For over a decade, MIT Associate Professor Rafael Gómez-Bombarelli has been at the forefront of using artificial intelligence to innovate new materials. As AI technology has advanced, so too have Gómez-Bombarelli’s ambitions. Now a newly tenured professor in materials science and engineering, he believes AI is on the brink of transforming science in unprecedented ways. His work at MIT and beyond is dedicated to accelerating this future.
“We’re at a second inflection point,” Gómez-Bombarelli asserts.
“The first one was around 2015 with the first wave of representation learning, generative AI, and high-throughput data in some areas of science. Those are some of the techniques I first brought into my lab at MIT. Now I think we’re at a second inflection point, mixing language and merging multiple modalities into general scientific intelligence.”
Gómez-Bombarelli’s research merges physics-based simulations with machine learning and generative AI to discover new materials with significant real-world applications. His work has led to breakthroughs in materials for batteries, catalysts, plastics, and organic light-emitting diodes (OLEDs). He has co-founded multiple companies and served on scientific advisory boards for startups applying AI to fields like drug discovery and robotics. His latest venture, Lila Sciences, aims to build a scientific superintelligence platform for the life sciences, chemical, and materials science industries.
From Experiments to Simulations
Gómez-Bombarelli’s journey into the world of AI and simulations began in Spain, where his early interest in physical sciences led him to win a Chemistry Olympics competition in 2001. This achievement set him on an academic path in chemistry at the University of Salamanca, where he later pursued a PhD investigating the function of DNA-damaging chemicals.
“My PhD started out experimental, and then I got bitten by the bug of simulation and computer science about halfway through,” he recalls.
“I started simulating the same chemical reactions I was measuring in the lab. I like the way programming organizes your brain; it felt like a natural way to organize one’s thinking.”
After completing his PhD, Gómez-Bombarelli moved to Scotland for a postdoctoral position, studying quantum effects in biology. This work connected him with Alán Aspuru-Guzik, a Harvard University chemistry professor, leading to his next postdoc in 2014. During this time, Gómez-Bombarelli became one of the pioneers in using generative AI for chemistry, leveraging neural networks to understand molecules.
Building a Computational Future
In 2018, encouraged by Aspuru-Guzik, Gómez-Bombarelli applied for a position at MIT’s Department of Materials Science and Engineering. Despite initial hesitations about a faculty role, he was drawn to MIT’s collaborative environment and the expansive research possibilities it offered.
Today, his lab focuses on the impact of atomic composition, structure, and reactivity on material performance. The group is solely computational, allowing them to explore a wide range of projects simultaneously. “It’s a blessing because we can have a huge amount of breadth and do lots of things at once,” Gómez-Bombarelli notes.
His lab collaborates closely with companies and organizations such as MIT’s Industrial Liaison Program to address the material needs of the private sector and the challenges of commercial development.
Accelerating Science with AI
As AI technology has gained momentum, Gómez-Bombarelli has witnessed the field’s maturation. Companies like Meta, Microsoft, and Google’s DeepMind now regularly conduct physics-based simulations similar to those he worked on in 2016. In a significant move, the U.S. Department of Energy launched the Genesis Mission to leverage AI for scientific discovery and national security.
“AI for simulations has gone from something that maybe could work to a consensus scientific view,” Gómez-Bombarelli observes.
“Humans think in natural language, we write papers in natural language, and it turns out these large language models that have mastered natural language have opened up the ability to accelerate science.”
Reflecting on his time at MIT, Gómez-Bombarelli is struck by the non-competitive nature of the research environment. He fosters this positive-sum thinking within his research group, which comprises about 25 graduate students and postdocs. “We’ve naturally grown into a really diverse group, with a diverse set of mentalities,” he says.
As AI continues to evolve, Gómez-Bombarelli’s work stands as a testament to the transformative potential of technology in scientific research. His efforts are not only advancing material science but also paving the way for a future where AI plays a central role in accelerating scientific discovery.
