Author Correction: Controlling an organic synthesis robot with machine learning to search for new reactivity.

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.

Controlling an organic synthesis robot with machine learning to search for new reactivity.

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.

Publisher Correction: Controlling an organic synthesis robot with machine learning to search for new reactivity.

The chemical structure formatting in Fig. 5 has been corrected online.

An autonomous organic reaction search engine for chemical reactivity.

The exploration of chemical space for new reactivity, reactions and molecules is limited by the need for separate work-up-separation steps searching for molecules rather than reactivity. Herein we present a system that can autonomously evaluate chemical reactivity within a network of 64 possible reaction combinations and aims for new reactivity, rather than a predefined set of targets. The robotic system combines chemical handling, in-line spectroscopy and real-time feedback and analysis with an algorithm that is able to distinguish and select the most reactive pathways, generating a reaction selection index (RSI) without need for separate work-up or purification steps. This allows the automatic navigation of a chemical network, leading to previously unreported molecules while needing only to do a fraction of the total possible reactions without any prior knowledge of the chemistry. We show the RSI correlates with reactivity and is able to search chemical space using the most reactive pathways.

A self optimizing synthetic organic reactor system using real-time in-line NMR spectroscopy.

A configurable platform for synthetic chemistry incorporating an in-line benchtop NMR that is capable of monitoring and controlling organic reactions in real-time is presented. The platform is controlled via a modular LabView software control system for the hardware, NMR, data analysis and feedback optimization. Using this platform we report the real-time advanced structural characterization of reaction mixtures, including 19F, 13C, DEPT, 2D NMR spectroscopy (COSY, HSQC and 19F-COSY) for the first time. Finally, the potential of this technique is demonstrated through the optimization of a catalytic organic reaction in real-time, showing its applicability to self-optimizing systems using criteria such as stereoselectivity, multi-nuclear measurements or 2D correlations.

3D-printed devices for continuous-flow organic chemistry.

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.

Configurable 3D-Printed millifluidic and microfluidic 'lab on a chip' reactionware devices.

We utilise 3D design and 3D printing techniques to fabricate a number of miniaturised fluidic 'reactionware' devices for chemical syntheses in just a few hours, using inexpensive materials producing reliable and robust reactors. Both two and three inlet reactors could be assembled, as well as one-inlet devices with reactant 'silos' allowing the introduction of reactants during the fabrication process of the device. To demonstrate the utility and versatility of these devices organic (reductive amination and alkylation reactions), inorganic (large polyoxometalate synthesis) and materials (gold nanoparticle synthesis) processes were efficiently carried out in the printed devices.