Rersearch & Innovation

'No small feat': U of T's Anatole von Lilienfeld is using AI to explore the vastness of 'chemical space'

Christopher.Sorensen — Mon, 05 Dec 2022 16:55:07 +0000

'No small feat': U of T's Anatole von Lilienfeld is using AI to explore the vastness of 'chemical space'

Christopher.Sorensen Mon, 12/05/2022 - 11:55

Cutline

Anatole von Lilienfeld is one of the world's brightest visionaries on the use of computers to understand the vastness of chemical space. (photo by Diana Tyszko)

Erin Warner

Topic

Our Community

Acceleration Consortium

Institutional Strategic Initiatives

Artificial Intelligence

Department of Chemistry

Faculty of Applied Science & Engineering

Faculty of Arts & Science

Rersearch & Innovation

Vector Institute

The ��Ƶ’s Anatole von Lilienfeld navigates space – but rather than exploring the depths of the universe, his artificial intelligence-powered work focuses on “chemical space” and the untapped potential of undiscovered chemical combinations.

The inaugural Clark Chair in Advanced Materials at U of T and the Vector Institute for Artificial Intelligence – and a pivotal member of U of T's Acceleration Consortium – von Lilienfeld is one of the world's foremost visionaries for the use of computers to understand the vastness of chemical space.

Von Lilienfeld, a professor jointly appointed to U of T’s department of chemistry in the Faculty of Arts & Science and the department of materials science and engineering in the Faculty of Applied Science & Engineering, was a speaker at the Acceleration Consortium’s first annual Accelerate conference earlier this year. The four-day program explored the power of self-driving labs, an emerging technology that combines AI, automation and advanced computing to accelerate materials and molecular discovery.

Writer Erin Warner recently spoke with von Lilienfeld about the digitization of chemistry and what the future holds.

How big is chemical space?

We are surrounded by materials and molecules. Consider the chemical compounds that make up our clothing, the pavement we walk on, and the batteries in our electric cars. Now think about the new possible combinations that are out there waiting to be discovered, such as catalysts for effective atmospheric CO2 capture and utilization, low-carbon cement, lightweight biodegradable composites, membranes for water filtration, and potent molecules for treatment of cancer and bacterial-resistant disease.

In a practical sense, 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 do we need to accelerate the search for new materials?

Many of the most widely used materials no longer serve us. Most of the world’s plastic waste generated to date has not yet been recycled. But the materials that will power the future will hopefully be sustainable, circular, and inexpensive.

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 accelerate the process by predicting which combinations might result in a material with the set of desired characteristics we are looking for (e.g., conductive, biodegradable, etc.).

This is but onestep in self-driving laboratories, an emerging technology that combines AI, automation, and advanced computing to reduce the time and cost of discovering and developing materials by up to 90 per cent.

How can human chemists and AI work together effectively?

AI is a tool that humans can use to accelerate and improve their own research. It can be thought of as the fourth pillar of science. The pillars, which build on each other, include experimentation, theory, computer simulation and AI.

Experimentation is the foundation. We experiment with the aim of improving the physical world for humans. Then comes theory to give your experiments shape and direction. But theory has its limitations. Without computer simulation, the amount of computation needed to support scientific research would take far longer than a lifetime. But even computers have constraints.

With difficult equations come the need for high-performance computing, which can be quite costly. This is where AI comes in. AI is a less costly alternative. It can help scientists predict both an experimental and computational outcome. And the more theory we build into the AI model, the better the prediction. AI can also be used to power a robotic lab, allowing the lab the ability to run 24/7. Human chemists will not be replaced; instead, they can hand off tedious hours of trial and error to focus more on designing the objectives and other higher-level analysis.

Are there any limitations to AI, 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 cannot use AI without data. And data acquisition requires experimenting and recording the outcome in a way that can be processed by computers. Like a human, the AI then learns by reviewing the data and making an extrapolation or prediction.

