by It’s not hard to be blown away by the beauty and unprecedented detail of the photos taken by NASA’s James Webb Space Telescope. Not only are the images beautiful, but they also have the potential to enhance our understanding of the origins of the universe and reveal previously unseen aspects of the universe. When we can see our surroundings, we can better understand where we are going — or want to go — and how best to get there.
Anatole von Lilienfeld also navigates space, but instead of exploring the depths of the universe, his work is here on Earth in “chemical space.”
And instead of chasing unknown stars, galaxies and other celestial objects, his focus is on the untapped potential of unexplored chemical combinations. To do this job, he is not equipped with a powerful telescope – his tool of choice is artificial intelligence (AI).
Von Lilienfeld is the inaugural Clark Chair in Advanced Materials at the Vector Institute and the University of Toronto and a core member of the U of T’s Acceleration Consortium (AC). Jointly appointed to the Department of Chemistry in the School of Arts & Science and the Department of Materials Science & Engineering in the School of Applied Science & Engineering, he is one of the world’s brightest visionaries about using computers to understand the vastness of the chemical space.
Von Lilienfeld, who was recently named CIFAR AI Chair in Canada, was a speaker at AC’s first annual Accelerate conference last month at U of T.
This four-day program focused on the power of self-driving laboratories (SDL), an emerging technology that combines artificial intelligence, automation and advanced computing to accelerate materials and molecular discovery. The Accelerate conference drew over 200 people and featured keynotes and panels featuring more than 60 experts from academia, industry and government who are shaping the emerging field of accelerated science.
Erin Warner, communications specialist at the Acceleration Consortium, recently spoke with von Lilienfeld about the conference and the digitization of chemistry.
How big is the “chemical” space?
We are surrounded by matter and molecules. Think of the chemical compounds that make up our clothes, the pavement we walk on, and the batteries in our electric cars. Now consider the new potential combinations that are out there waiting to be discovered, such as catalysts for efficient capture and use of atmospheric CO2, low-carbon cement, lightweight biodegradable composites, membranes for water filtration, and powerful molecules for treating cancer and bacteria -resistant disease.
From a practical point of view, chemical space is infinite, and searching it is no small feat. A lower estimate says it contains 1060 compounds — more than the number of atoms in our solar system.
Why should we accelerate the search for new materials?
Many of the most widely used materials no longer serve us. Most of the world’s plastic waste produced to date has not yet been recycled. But the materials that will power the future will hopefully be sustainable, circular and cheap.
Conventional chemistry is slow, a series of often tedious trial and error that limits our ability to explore beyond a small subset of possibilities. However, AI can speed up the process by predicting which combinations might result in a material with the set of desired characteristics we are looking for (eg conductive, biodegradable, etc.).
This is just one step in self-driving labs, an emerging technology that combines artificial intelligence, automation and advanced computing to reduce the time and cost of materials discovery and development by up to 90%.
How can human chemists and artificial intelligence work together effectively?
AI is a tool that people can use to speed up and improve their own research. It can be considered as the fourth pillar of science. The pillars, which build on each other, include experimentation, theory, computer simulation and artificial intelligence.
Experimentation is the foundation. We experiment with the goal of improving the natural world for people. Then comes theory to give your experiments shape and direction. But the theory has its limitations. Without computer simulation, the amount of computation required to support scientific research would take much longer than a lifetime. But even computers have limitations.
With difficult equations comes the need for high performance computers, which can be quite expensive. This is where AI comes in. AI is a less expensive alternative. It can help scientists predict both an experimental and a computational result. And the more theory we incorporate into the AI model, the better the prediction. AI can also be used to power a robotic lab, allowing the lab the ability to operate 24/7. Human chemists will not be replaced. Instead, they can forego tedious hours of trial and error to focus more on goal planning and other higher-level analysis.
Are there limitations to artificial intelligence like the ones you described in the other pillars of science?
Yes, it is important to note that AI is not a silver bullet and that there is a cost associated with it that can be measured in data acquisition. You can’t use AI without data. And acquiring data requires experimentation and recording the result in a way that can be processed by computers. Like a human, the AI then learns by looking at the data and making an extrapolation or prediction.
Acquiring data is expensive, both financially and in terms of carbon footprint. To counter this, the aim is to improve artificial intelligence. If you can encode our understanding of physics into AI, it becomes more efficient and requires less data to learn from, but provides the same predictive properties. If less data is needed for training, then the AI model becomes smaller.
Instead of just using the AI as a tool, the chemist can also interrogate it to see how well its data captures the theory, perhaps leading to the discovery of a relevant new law of chemistry. Although this interactive relationship is not so common, it may be on the horizon and could improve our theoretical understanding of the world.
How can we make AI for discovery more accessible?
The first way is open source research. In the emerging field of accelerated science, there are many proponents of open source access. Not only do journals provide access to research papers, but in many cases to data, which is an important element in making the field more accessible. There are also repositories for models and code such as GitHub. Providing access could lead to scientific advances that will ultimately benefit all of humanity.
A second way to expand AI for discovery is to include more learners. We need to teach basic computer science and coding skills as part of a chemistry or materials science education. Schools around the world are beginning to update their curricula toward this end, but we have yet to see more incorporate this basic education. The future of science is digital.
How do initiatives like the Acceleration Consortium and a conference like Accelerate help advance the field?
We are at the dawn of true digitization of the chemical sciences. Coordinated joint efforts, such as the Acceleration Consortium, will play a critical role in synchronizing efforts not only at the technical but also at the societal level, thus enabling the global application of an “updated” version of chemical engineering with unprecedented benefits for humanity unimaginable. The consortium also serves to connect academia and industry, two worlds that could benefit from a closer relationship. Visionaries in the commercial sector can dream up opportunities, and the consortium will be there to help make the science work. The innovative nature of artificial intelligence is that it can be applied to any field. Artificial intelligence is on track to have an even bigger impact than the advent of computers.
Accelerate, the consortium’s first annual conference, was a great gathering event for the community and a reminder that remarkable things can come from a gathering of brilliant minds. While Zoom has done a lot for us during the pandemic, it can’t easily replicate the excitement and enthusiasm often fostered in an in-person conference that is needed to drive research and encourage a team to pursue a complex goal. .
Which area of the “chemical space” fascinates you the most?
Catalysts, which allow a certain chemical reaction to occur, but remain unchanged in the process. A century ago, Haber and Bosch developed a catalytic process that would allow nitrogen – the dominant substance in the air we breathe – to be converted into ammonia. Ammonia is a critical raw material for the chemical industries, but also for fertilizers. It made possible the mass production of fertilizers and saved millions of people from starvation. Large fractions of humanity would not exist at this time if it were not for this catalyst.
From a physics perspective, what determines and controls catalyst activity and components are fascinating questions. They can also be critical in helping us face some of our most pressing challenges. If we could find a catalyst that could use sunlight to quickly and efficiently convert nitrogen into ammonia, we could solve our energy problem by using ammonia as a fuel. You can think of the reactions that catalysts enable as ways of traveling through chemical space and connecting different states of matter.
#Exploring #chemical #space #Anatole #von #Lilienfeld
