For greater than a decade, MIT Associate Professor Rafael Gómez-Bombarelli has used artificial intelligence to create latest materials. Because the technology has expanded, so have his ambitions.
Now, the newly tenured professor in materials science and engineering believes AI is poised to remodel science in ways never before possible. His work at MIT and beyond is dedicated to accelerating that future.
“We’re at a second inflection point,” Gómez-Bombarelli says. “The primary one was around 2015 with the primary wave of representation learning, generative AI, and high-throughput data in some areas of science. Those are a number of the techniques I first brought into my lab at MIT. Now I feel we’re at a second inflection point, mixing language and merging multiple modalities into general scientific intelligence. We’re going to have all of the model classes and scaling laws needed to reason about language, reason over material structures, and reason over synthesis recipes.”
Gómez Bombarelli’s research combines physics-based simulations with approaches like machine learning and generative AI to find latest materials with promising real-world applications. His work has led to latest materials for batteries, catalysts, plastics, and organic light-emitting diodes (OLEDs). He has also co-founded multiple corporations and served on scientific advisory boards for startups applying AI to drug discovery, robotics, and more. His latest company, Lila Sciences, is working to construct a scientific superintelligence platform for the life sciences, chemical, and materials science industries.
All of that work is designed to make sure the longer term of scientific research is more seamless and productive than research today.
“AI for science is one of the vital exciting and aspirational uses of AI,” Gómez-Bombarelli says. “Other applications for AI have more downsides and ambiguity. AI for science is about bringing a greater future forward in time.”
From experiments to simulations
Gómez-Bombarelli grew up in Spain and gravitated toward the physical sciences from an early age. In 2001, he won a Chemistry Olympics competition, setting him on an instructional track in chemistry, which he studied as an undergraduate at his hometown college, the University of Salamanca. Gómez-Bombarelli stuck around for his PhD, where he investigated the function of DNA-damaging chemicals.
“My PhD started off experimental, after which I got bitten by the bug of simulation and computer science about halfway through,” he says. “I began simulating the identical chemical reactions I used to be measuring within the lab. I like the way in which programming organizes your brain; it felt like a natural strategy to organize one’s considering. Programming can be loads less limited by what you possibly can do along with your hands or with scientific instruments.”
Next, Gómez-Bombarelli went to Scotland for a postdoctoral position, where he studied quantum effects in biology. Through that work, he connected with Alán Aspuru-Guzik, a chemistry professor at Harvard University, whom he joined for his next postdoc in 2014.
“I used to be one in all the primary people to make use of generative AI for chemistry in 2016, and I used to be on the primary team to make use of neural networks to grasp molecules in 2015,” Gómez-Bombarelli says. “It was the early, early days of deep learning for science.”
Gómez-Bombarelli also began working to eliminate manual parts of molecular simulations to run more high-throughput experiments. He and his collaborators ended up running a whole lot of hundreds of calculations across materials, discovering a whole lot of promising materials for testing.
After two years within the lab, Gómez-Bombarelli and Aspuru-Guzik began a general-purpose materials computation company, which eventually pivoted to deal with producing organic light-emitting diodes. Gómez-Bombarelli joined the corporate full-time and calls it the toughest thing he’s ever done in his profession.
“It was amazing to make something tangible,” he says. “Also, after seeing Aspuru-Guzik run a lab, I didn’t need to turn into a professor. My dad was a professor in linguistics, and I assumed it was a mellow job. Then I saw Aspuru-Guzik with a 40-person group, and he was on the road 120 days a yr. It was insane. I didn’t think I had that sort of energy and creativity in me.”
In 2018, Aspuru-Guzik suggested Gómez-Bombarelli apply for a brand new position in MIT’s Department of Materials Science and Engineering. But, together with his trepidation about a school job, Gómez-Bombarelli let the deadline pass. Aspuru-Guzik confronted him in his office, slammed his hands on the table, and told him, “It’s good to apply for this.” It was enough to get Gómez-Bombarelli to place together a proper application.
Fortunately at his startup, Gómez-Bombarelli had spent a number of time eager about easy methods to create value from computational materials discovery. In the course of the interview process, he says, he was interested in the energy and collaborative spirit at MIT. He also began to understand the research possibilities.
“All the pieces I had been doing as a postdoc and at the corporate was going to be a subset of what I could do at MIT,” he says. “I used to be making products, and I still get to do this. Suddenly, my universe of labor was a subset of this latest universe of things I could explore and do.”
It’s been nine years since Gómez Bombarelli joined MIT. Today his lab focuses on how the composition, structure, and reactivity of atoms impact material performance. He has also used high-throughput simulations to create latest materials and helped develop tools for merging deep learning with physics-based modeling.
“Physics-based simulations make data and AI algorithms recuperate the more data you give them,” Gómez Bombarelli’s says. “There are all types of virtuous cycles between AI and simulations.”
The research group he has built is solely computational — they don’t run physical experiments.
“It’s a blessing because we are able to have an enormous amount of breadth and do a lot of things directly,” he says. “We love working with experimentalists and take a look at to be good partners with them. We also like to create computational tools that help experimentalists triage the ideas coming from AI .”
Gómez-Bombarelli can be still focused on the real-world applications of the materials he invents. His lab works closely with corporations and organizations like MIT’s Industrial Liaison Program to grasp the fabric needs of the private sector and the sensible hurdles of business development.
Accelerating science
As excitement around artificial intelligence has exploded, Gómez-Bombarelli has seen the sector mature. Corporations like Meta, Microsoft, and Google’s DeepMind now often conduct physics-based simulations paying homage to what he was working on back in 2016. In November, the U.S. Department of Energy launched the Genesis Mission to speed up scientific discovery, national security, and energy dominance using AI.
“AI for simulations has gone from something that perhaps could work to a consensus scientific view,” Gómez-Bombarelli says. “We’re at an inflection point. Humans think in natural language, we write papers in natural language, and it seems these large language models which have mastered natural language have opened up the power to speed up science. We’ve seen that scaling works for simulations. We’ve seen that scaling works for language. Now we’re going to see how scaling works for science.”
When he first got here to MIT, Gómez-Bombarelli says he was blown away by how non-competitive things were between researchers. He tries to bring that very same positive-sum considering to his research group, which is made up of about 25 graduate students and postdocs.
“We’ve naturally grown into a very diverse group, with a various set of mentalities,” Gomez-Bombarelli says. “Everyone has their very own profession aspirations and strengths and weaknesses. Determining easy methods to help people be one of the best versions of themselves is fun. Now I’ve turn into the one insisting that folks apply to college positions after the deadline. I assume I’ve passed that baton.”