Data acquisition is costly, both financially and in terms of its carbon footprint. To address this, the goal is to improve the AI. If you can encode our understanding of physics into the AI, it becomes more efficient and requires less data to learn but provides the same predictive qualities. If less data is needed for training, then the AI model becomes smaller.

Rather than just using AI as a tool, the chemist can also interrogate it to see how well its data captures theory, perhaps leading to the discovery of a new relative law for chemistry. While this interactive relationship is not as 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 are journals providing access to research papers, but also in many cases to the data, which is a major component for making the field more accessible.

There are also repositories for models and code, like GitHub. Data sets can record and encode a lot of value.Providing more open access to data, which can be too costly for some to generate on their own, could lead to scientific advancements that ultimately benefit all of humanity. Scientists can then use the data from other scientists to ask their own research questions and make their own AI models.

A second way to expand AI for discovery is to include more students. 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 to this effect, but we still need to see more incorporate this essential training. The future of the sciences is digital.

How do initiatives like Acceleration Consortium, and a conference like Accelerate, help advance the field?

We are at the dawn of truly digitizing the chemical sciences. Coordinated, joint efforts, such as the Acceleration Consortium, will play a crucial role in synchronizing efforts not only at the technical but also at the societal level, thereby enabling the worldwide implementation of an ‘updated’ version of chemical engineering with unprecedented advantages for humanity at large. 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 groundbreaking nature of AI is that it can be applied to any sector. AI is on a trajectory to have an even greater impact than the advent of computers.

Accelerate, the consortium’s first annual conference, was a great rallying event for the community and was a reminder that remarkable things can come from a gathering of bright minds. While Zoom has done a lot for us during the pandemic, it cannot easily replicate the excitement and enthusiasm often cultivated at an in-person conference and which are needed to direct research and encourage a group to pursue a complex goal.

Anatole von Lilienfeld at the first annual Accelerate conference (photo by Clifton Li)

What area of chemical space fascinates you the most?

Catalysts, which enable 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 the transformation of nitrogen—the dominant substance in the air we breathe—into ammonia. Ammonia is a crucial starting material for chemical industries, but also for fertilizers. It made the mass production of fertilizers possible and saved millions of people from starvation. Major fractions of humanity would not exist right now if it were not for this catalyst.

From a physics point of view, what defines and controls catalyst activity and components are fascinating questions. They might also be critical for helping us address some of our most pressing challenges. If we were to find a catalyst that could use sunlight to turn nitrogen rapidly and efficiently into ammonia, we might be able to solve our energy problem by using ammonia for fuel. You can think of the reactions that catalysts enable as ways of traveling through chemical space and to connect different states of matter.

Percentage of breast cancer survivors in Canada doubles over past 15 years, study finds

Christopher.Sorensen — Thu, 27 Oct 2022 15:37:10 +0000

Percentage of breast cancer survivors in Canada doubles over past 15 years, study finds

Christopher.Sorensen Thu, 10/27/2022 - 11:37

Cutline

A study shows there are 2.5 times as many breast cancer survivors in Canada today as there were in 2007 – a success story that brings some new health challenges (photo by Boogich/Getty Images)

Topic

Faculty of Kinesiology & Physical Education

Rersearch & Innovation

It was the information she couldn’t find that led Amy Kirkham, an assistant professor in the ��Ƶ’s Faculty of Kinesiology & Physical Education (KPE), to her latest discovery.

Asked by the Canadian Women’s Heart Health Alliance to co-author a scientific statement paper in 2020 on the state of women’s heart health in Canada, Kirkham - whose research is focused on preventing and treating the risk of heart disease related to breast cancer treatment – needed to know what percentage of the Canadian female population has a history of breast cancer.

But the most recent statistic she could find – one percent – was from 2007.

“Nearly 15 years had passed and I could not find a more recent citation about the prevalence of breast cancer survivors in Canada,” says Kirkham. “Breast cancer mortality rates had continued to improve 26 per cent over this time period, so I suspected that this number was no longer accurate.”

