Combining Bayesian optimization and automation to simultaneously optimize reaction conditions and routes.

Reaching optimal reaction conditions is crucial to achieve high yields, minimal by-products, and environmentally sustainable chemical reactions. With the recent rise of artificial intelligence, there has been a shift from traditional Edisonian trial-and-error optimization to data-driven and automated approaches, which offer significant advantages. Here, we showcase the capabilities of an integrated platform; we conducted simultaneous optimizations of four different terminal alkynes and two reaction routes using an automation platform combined with a Bayesian optimization platform. Remarkably, we achieved a conversion rate of over 80% for all four substrates in 23 experiments, covering ca. 0.2% of the combinatorial space. Further analysis allowed us to identify the influence of different reaction parameters on the reaction outcomes, demonstrating the potential for expedited reaction condition optimization and the prospect of more efficient chemical processes in the future.

Fuelling the Digital Chemistry Revolution with Language Models.

The RXN for Chemistry project, initiated by IBM Research Europe - Zurich in 2017, aimed to develop a series of digital assets using machine learning techniques to promote the use of data-driven methodologies in synthetic organic chemistry. This research adopts an innovative concept by treating chemical reaction data as language records, treating the prediction of a synthetic organic chemistry reaction as a translation task between precursor and product languages. Over the years, the IBM Research team has successfully developed language models for various applications including forward reaction prediction, retrosynthesis, reaction classification, atom-mapping, procedure extraction from text, inference of experimental protocols and its use in programming commercial automation hardware to implement an autonomous chemical laboratory. Furthermore, the project has recently incorporated biochemical data in training models for greener and more sustainable chemical reactions. The remarkable ease of constructing prediction models and continually enhancing them through data augmentation with minimal human intervention has led to the widespread adoption of language model technologies, facilitating the digitalization of chemistry in diverse industrial sectors such as pharmaceuticals and chemical manufacturing. This manuscript provides a concise overview of the scientific components that contributed to the prestigious Sandmeyer Award in 2022.

Biocatalysed synthesis planning using data-driven learning.

Enzyme catalysts are an integral part of green chemistry strategies towards a more sustainable and resource-efficient chemical synthesis. However, the use of biocatalysed reactions in retrosynthetic planning clashes with the difficulties in predicting the enzymatic activity on unreported substrates and enzyme-specific stereo- and regioselectivity. As of now, only rule-based systems support retrosynthetic planning using biocatalysis, while initial data-driven approaches are limited to forward predictions. Here, we extend the data-driven forward reaction as well as retrosynthetic pathway prediction models based on the Molecular Transformer architecture to biocatalysis. The enzymatic knowledge is learned from an extensive data set of publicly available biochemical reactions with the aid of a new class token scheme based on the enzyme commission classification number, which captures catalysis patterns among different enzymes belonging to the same hierarchy. The forward reaction prediction model (top-1 accuracy of 49.6%), the retrosynthetic pathway (top-1 single-step round-trip accuracy of 39.6%) and the curated data set are made publicly available to facilitate the adoption of enzymatic catalysis in the design of greener chemistry processes.

Catalytic Cascade Reactions Inspired by Polyketide Biosynthesis.

Aldol reactions belong to the most important methods for carbon-carbon bond formation and are also involved in one of the most astonishing biosynthetic processes: the biosynthesis of polyketides governed by an extraordinarily sophisticated enzymatic machinery. In contrast to the typical linear or convergent strategies followed in chemical synthesis, this late-stage catalysis concept allows Nature to assemble intermediates that are diversified into a broad range of scaffolds, which assume various crucial biological functions. To transfer this concept to small-molecule catalysis to access products beyond the natural systems, a stepwise approach to differentiate increasingly complex substrates was followed by investigating arene-forming polyketide cyclizations. An outline of our efforts to develop and apply these concepts are presented herein.

JoyaPhos: An Atropisomeric Teraryl Monophosphine Ligand.

A topologically well-defined atropisomeric teraryl monophosphine ligand system, prepared by a highly stereoselective arene-forming aldol condensation combined with a direct ester-to-anthracene transformation, is described herein. The ligands were evaluated for gold(I)-catalyzed [2+2] cycloaddition and cycloisomerization reactions as well as a unique intramolecular Pd-catalyzed C-N cross-coupling for the atroposelective synthesis of a N-aryl-indoline bearing a C-N stereogenic axis. The ligand structure induced up to 95:5 stereoselectivity in the asymmetric allylic alkylation reaction and features an interesting dynamic behavior as observed by X-ray crystallographic studies.

Shortcuts for Electron-Transfer through the Secondary Structure of Helical Oligo-1,2-Naphthylenes.

Atropisomeric 1,2-naphthylene scaffolds provide access to donor-acceptor compounds with helical oligomer-based bridges, and transient absorption studies revealed a highly unusual dependence of the electron-transfer rate on oligomer length, which is due to their well-defined secondary structure. Close noncovalent intramolecular contacts enable shortcuts for electron transfer that would otherwise have to occur over longer distances along covalent pathways, reminiscent of the behavior seen for certain proteins. The simplistic picture of tube-like electron transfer can describe this superposition of different pathways including both the covalent helical backbone, as well as noncovalent contacts, contrasting the wire-like behavior reported many times before for more conventional molecular bridges. The exquisite control over the molecular architecture, achievable with the configurationally stable and topologically defined 1,2-naphthylene-based scaffolds, is of key importance for the tube-like electron transfer behavior. Our insights are relevant for the emerging field of multidimensional electron transfer and for possible future applications in molecular electronics.

Catalyst-Controlled Stereodivergent Synthesis of Atropisomeric Multiaxis Systems.

Molecular scaffolds with multiple rotationally restricted bonds allow a precise spatial positioning of functional groups. However, their synthesis requires methods addressing the configuration of each stereogenic axis. We report here a catalyst-stereocontrolled synthesis of atropisomeric multiaxis systems enabling divergence from the prevailing stereochemical reaction path. By using ion-pairing catalysts in arene-forming aldol condensations, a strong substrate-induced stereopreference can be overcome to provide structurally well-defined helical oligo-1,2-naphthylenes. The configuration of up to four stereogenic axes was individually catalyst-controlled, affording quinquenaphthalenes with a unique topology.