Robots have repeatedly demonstrated that they can do the work that humans do. And chemists havent escaped this automation trend. Food, pharmaceutical, and other industries have sped up routine processes by using robots to sample and analyse products. Chemists have deigned programs like Chematica to let computers plan synthetic routes. Research groups have even demonstrated nearly autonomous systems that use machine learning to design, carry out, and evaluate experiments. But the cost and complexity of some of these systems make them unattainable for many chemistry labs. At the American Chemical Society national meeting in New Orleans on Sunday, Alán Aspuru-Guzik of Harvard University described a free software package called ChemOS that he developed to make the tools of automation available to more scientists. If you look at the chemistry lab of the 16th century or even the 21st century, you will see the same thing, in terms of how chemists run experiments, Aspuru-Guzik says. Nothing has changed really. If we really want to rethink discovery, we need to rethink the laboratory. ChemOS uses machine learning to interpret commands from users and then plan, execute, evaluate, and refine experiments. It can communicate with humans through email or programs like Slack and Twitter. It can also interact with other automation software like the programs that control robotic arms or solution injectors on laboratory machines. Aspuru-Guzik compares it to a brain, performing the higher-level functions needed to coordinate a successful experiment. His group also demonstrated how ChemOS could run experiments in remote labs. Aspuru-Guzik designed an experiment at Harvard and used ChemOS to carry it out with equipment on the other side of the continent in the laboratory of organic chemist Jason E. Hein at the University of British Columbia. Running experiments from centralised laboratories could reduce costs and improve efficiency, Aspuru-Guzik says. At a session in the Division of Polymeric Materials: Science & Engineering, Aspuru-Guzik also described how ChemOS could help find new materials. He said autonomous systems could quickly screen and optimise methods for making carbon nanotubes or discover new metal-organic frameworks that could help us generate, store, and use energy in more environmentally friendly ways. A program like ChemOS could be a boon for high-throughput screening, said S. Joshua Swamidass, a bioinformatics scientist at Washington University in St. Louis. He has created algorithms to make screening more efficient and says they could have a broader impact if integrated into software like ChemOS.
Chemical & Engineering News, 19 March 2018 ; http://pubs.acs.org/cen/news