Tomasz Badowski

TL;DR: Results indicate that expert-level automated synthetic planning is feasible, pending continued improvements to the reaction knowledge base and further code optimization, and a synthetic route-planning algorithm, augmented with causal relationships that allow it to strategize over multiple steps, can design complex natural-product syntheses that are indistinguishable from those designed by human experts.

TL;DR: Machine learning can predict the major regio-, site-, and diastereoselective outcomes of Diels-Alder reactions better than standard quantum-mechanical methods and with accuracies exceeding 90 % provided that the diene/dienophile substrates are represented by "physical-organic" descriptors reflecting the electronic and steric characteristics of their substituents.

TL;DR: The optimal control approach described in detail resembles the use of Jarzynski's equality for free energy calculations, but with an optimized protocol that speeds up the sampling, while (theoretically) giving variance-free estimators of the rare events statistics.

TL;DR: This paper shows that expert and ML approaches can be synergistic-specifically, when NNs are trained on literature data matched onto high-quality, expert-coded reaction rules, they achieve higher synthetic accuracy than either of the methods alone and, importantly, can also handle rare/specialized reaction types.

TL;DR: A family of network algorithms allows the Chematica retrosynthetic platform to plan both cost-effective and chemically diverse syntheses.