My watch list  

Man versus (synthesis) machine

Active machine learning for the discovery and crystallization of gigantic polyoxometalate molecules


© Wiley-VCH

Who is the better experimentalist, a human or a robot? When it comes to exploring synthetic and crystallization conditions for inorganic gigantic molecules, actively learning machines are clearly ahead, as demonstrated by British Scientists in an experiment with polyoxometalates.

Polyoxometalates form through self-assembly of a large number of metal atoms bridged by oxygen atoms. Potential uses include catalysis, electronics, and medicine. Insights into the self-organization processes could also be of use in developing functional chemical systems like "molecular machines".

Polyoxometalates offer a nearly unlimited variety of structures. However, it is not easy to find new ones, because the aggregation of complex inorganic molecules to gigantic molecules is a process that is difficult to predict. It is necessary to find conditions under which the building blocks aggregate and then also crystallize, so that they can be characterized.

A team led by Leroy Cronin at the University of Glasgow (UK) has now developed a new approach to define the range of suitable conditions for the synthesis and crystallization of polyoxometalates. It is based on recent advances in machine learning, known as active learning. They allowed their trained machine to compete against the intuition of experienced experimenters. The test example was Na6[Mo120Ce6O366H12(H2O)78]·200 H2O, a new, ring-shaped polyoxometalate cluster that was recently discovered by the researchers' automated chemical robot.

In the experiment, the relative quantities of the three necessary reagent solutions were to be varied while the protocol was otherwise prescribed. The starting point was a set of data from successful and unsuccessful crystallization experiments. The aim was to plan ten experiments and then use the results from these to proceed to the next set of ten experiments - a total of one hundred crystallization attempts.

Although the flesh-and-blood experimenters were able to produce more successful crystallizations, the far more "adventurous" machine algorithm was superior on balance because it covered a significantly broader domain of the "crystallization space". The quality of the prediction of whether an experiment would lead to crystallization was improved significantly more by the machine than the human experimenters. A series of 100 purely random experiments resulted in no improvement. In addition, the machine discovered a range of conditions that led to crystals which would not have been expected based on pure intuition. This "unbiased" automated method makes the discovery of novel compounds more probably than reliance on human intuition. The researchers are now looking for ways to make especially efficient "teams" of man and machine.

Facts, background information, dossiers
  • automated synthesis
More about University of Glasgow
  • News

    Un-mixing using lasers to make new crystals

    Scientists have managed to separate two liquids in a mixture using a laser, which they claim will lead to new ways of manipulating matter and creating crystals for industry. Researchers from the University of Glasgow present a novel approach to separate and create new phases using a simple ... more

    Scientists create magnetic system transforming heat into motion

    A team of scientists have found a new way to transform ambient heat into motion in nanoscale devices – a discovery which could open up new possibilities for data storage, sensors, nanomotors and other applications in the ever-shrinking world of electronics. An international team of research ... more

    Lifting the lid on future military aircraft technologies

    Ahead of this years' Farnborough International Airshow, engineers and scientists at BAE Systems and the University of Glasgow have outlined their current thinking about military aircraft and how they might be designed and manufactured in the future. The concepts have been developed collabor ... more

  • Videos

    Growing UAVs Through Chemistry

    During this century, scientists and engineers from BAE Systems and The University of Glasgow envisage that small Unmanned Air Vehicles (UAVs) bespoke to military operations, could be 'grown' in large-scale labs through chemistry, speeding up evolutionary processes and creating bespoke aircr ... more

More about Wiley-VCH
  • News

    Pores with a Memory

    Whether for separation processes, photovoltaics, catalysis, or electronics, porous polymer membranes are needed in many fields. Membranes with micropores that switch between different shapes and/or sizes would expand the possibilities. Scientists have introduced a process that produces poro ... more

    Prelithiation strategy enhances battery performance at low temperatures

    When it is cold in winter, cars tend to have starting problems. This is not much better with electric cars, which inevitably lose capacity of their rechargeable lithium-ion batteries at freezing temperatures. Now, Chinese scientists have offered a strategy to avoid plunging battery kinetics ... more

    More solar power thanks to titanium

    Earth-abundant, cheap metals are promising photocatalytic electrode materials in artificial photosynthesis. A team of Chinese scientists now reports that a thin layer of titania beneath hematite nanorods can boost the performance of the photoanode. As outlined in their report, the nanostruc ... more

  • Companies

    Wiley-VCH Verlag GmbH & Co. KGaA

    Wiley-VCH publishes monographs, textbooks, major references works and journals in print or online. Wiley-VCH can look back on over 80 years of publishing in chemistry, materials sciences, physics and the life sciences. more

Your browser is not current. Microsoft Internet Explorer 6.0 does not support some functions on Chemie.DE