesis via prompting, using a disconnection-aware transformer and multi-objective Monte Carlo Tree Search.