Search

The discovery of chemical reactions is an inherently unpredictable and time-consuming process1. An attractive alternative is to predict reactivity, although relevant approaches, such as computer-aided reaction design, are still in their infancy2. Reaction prediction based on high-level quantum chemical methods is complex3, even for simple molecules. Although machine learning is powerful for data analysis4,5, its applications in chemistry are still being developed6. Inspired by strategies based on chemists’ intuition7, we propose that a reaction system controlled by a machine learning algorithm may be able to explore the space of chemical reactions quickly, especially if trained by an expert8. Here we present an organic synthesis robot that can perform chemical reactions and analysis faster than they can be performed manually, as well as predict the reactivity of possible reagent combinations after conducting a small number of experiments, thus effectively navigating chemical reaction space. By using machine learning for decision making, enabled by binary encoding of the chemical inputs, the reactions can be assessed in real time using nuclear magnetic resonance and infrared spectroscopy. The machine learning system was able to predict the reactivity of about 1,000 reaction combinations with accuracy greater than 80 per cent after considering the outcomes of slightly over 10 per cent of the dataset. This approach was also used to calculate the reactivity of published datasets. Further, by using real-time data from our robot, these predictions were followed up manually by a chemist, leading to the discovery of four reactions.

We present a study in which the versatility of 3D-printing is combined with the processing advantages of flow chemistry for the synthesis of organic compounds. Robust and inexpensive 3D-printed reactionware devices are easily connected using standard fittings resulting in complex, custom-made flow systems, including multiple reactors in a series with in-line, real-time analysis using an ATR-IR flow cell. As a proof of concept, we utilized two types of organic reactions, imine syntheses and imine reductions, to show how different reactor configurations and substrates give different products.

Change history: Owing to the misidentification of compound 22 in the original Letter, changes have been made to Fig. 5, Extended Data Fig. 2 and the main text; see accompanying Amendment.

Selenium-based reagents bear a high potential for the improvement of known reactions not only from an environmental and pharmaceutical point of view, but also as interesting reagents for the development of, completely new synthetic transformations and as potential ligands in catalytic reactions. A variety of organoselenium compounds have been proven to be useful for organic synthesis over several decades. Organoselenium species can be introduced as either nucleophiles or electrophiles to other organic molecules, producing useful intermediates for organic synthesis. Optically active organoselenium derivatives and their application to highly selective asymmetric synthesis are also of current interest. Probably the most interesting aspect, which emerged in recent years, concerns the possibility of effecting some functional group conversions using catalytic amounts of the selenium reagent or using selenium containing compounds as chiral ligands in metal catalyzed reactions. The developments of all these catalytic processes represent the most important results which have been reported recently in this field and their conceptual and synthetic relevance considerably increases the use of some organoselenium derivatives as Green Catalysts. [1] In consideration that in Nature, the main biological function of selenium is associated with its incorporation in the form of selenocysteine (Sec) into certain proteins having redox motifs different selenium containing compounds can be investigated as bio-inspired catalysts in the carbon-carbon multiple bond oxidation mediated by H2O2 in water. These catalysts resulted to be also interesting good GPx-mimetics. Acknowledgement: Financial support from M.I.U.R.-PRIN2007, Consorzio CINMPIS, Bari, University of Perugia, the grant "British-Italian Partnership" from the British Council/CRUI. References [1] a) D. M. Freudendahl, S. Santoro, S. A. Shahzad, C. Santi, T. Wirth Angew. Chem. Int. Ed.2009, 8, 8409.b) C. Santi, M. Tiecco, L. Testaferri, C. Tomassini, S. Santoro, G. Bizzoca Phosphorus Sulfur Silicon Relat. Elem. 2008,183, 956. c) S. Santoro, C. Santi, M. Sabatini, L. Testaferri, M. Tiecco Adv.Synth. Catal. 2008, 350, 2881. d) S. Santoro, B. Battistelli, B. Gjoka, C-w.S.Si, L.Testaferri, M. Tiecco, C. Santi Synlett, 2010, 1402.