Applications of machine learning (ML) to synthetic chemistry rely on the assumption that large numbers of literature-reported examples should enable construction of accurate and predictive models of chemical reactivity. This paper demonstrates that abundance of carefully curated literature data may be insufficient for this purpose. Using an example of Suzuki–Miyaura coupling with heterocyclic building blocks—and a carefully selected database of >10,000 literature examples—we show that ML models cannot offer any meaningful predictions of optimum reaction conditions, even if the search space is restricted to only solvents and bases. This result holds irrespective of the ML model applied (from simple feed-forward to state-of-the-art graph-convolution neural networks) or the representation to describe the reaction partners (various fingerprints, chemical descriptors, latent representations, etc.). In all cases, the ML methods fail to perform significantly better than naive assignments based on the sheer frequency of certain reaction conditions reported in the literature. These unsatisfactory results likely reflect subjective preferences of various chemists to use certain protocols, other biasing factors as mundane as availability of certain solvents/reagents, and/or a lack of negative data. These findings highlight the likely importance of systematically generating reliable and standardized data sets for algorithm training.

General conditions for organic reactions are important but rare, and efforts to identify them usually consider only narrow regions of chemical space. Discovering more general reaction conditions requires considering vast regions of chemical space derived from a large matrix of substrates crossed with a high-dimensional matrix of reaction conditions, rendering exhaustive experimentation impractical. Here, we report a simple closed-loop workflow that leverages data-guided matrix down-selection, uncertainty-minimizing machine learning, and robotic experimentation to discover general reaction conditions. Application to the challenging and consequential problem of heteroaryl Suzuki-Miyaura cross-coupling identified conditions that double the average yield relative to a widely used benchmark that was previously developed using traditional approaches. This study provides a practical road map for solving multidimensional chemical optimization problems with large search spaces.

Efficient long-range charge transport is required for high-performance molecular electronic devices. Resonant transport is thought to occur in single molecule junctions when molecular frontier orbital energy levels align with electrode Fermi levels, thereby enabling efficient transport without molecular or environmental relaxation. Despite recent progress, we lack a systematic understanding of the transition between nonresonant and resonant transport for molecular junctions with different chemical compositions. In this work, we show that molecular junctions undergo a reversible transition from nonresonant tunneling to resonant transport as a function of applied bias. Transient bias-switching experiments show that the nonresonant to resonant transition is reversible with the applied bias. We determine a general quantitative relationship that describes the transition voltage as a function of the molecular frontier orbital energies and electrode Fermi levels. Overall, this work highlights the importance of frontier orbital energy alignment in achieving efficient charge transport in molecular devices.

The development of next-generation organic electronic materials critically relies on understanding structure-function relationships in conjugated polymers. However, unlocking the full potential of organic materials requires access to their vast chemical space while efficiently managing the large synthetic workload to survey new materials. In this work, we use automated synthesis to prepare a library of conjugated oligomers with systematically varied side chain composition followed by single-molecule characterization of charge transport. Our results show that molecular junctions with long alkyl side chains exhibit a concentration-dependent bimodal conductance with an unexpectedly high conductance state that arises due to surface adsorption and backbone planarization, which is supported by a series of control experiments using asymmetric, planarized, and sterically hindered molecules. Density functional theory simulations and experiments using different anchors and alkoxy side chains highlight the role of side chain chemistry on charge transport. Overall, this work opens new avenues for using automated synthesis for the development and understanding of organic electronic materials.

Conventional materials discovery is a laborious and time‐consuming process that can take decades from initial conception of the material to commercialization. Recent developments in materials acceleration platforms promise to accelerate materials discovery using automation of experiments coupled with machine learning. However, most of the automation efforts in chemistry focus on synthesis and compound identification, with integrated target property characterization receiving less attention. In this work, an automated platform is introduced for the discovery of molecules as gain mediums for organic semiconductor lasers, a problem that has been challenging for conventional approaches. This platform encompasses automated lego‐like synthesis, product identification, and optical characterization that can be executed in a fully integrated end‐to‐end fashion. Using this workflow to screen organic laser candidates, discovered eight potential candidates for organic lasers is discovered. The lasing threshold of four molecules in thin‐film devices and find two molecules with state‐of‐the‐art performance is tested. These promising results show the potential of automated synthesis and screening for accelerated materials development.