Northeastern University's College of Science is positioning itself at the forefront of AI-driven materials and drug discovery, developing new machine learning methods while training students to use these technologies ethically and responsibly. The institution's approach goes beyond simply applying AI to existing problems; it's fundamentally rethinking how scientists ask questions and validate answers across chemistry, physics, biology, and genomics.

What Makes Northeastern's AI Materials Research Different?

Unlike many universities that treat AI as a separate discipline, Northeastern integrates artificial intelligence directly into core scientific research. Faculty members are developing novel machine learning methods and applying them in drug discovery, climate science, adaptive robotics, and personalized health. The institution's strength lies in pairing genuine AI fluency with critical thinking, ethical reasoning, and creative collaboration, ensuring students learn to work alongside AI rather than become dependent on it.

The College of Science houses several specialized research centers that leverage AI for breakthrough discoveries. These include the Quantum Materials and Sensing Institute, which accelerates practical quantum materials and technologies from concept to commercialization, and the Center for Marine and Ecological Genomics, which develops an open science ecosystem for marine genomics research using AI advancements to accelerate discoveries from non-model marine organisms.

How Are Researchers Using AI to Decode Disease and Chemistry?

One concrete example of Northeastern's impact involves using AI to predict genetic mutations that cause disease. Professors Penny Beuning and Mary Jo Ondrechen used artificial intelligence to predict which genetic mutations cause OTC deficiency, a deadly genetic disorder, uncovering clues to guide future treatments. This work demonstrates how AI can move beyond pattern recognition to reveal the underlying chemistry behind disease mechanisms.

The research spans multiple domains. Mary Jo Ondrechen's group develops computational methods for genomics, studies how enzymes work, and collaborates in drug discovery using computation. Meanwhile, Srinivas Sridhar, a University Distinguished Professor of Physics, focuses his research on quantitative MRI, drug discovery, and neurovisual science, showing how physics-based approaches complement AI-driven chemistry.

How to Build a Career at the Intersection of AI and Materials Science

• Pursue Specialized Graduate Programs: Northeastern offers MS programs in bioinformatics and nanomedicine, as well as PhD programs that combine AI fluency with domain expertise in chemistry, physics, or biology, preparing students for leadership roles in AI-driven research.
• Engage in Experiential Learning: The College of Science pioneers experiential models that let students apply AI to real challenges while shaping the responsible standards institutions worldwide follow, including co-op opportunities in research centers like the Center for Marine and Ecological Genomics.
• Develop Ethical and Critical Thinking Skills: Beyond technical training, students pair AI literacy with ethical reasoning and creative collaboration, learning not only how to use these technologies but how to wield them responsibly in scientific and commercial contexts.

Why Physics and AI Are Becoming Inseparable in Materials Science

A surprising insight emerging from Northeastern's research is that the relationship between AI and physics runs both directions. James Halverson, an Associate Professor of Physics, explained the deeper connection:

"The basic premise is that AI can help us do better physics, and something that is less expected is that physics can also help us understand AI better," said Halverson.

James Halverson, Associate Professor of Physics at Northeastern University

This bidirectional relationship is reshaping how researchers approach materials discovery. Rather than treating AI as a black box that generates predictions, physicists are using fundamental principles from quantum mechanics and field theory to make AI models more interpretable and reliable. Professors like Fabian Ruehle and Ning Bao incorporate AI, string theory, and mathematics into their research, bridging theoretical physics with practical machine learning applications.

The faculty roster reflects this interdisciplinary approach. Paul Hand, an Assistant Professor of Mathematics jointly appointed with Khoury College of Computer Sciences, researches theory and algorithms for AI and machine learning in the context of vision and imaging. Jose Perea, an Associate Professor of Mathematics, is passionate about using nonstandard mathematical ideas to solve problems in data science and machine learning. These researchers are not simply applying existing AI tools; they are developing new mathematical frameworks that make AI more powerful and trustworthy.

How Is Northeastern Preparing Students for Responsible AI Innovation?

Education is central to Northeastern's strategy. The institution recognizes that as AI redefines what's possible in materials science and drug discovery, it doesn't diminish what makes human scientists essential; it makes those qualities more critical. Students learn to combine AI fluency with the judgment, creativity, and ethical reasoning that machines cannot replicate.

The College of Science offers multiple pathways for students to develop AI expertise. Undergraduate majors, MS programs, and PhD programs all integrate AI into their curricula. Graduate students like Megha Prasad, an MS in Bioinformatics student, explore the intersection of biology and data science through co-ops in specialized research centers, gaining hands-on experience with real-world problems in materials and drug discovery.

Beyond technical training, Northeastern emphasizes the responsible development and deployment of AI in science. Faculty members translate their research into impact and into the classroom, pioneering experiential models that let students apply AI to real challenges while shaping the responsible standards institutions worldwide follow. This approach ensures that the next generation of materials scientists and chemists will be equipped not only to innovate but to do so ethically and transparently.

As AI continues to accelerate materials discovery and drug development, institutions like Northeastern are demonstrating that the future of science depends not on replacing human expertise with algorithms, but on creating a new generation of scientists who understand both the power and the limitations of artificial intelligence, and who can use these tools to solve humanity's most pressing challenges.