Amy Kirkham

So, in collaboration with Katarzyna Jerzak, a medical oncologist at Sunnybrook Odette Cancer Centre and assistant professor in the department of medicine in U of T’s Temerty Faculty of Medicine, Kirkham embarked on a new study that would determine an up-to-date estimate of the prevalence of breast cancer survivors in Canada in 2022 using the Canadian Cancer Society’s annual cancer statistic reports.

The study, recently published in the Journal of the National Comprehensive Cancer Network, found that in the 15-year span from 2007 to 2021, there were 370,756 patients (2.1 per cent of the adult female population in Canada in 2022) diagnosed with breast cancer and 86 per cent of these women would have survived breast cancer by 2022.

“This indicates that the prevalence of breast cancer survivors in the Canadian female population has doubled and that there are 2.5 times more survivors since the last estimate in 2007,” says Kirkham.

The prior estimate did not include the age group of survivors, but according to the new estimate provided by Kirkham and Jerzak, breast cancer survivors represent one per cent of Canadian women in the typical working and/or child-raising age group (20 to 64 years) and 5.4 per cent of senior (aged 65-plus) Canadian women.

But it’s not all good news.

Many of the treatments that have improved breast cancer mortality rates also cause short-term and long-term side effects, which, in turn, can raise the risk of death from other causes such as heart disease, stroke, Alzheimer’s disease, liver disease and other non-fatal health outcomes.

“The most common cause of death in women with breast cancer is heart disease,” Kirkham says.

Such conditions also affect overall health-care costs.

To demonstrate the excess health-care costs related to heart disease, Kirkham and Jerzak performed an additional analysis using Canadian data on rates of hospitalization for heart failure and their costs. They found that two per cent of the women diagnosed with breast cancer between 2007 and 2021 would likely experience heart failure hospitalization costing $66.5 million in total. As much as 25 per cent of these costs, or $16.5 million, were in excess of those costs that would be associated with women who did not have breast cancer.

“Given the excess health-care costs, potential for reduced contributions to the workforce and reduced quality of life associated with long-term side effects and risk of excess death among breast cancer survivors, our work highlights that there is a growing segment of the population who require services to support recovery following breast cancer treatment," says Kirkham.

“The goal of my research lab is to develop new therapies to improve the health of women after surviving breast cancer.”

U of T's Sajeev John receives Gerhard Herzberg Canada Gold Medal for work on harnessing flow of photons

Christopher.Sorensen — Wed, 17 Nov 2021 15:36:54 +0000

U of T's Sajeev John receives Gerhard Herzberg Canada Gold Medal for work on harnessing flow of photons

Christopher.Sorensen Wed, 11/17/2021 - 10:36

Cutline

Physicist Sajeev John received the award for his groundbreaking research and fundamental advancements in confining and harnessing the flow of photons of light in a manner analogous to harnessing the flow of electrons (photo by Sylvie Li/Shoot Studio)

Chris Sasaki

Topic

Our Community

Gerhard Herzberg Canada Gold Medal

Awards

Faculty of Arts & Science

NSERC

Physics

Rersearch & Innovation

Theoretical physicist Sajeev John has received Canada’s highest science and engineering honour, the prestigious Gerhard Herzberg Canada Gold Medal.

John is receiving the award for his groundbreaking research and fundamental advancements in confining and harnessing the flow of photons of light in a manner analogous to harnessing the flow of electrons.

The medal also recognizes John for his leadership in efforts to transform this research into groundbreaking applications in optical micro-chips, optical communications and information processing, laser technologies, solar-energy harvesting and clinical medicine – including life-saving surgical tools and techniques.

“I am profoundly honoured and feel singularly energized to bring to broader fruition the work I began on light-trapping crystals,” says John, a University Professor in the Faculty of Arts & Science's department of physics.

“The Herzberg Gold Medal offers a unique opportunity for creativity and unfettered pursuit of essential applications such as the world’s most efficient, lightweight silicon solar cells; light-trapping to enhance artificial photosynthesis for solar fuel production; development of the most compact lab-in-a-photonic-crystal sensors for early-stage disease detection and diagnosis; and much more.”

Named after the Canadian physicist and Nobel laureate in chemistry, the Gerhard Herzberg Canada Gold Medal recognizes the excellence and impact of a recipient’s research. It is awarded annually by the Natural Sciences and Engineering Research Council of Canada (NSERC).

“Professor John is truly deserving of the country’s highest scientific honour,” says Melanie Woodin, dean of the Faculty of Arts & Science. “Not only has his work been foundational, it has also had an impact in physics, chemistry, engineering and medicine, and is leading to advancements that are benefiting people’s lives.”

John's research provides a solution to the problem that photons do not tend to flow along confined pathways like electrons but instead disperse or are absorbed.

According to Kim Strong, chair of the department of physics, “Professor John’s research laid out the theoretical foundation for special materials – called Photonic Band Gap (PBG) materials – that allow confinement, or localization, of photons to a microscopic region with the size of the wavelength of light.”

“Once you know how to confine photons to a single location,” she says, “you can confine their motion along prescribed microscopic circuit paths, analogous to the way the motion of electrons is controlled on the nanometer scale in semiconductors.”

Following up on his theoretical work, John and his collaborators built the first large-scale silicon PBG material out of a synthetic opal and have created PBG materials that are even easier and cheaper to manufacture.

The groundbreaking work has sparked the development of novel micro-structured materials known as photonic crystals, now referred to as “semiconductors of light.” Ultimately, the breakthrough will enable computer chips to operate with photons instead of electrons.

Among many impacts beyond the lab, research into PBG materials has already produced life-saving advancements in clinical medicine. In 2004, laser surgery was performed on a patient to remove a previously treated tumour that was recurring and remained life-threatening. A final, successful surgery was carried out using a hollow-core photonic band gap fibre. Thousands of similar procedures have been performed using PBG fibres and several major medical centres are now testing PBG-fibre-based laser surgery tools.

"The ��Ƶ congratulates Sajeev John on this important recognition,” says Professor Leah Cowen, U of T’s associate vice-president of research. “From his groundbreaking work on confining and harnessing the flow of photons to his leadership in exploring applications for his research in optical micro-chips, optical communications and information processing, laser technologies, solar energy-harvesting and clinical medicine – his impact has been remarkable.”

In 1984, John received his PhD in physics from Harvard University, where he published the original paper on light localization. He was an assistant professor at Princeton University, where he pioneered the concept of photonic band gap materials. He joined U of T in 1989.

John’s research and scientific leadership earned him the 2001 King Faisal International Prize in Science (with Nobel laureate C.N. Yang). In 2007, the Institute of Electrical and Electronics Engineers (IEEE) awarded him with the International Quantum Electronics Award for “the invention of and development of light-trapping crystals and the elucidation of their properties and applications.”

He is holder of a Canada Research Chair in optical sciences and was named an Officer of the Order of Canada in 2017.

TikTok teaching? U of T researchers study the social media platform's use in academia

Christopher.Sorensen — Tue, 16 Nov 2021 16:42:21 +0000

TikTok teaching? U of T researchers study the social media platform's use in academia

Christopher.Sorensen Tue, 11/16/2021 - 11:42

Cutline

(Image courtesy of KMDI)

Topic

Our Community

Faculty of Information

Graduate Students

Rersearch & Innovation

Social Media

In a bid to shine a spotlight on their research and make it more accessible, academics around the world are following in the footsteps of their students and taking to TikTok to share videos.

The trend is being highlighted by a team of researchers at the Knowledge Media Design Institute (KMDI) at the ��Ƶ’s Faculty of Information. The researchers looked at the different ways academics, educators and scholarly communities are using TikTok, the popular social media platform that specializes in short-form user-generated videos, to share knowledge – from Gothic architecture explainers to weight loss tips.

In particular, the researchers examined user behaviour, concerns about youth engagement, data and privacy implications, the technical features of the app and the visual aspect of scholarly contribution.

“If watching YouTube is like sitting in a lecture, then using TikTok is like having a conversation,” says study co-lead JP King, a sessional instructor at the John H. Daniels Faculty of Architecture, Landscape, and Design who works as KMDI’s data visualization and graphic designer. “TikTok provides a fun place to create new forms of accessible learning shared outside of classrooms, textbooks, and conference halls.

Led by King and Associate Professor Sara Grimes, director of KMDI, four graduate students with an interest in critical media literacy reviewed TikTok videos made by academics for the study. The team also analyzed more than 100 journal articles, books and research papers focused on TikTok, social media, technology and digital rights. Their study recommends some best practices for academics using TikTok, which ranks as the fourth most popular social media platform after YouTube, Snapchat and Instagram (see below).

The researchers found that TikTok videos often tend to be “amateurish” and offer a peek behind the scenes. The estimated 20 million-plus daily users, who are mostly under 30, embrace a less professional approach and don't feel the need to make everything perfect. They may simply record themselves with their smartphones with no special lighting or makeup. While this might feel out of place on Instagram or YouTube, it is acceptable if not expected on TikTok.

TikTok is also unique in how it encourages active engagement. Users can remix one another’s videos or produce creative responses towards others’ content. At the same time, however, users risk having their video or audio remixed or repurposed without their permission if they don’t adjust their privacy settings accordingly.

“You might make a sincere video explaining your research that someone else turns into a song or a joke,” the study warns academics. “Decide now if you’re comfortable with that possibility.”

The study’s authors attributed the phenomenon at least partly to a generational shift around intellectual property. Without bibliographies or citations, TikTok videos can challenge the sense of ownership that academic communities have traditionally had around ideas. “It’s more difficult to maintain ownership of your ideas online, and you can’t control how people will use your imagery or audio. Researchers must be aware of this fact, and be thoughtful when they are publishing content,” King says.

The researcher say that academics also need to understand the large impact that a single video could have on their personal brand. If their personal views clash with institutional values, there could be pushback from the academic community and repercussions from administrators. Even though tenured faculty members have academic freedom, they may not get a free pass if they use TikTok in ways their colleagues consider out of line, the researchers warn.

What’s more, an outsized social media profile won’t necessarily enhance a scholar’s professional status. “In simple terms, a million followers won't guarantee you tenure or a promotion,” says King.

Above all, it’s a way to spread the word, possibly dispelling popular myths with facts and encouraging an audience to think about a topic from a different perspective. Casey Fiesler, an assistant professor at the University of Colorado Boulder, runs a popular TikTok account that often challenges viewers to consider the problems with Facebook’s domination of the online experience. It’s possible to imagine a teenager finding one of Fiesler’s videos tucked between dance trends and dog tricks and questioning Facebook for the first time, according to King.

“TikTok offers enormous potential for the discovery of critical ideas,” he says. “This is why using TikTok effectively is crucial. Sharing research with an audience outside of the academy brings together people with diverse educational backgrounds. TikTok offers an exciting new way to find like-minded thinkers, makes research accessible, and start important conversations.”

Here are a few of the study’s recommendations for best practices on how scholarly communities can engage:

Keep your videos short and simple: Less than one minute is ideal because online attention spans are shorter than in-person ones
Use storytelling and humour to make your content more accessible: You are competing with all the other content online, so lighten the mood by telling a story or adding unique humour
Find ways to engage people instead of speaking to them: Invite users to try out an experiment for themselves and create a video reply with their results
Get your data from TikTok so you know what’s being tracked. Remember social media lives forever: You might be surprised by how well TikTok knows you. Download your data and decide for yourself if you are comfortable with TikTok having this information and selling it without your knowledge
Be aware that your video or audio may be remixed or repurposed without your permission, unless you change your privacy settings: You might make a sincere video explaining your research that someone else turns into a song or a joke. Decide now if you’re comfortable with that possibility